A construction safety early warning system and method based on artificial intelligence

Abstract

The present invention relates to the field of construction supervision technology, and specifically to an artificial intelligence-based construction safety early warning system and method thereof, the system comprising: a data acquisition layer collects various construction data of different areas of a construction site in real time; a risk identification layer retrieves corresponding AI models according to the construction stage and the category of construction data, identifies potential safety risks in each area, and when a certain area has a safety risk, controls the on-site alarm equipment in the area to send out an alarm message; a visualization display layer generates a three-dimensional model of the construction site at different construction stages, and identifies the spatial positions of construction personnel and construction equipment in the construction site according to the construction data, and dynamically displays the spatial position relationship between the construction personnel and construction equipment in the three-dimensional model; when a safety risk exists in a certain area, displays relevant warning information at the corresponding position of the three-dimensional model. The present invention can provide more comprehensive and timely safety early warnings for different construction stages of a construction site.

Description

Technical Field

[0001] The present invention relates to the technical field of construction supervision, and more specifically to an artificial intelligence-based building construction safety early warning system and method thereof. Background Art

[0002] There are a large number of construction workers, construction tools and construction materials distributed at the construction site, which makes the construction environment complex, dynamic and uncertain. Therefore, there are many different types of safety risks, such as the risk of falling from heights, collision, electric shock, mechanical injury and fire.

[0003] At present, it is common to install fixed monitoring equipment in specific places and use image recognition technology to identify the construction status of workers or equipment in the place to analyze whether there are safety risks in the construction behavior. However, this method often only focuses on the single monitoring of people or equipment in specific scenarios, and it is difficult to cover the wider work behavior and spatial distribution of the construction site. At the same time, since the risk factors in different construction stages will also change accordingly, the current inherent monitoring method cannot be dynamically adjusted according to the construction stage.

[0004] Therefore, how to provide more comprehensive and timely safety warnings for construction sites is a technical problem that technical personnel in this field urgently need to solve. Summary of the invention

[0005] In view of this, the present invention provides an artificial intelligence-based construction safety early warning system and method thereof, which can provide more comprehensive and timely safety early warnings for different construction stages of a construction site.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] In a first aspect, the present invention provides a construction safety early warning system based on artificial intelligence, comprising:

[0008] The data collection layer is used to collect various construction data from different areas of the construction site in real time;

[0009] The risk identification layer is used to call the corresponding AI model according to the construction stage and construction data category to identify the potential safety risks in each area. When there is a safety risk in a certain area, the on-site alarm equipment in the area is controlled to issue an alarm message;

[0010] The visualization display layer is used to generate three-dimensional models of the construction site at different construction stages, and identify the spatial positions of construction personnel and construction equipment on the construction site based on construction data, and dynamically display the spatial position relationship between construction personnel and construction equipment in the three-dimensional model; when there is a safety risk in a certain area, relevant warning information is displayed at the corresponding position of the three-dimensional model.

[0011] Furthermore, the data collection layer includes: a sensor network, a camera and a wearable device;

[0012] Wherein, the sensor network is used to collect one or more of structural data, environmental data, fire characteristic data, equipment data and power data in different areas of the construction site;

[0013] The camera is used to collect image data of different areas of the construction site;

[0014] The wearable device is used to collect physiological data and location information of construction workers.

[0015] Furthermore, the risk identification layer includes: a construction phase division module, an algorithm model storage module, a data screening module and a phase risk identification module;

[0016] The construction phase division module is used to divide the construction phase into a site survey and clearing phase, a foundation construction phase, a main structure construction phase, a greening construction phase and a decoration construction phase;

[0017] The algorithm model storage module stores typical AI models corresponding to different construction stages;

[0018] The data screening module is used to screen out data associated with the current construction stage from all the construction data collected by the data collection layer;

[0019] The stage risk identification module is used to retrieve the typical AI model corresponding to the current construction stage from the algorithm model storage module, and perform safety risk identification on the screened data based on the retrieved typical AI model.

[0020] Furthermore, during the site survey and cleanup phase, the data screening module screens out geological radar data and magnetic field detection data from the construction data; the risk identification module of the phase adopts the pre-trained first AI model to analyze the screened data to identify hidden dangers of underground pipeline damage, unknown geological conditions, unexploded munitions or other relics;

[0021] During the foundation construction phase, the data screening module screens out structural data and image data from the construction data; the stage risk identification module uses a pre-trained second AI model to analyze the screened data to identify whether there is a risk of foundation pit collapse and an object impact risk;

[0022] During the main structure construction phase, the data screening module screens image data from the construction data; the risk identification module uses a pre-trained third AI model to analyze the image data to identify whether there are risks of high-altitude operations, template collapse, crane overturning, and falling objects in each area;

[0023] During the greening construction stage, the data screening module screens image data from the construction data; the risk identification module uses the pre-trained fourth AI model to analyze the image data, identify the greening area, and determine whether there is a safety hazard in the relative position relationship between the construction equipment and the construction personnel in the greening area;

[0024] During the decoration construction stage, the data screening module filters out fire characteristic data from the construction data; the stage risk identification module adopts the pre-trained fifth AI model to analyze the filtered data, identify whether there is a fire risk, and predict the fire risk level based on the decoration materials in different areas.

[0025] Furthermore, the stage risk identification module also includes a personnel risk identification unit, an equipment risk identification unit and an electric power risk identification unit;

[0026] The personnel risk identification unit is used to pre-demarcate an electronic fence in each area as a dangerous work area during each construction phase, analyze the image data of each area of ​​the construction site, determine whether the construction personnel are wearing compliant clothing, and determine whether the construction personnel have invaded the dangerous work area based on the pre-demarcated electronic fence. When a construction personnel invades the dangerous work area, the alarm device in the dangerous work area is controlled to send a corresponding alarm message;

[0027] The equipment risk identification unit is connected to all construction equipment at the construction site. It is used to determine whether the operating data of each construction equipment exceeds the threshold at each construction stage, and when the operating data of a certain construction equipment exceeds the threshold, control the alarm device in the area where the construction equipment is located to send out corresponding alarm information;

[0028] The power risk identification unit is connected to all distribution boxes at the construction site. It is used to analyze the fluctuations in the current and voltage data of the distribution boxes and the temperature data of key points at each construction stage. When the current or voltage data of a distribution box fluctuates abnormally, or the temperature of the key point exceeds the threshold, it is judged that there is a fire risk. At this time, the main power supply of the distribution box is disconnected, and the alarm equipment in the area to which the distribution box belongs is controlled to send out corresponding alarm information.

[0029] Furthermore, the personnel risk identification unit is also used to identify facial image information of construction workers in each area and determine whether there are illegal intruders in each area.

[0030] Furthermore, the stage risk identification module further includes: an environmental risk identification unit;

[0031] The environmental risk identification unit is used to calculate the environmental safety risk assessment value of each area based on the dust, noise, temperature, wind speed and frequency of construction personnel activities in each area of ​​the construction site. If the environmental safety risk assessment value of an area exceeds the threshold, it is considered that there is an environmental safety risk in the area.

[0032] Furthermore, for a certain area, the calculation method of its environmental safety risk assessment value is:

[0033] ;

[0034] in, represents the environmental safety risk assessment value of the ith region, represents the dust data of the ith area, represents the noise data of the ith region, represents the degree data of the ith region, represents the wind speed data of the ith area, represents the activity frequency of construction workers in the ith area, , , , , Respectively represent the weight coefficients of dust, noise, temperature, wind speed and construction workers' activity frequency; represents the error term.

[0035] Furthermore, the visualization display layer includes a three-dimensional model generation module, a spatial association module and a warning module;

[0036] The 3D model generation module is used to generate BIM 3D models of various areas of the construction site at different construction stages according to a preset scale;

[0037] The spatial association module is used to identify the real spatial position of each construction worker and construction equipment according to the positioning devices equipped by the construction workers and construction equipment, convert the real spatial position according to the scale, or identify the pixel position of each construction worker and construction equipment from the image data of each area of ​​the construction site, convert the pixel position into a spatial position according to the coordinate conversion formula and the scale, obtain the spatial position of the construction workers and construction equipment in the BIM three-dimensional model, and dynamically update it;

[0038] The warning module is used to render the corresponding position of the three-dimensional model in color when there is a safety risk in a certain area, and pop up a warning information list to display the location, category and construction personnel information of the safety risk area in the list.

[0039] In a second aspect, the present invention provides a construction safety early warning method based on artificial intelligence, which is applicable to the system as described above, comprising the following steps:

[0040] Collect various construction data from different areas of the construction site in real time;

[0041] According to the construction stage and construction data category, the corresponding AI model is called up to identify the potential safety risks in each area. When there is a safety risk in a certain area, the on-site alarm equipment in the area is controlled to send out an alarm message;

[0042] Generate a three-dimensional model of the construction site at different construction stages, identify the spatial positions of construction personnel and equipment on the construction site based on construction data, and dynamically display the spatial position relationship between construction personnel and equipment in the three-dimensional model; when there is a safety risk in a certain area, display relevant warning information at the corresponding position of the three-dimensional model.

[0043] It can be seen from the above technical solutions that, compared with the prior art, the present invention has the following beneficial effects:

[0044] 1. The present invention takes into account that the safety risk factors of the construction site are different at different construction stages of the building. From the site survey and cleaning stage to the decoration and construction stage, each link is accompanied by its specific safety challenges. By screening out typical data of corresponding categories at different construction stages and adopting corresponding AI models to analyze the typical data, the safety risk categories at different construction stages are determined, thereby focusing on the risk factors at different construction stages to ensure construction safety.

[0045] 2. The present invention realizes comprehensive and intuitive control of the construction dynamics and early warning status of the entire construction site by performing three-dimensional modeling of the construction site at different construction stages, importing the spatial positions of the construction personnel and construction equipment at the construction site into the three-dimensional model, and displaying safety risk information at the corresponding positions of the three-dimensional model. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0047] Figure 1 A structural block diagram of the artificial intelligence-based construction safety early warning system provided by the present invention;

[0048] Figure 2A flow chart of the artificial intelligence-based construction safety early warning method provided by the present invention. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] like Figure 1 As shown, the embodiment of the present invention discloses a construction safety early warning system based on artificial intelligence, including:

[0051] The data collection layer is used to collect various construction data from different areas of the construction site in real time;

[0052] The risk identification layer is used to call the corresponding AI model according to the construction stage and construction data category to identify the potential safety risks in each area. When there is a safety risk in a certain area, the on-site alarm equipment in the area is controlled to issue an alarm message;

[0053] The visualization display layer is used to generate three-dimensional models of the construction site at different construction stages, and identify the spatial positions of construction personnel and construction equipment on the construction site based on construction data, and dynamically display the spatial position relationship between construction personnel and construction equipment in the three-dimensional model; when there is a safety risk in a certain area, relevant warning information is displayed at the corresponding position of the three-dimensional model.

[0054] The above layers are further described below.

[0055] (1) The data collection layer includes sensor networks, cameras, and wearable devices;

[0056] The sensor network is used to collect one or more of structural data, environmental data, fire characteristic data, equipment data and power data in different areas of the construction site; the structural data includes one or more of geological radar data, magnetic field detection data, stress information, strain information, settlement information, inclination information, soil displacement, water level change and pressure information of the construction site;

[0057] The camera is used to collect image data from different areas of the construction site;

[0058] Wearable devices are used to collect physiological data and location information of construction workers.

[0059] (2) The risk identification layer includes: construction stage division module, algorithm model storage module, data screening module and stage risk identification module;

[0060] The construction phase division module is used to divide the construction phase into site investigation and clearing phase, foundation construction phase, main structure construction phase, greening construction phase and decoration construction phase.

[0061] The algorithm model storage module stores typical AI models corresponding to different construction stages;

[0062] The data screening module is used to screen out data associated with the current construction stage from all construction data collected by the data acquisition layer as typical data; in different construction stages, corresponding sensor equipment is arranged in different areas of the construction site, and the data screening module screens out data types with a relatively high degree of relevance to the current stage from the data acquisition layer for subsequent risk analysis.

[0063] The stage risk identification module is used to retrieve the typical AI model corresponding to the current construction stage from the algorithm model storage module, and identify safety risks of the screened data based on the retrieved typical AI model.

[0064] Specifically, during the site survey and cleanup phase, the data screening module screens out geological radar data and magnetic field detection data from the construction data; the stage risk identification module uses the pre-trained first AI model to analyze the screened data to identify underground pipeline damage, unknown geological conditions, unexploded ordnance or other remnant hazards. The first AI model is a supervised classification algorithm based on machine learning, such as a support vector machine. During the training process, geological radar data and magnetic field detection data under conditions of underground pipeline damage, unknown geological conditions, unexploded ordnance or other remnant hazards can be collected from the existing geological database as a data set, the data samples are labeled, and the supervised classification algorithm is trained to achieve risk identification of various foundation conditions.

[0065] During the foundation construction phase, the data screening module screens out structural data (such as stress information, strain information, soil displacement, and water level changes, etc.) and image data from the construction data; the stage risk identification module uses a pre-trained second AI model to analyze the screened structural data to identify whether there is a risk of foundation pit collapse, and analyzes the image data to identify whether there is a risk of being hit by objects during the excavation process. The second AI model can adopt a deep neural network architecture, which contains two sub-models, which respectively identify risks of structural data and image data. The training process retrieves structural data from historical foundation pit collapse situations as a data set, and trains one of the sub-models to identify foundation pit risks. For the other sub-model, historical image data or some artificially created risk images can be used as a data set for training.

[0066] During the main structure construction phase, the data screening module filters out image data from the construction data; the stage risk identification module uses the pre-trained third AI model to analyze the image data to identify whether there are risks of high-altitude operations in each area (such as unsafe behaviors of construction workers during high-altitude operations and the status of high-altitude operation equipment, such as not wearing safety belts, improper hoisting operations, etc.), template collapse risks, crane overturning risks, and object falling risks. The third AI model can use a convolutional neural network architecture, which has obvious advantages in image processing.

[0067] During the greening construction phase, the data screening module selects image data from the construction data; the stage risk identification module uses the pre-trained fourth AI model to analyze the image data, identify the greening area, and determine whether there are safety hazards in the posture of construction equipment in the greening area or the relative position relationship between construction equipment and construction personnel. The fourth AI model also uses a convolutional neural network architecture.

[0068] During the renovation and construction phase, the data screening module selects fire characteristic data from the construction data; the stage risk identification module uses the pre-trained fifth AI model to analyze the screened data, identify whether there is a fire risk, and predict the fire risk level based on the decoration materials in different areas. The fifth AI model can adopt a deep neural network architecture.

[0069] Similarly, for the third AI model, the fourth AI model and the fifth AI model, their training samples can be obtained from an existing building database, or can be artificially produced or generated by simulation.

[0070] In addition to processing specific risk identification for specific construction stages, the risk identification layer also performs some common functions in each stage. Specifically, the risk identification layer also includes a conventional risk identification module, which includes a personnel risk identification unit, an equipment risk identification unit, a power risk identification unit, and an environmental risk identification unit.

[0071] The personnel risk identification unit is used to pre-demarcate electronic fences in each area as dangerous work areas (such as temporary power areas, lifting areas, hot work areas, etc.) during each construction phase, analyze the image data of each area on the construction site, determine whether the construction workers are wearing compliant clothing, and determine whether the construction workers have invaded the dangerous work area based on the pre-demarcated electronic fences. When a construction worker invades the dangerous work area, the alarm equipment in the dangerous work area is controlled to send out corresponding alarm information, which can be an audible and visual alarm or a voice alarm. The personnel risk identification unit is also used to identify the facial image information of construction workers in each area, determine whether there are illegal intruders in each area, and ensure that each construction worker is active in their respective areas.

[0072] Furthermore, the personnel risk identification unit also monitors the current health status of the construction workers in combination with the physiological information collected by the wearable devices worn by the construction workers.

[0073] The equipment risk identification unit is connected to all construction equipment at the construction site. It is used to determine whether the operating data of each construction equipment exceeds the threshold at each construction stage. When the operating data of a certain construction equipment exceeds the threshold, it controls the alarm device in the area where the construction equipment is located to send out corresponding alarm information.

[0074] The power risk identification unit is connected to all distribution boxes at the construction site. It is used to analyze the fluctuations in the current and voltage data of the distribution boxes and the temperature data of key points at each construction stage. When the current or voltage data of a distribution box fluctuates abnormally, or the temperature of the key point exceeds the threshold, it is judged that there is a fire risk. At this time, the main power supply of the distribution box is disconnected, and the alarm equipment in the area to which the distribution box belongs is controlled to send out corresponding alarm information.

[0075] The environmental risk identification unit is used to calculate the environmental safety risk assessment value of each area based on the dust, noise, temperature, wind speed and frequency of construction personnel activities in each area of ​​the construction site. If the environmental safety risk assessment value of an area exceeds the threshold, it is considered that there is an environmental safety risk in that area.

[0076] For a certain area, the environmental safety risk assessment value is calculated as follows:

[0077] ;

[0078] in, represents the environmental safety risk assessment value of the ith region, represents the dust data of the ith area, represents the noise data of the ith region, represents the degree data of the ith region, represents the wind speed data of the ith area, represents the activity frequency of construction workers in the ith area, , , , , Respectively represent the weight coefficients of dust, noise, temperature, wind speed and construction workers' activity frequency; represents the error term.

[0079] (3) The visualization layer includes a 3D model generation module, a spatial association module, and a warning module;

[0080] The 3D model generation module is used to generate BIM 3D models of various areas of the construction site at different construction stages according to a preset scale, and retrieve the 3D model of the corresponding stage according to the current construction stage;

[0081] The spatial association module is used to identify the real spatial position of each construction worker and construction equipment according to the positioning devices equipped by the construction workers and construction equipment, convert the real spatial position according to the scale, or identify the pixel position of each construction worker and construction equipment from the image data of each area of ​​the construction site, convert the pixel position into a spatial position according to the coordinate conversion formula and the scale, obtain the spatial position of the construction workers and construction equipment in the BIM three-dimensional model, and update it dynamically;

[0082] The warning module is used to render the corresponding position of the 3D model in color when there is a safety risk in a certain area, and pop up a warning information list, which displays the location, category and construction personnel information of the safety risk area.

[0083] More advantageously, the system of the present invention also includes a mobile mini-program for on-site construction personnel to record on-site events, call for help with one click, associate construction equipment, view construction information, and view warning information.

[0084] In one embodiment, the system of the present invention also includes a data storage layer for storing massive amounts of sensor data, video image data, wearable data, warning data, etc., and storing them by category according to date.

[0085] In other embodiments, the system of the present invention may also include a risk management and control layer, which is used to generate corresponding management and control measures according to the risk category when a safety risk occurs in a certain area, and send them to the mobile terminal of the corresponding construction personnel.

[0086] In other embodiments, Figure 2 As shown, the present invention also discloses an artificial intelligence-based construction safety early warning method, which is applicable to the system as described above, and comprises the following steps:

[0087] S1. Real-time collection of various construction data in different areas of the construction site;

[0088] S2. According to the construction stage and construction data category, the corresponding AI model is retrieved to identify the potential safety risks in each area. When there is a safety risk in a certain area, the on-site alarm equipment in the area is controlled to send out an alarm message;

[0089] S3. Generate a three-dimensional model of the construction site at different construction stages, identify the spatial positions of construction personnel and construction equipment at the construction site based on the construction data, and dynamically display the spatial position relationship between the construction personnel and construction equipment in the three-dimensional model; when there is a safety risk in a certain area, display relevant warning information at the corresponding position of the three-dimensional model.

[0090] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0091] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A construction safety early warning system based on artificial intelligence, characterized in that: include: The data collection layer is used to collect various construction data from different areas of the construction site in real time; The risk identification layer is used to call the corresponding AI model according to the construction stage and construction data category to identify the potential safety risks in each area. When there is a safety risk in a certain area, the on-site alarm equipment in the area is controlled to issue an alarm message; The visualization layer is used to generate a 3D model of the construction site at different construction stages, identify the spatial positions of construction personnel and construction equipment on the construction site based on the construction data, and dynamically display the spatial position relationship between the construction personnel and construction equipment in the 3D model; when there is a safety risk in a certain area, relevant warning information is displayed at the corresponding position of the 3D model; The risk identification layer includes: a construction stage division module, an algorithm model storage module, a data screening module and a stage risk identification module; The construction phase division module is used to divide the construction phase into a site survey and clearing phase, a foundation construction phase, a main structure construction phase, a greening construction phase and a decoration construction phase; The algorithm model storage module stores typical AI models corresponding to different construction stages; The data screening module is used to screen out data associated with the current construction stage from all the construction data collected by the data collection layer; The stage risk identification module is used to retrieve the typical AI model corresponding to the current construction stage from the algorithm model storage module, and identify safety risks on the screened data based on the retrieved typical AI model, so as to focus on specific risk factors existing in different construction stages.

2. The artificial intelligence-based construction safety early warning system according to claim 1 is characterized in that: The data collection layer includes: sensor networks, cameras and wearable devices; Wherein, the sensor network is used to collect one or more of structural data, environmental data, fire characteristic data, equipment data and power data in different areas of the construction site; The camera is used to collect image data of different areas of the construction site; The wearable device is used to collect physiological data and location information of construction workers.

3. The artificial intelligence-based construction safety early warning system according to claim 1 is characterized in that: During the site survey and cleanup phase, the data screening module screens out geological radar data and magnetic field detection data from the construction data; the risk identification module uses the pre-trained first AI model to analyze the screened data to identify hidden dangers of underground pipeline damage, unknown geological conditions, unexploded munitions or other relics; During the foundation construction phase, the data screening module screens out structural data and image data from the construction data; the stage risk identification module uses a pre-trained second AI model to analyze the screened data to identify whether there is a risk of foundation pit collapse and an object impact risk; During the main structure construction phase, the data screening module screens image data from the construction data; the risk identification module uses a pre-trained third AI model to analyze the image data to identify whether there are risks of high-altitude operations, template collapse, crane overturning, and falling objects in each area; During the greening construction stage, the data screening module screens image data from the construction data; the risk identification module uses the pre-trained fourth AI model to analyze the image data, identify the greening area, and determine whether there is a safety hazard in the relative position relationship between the construction equipment and the construction personnel in the greening area; During the decoration construction stage, the data screening module filters out fire characteristic data from the construction data; the stage risk identification module adopts the pre-trained fifth AI model to analyze the filtered data, identify whether there is a fire risk, and predict the fire risk level based on the decoration materials in different areas.

4. The artificial intelligence-based construction safety early warning system according to claim 3 is characterized in that: The risk identification layer also includes a conventional risk identification module; The conventional risk identification module includes: a personnel risk identification unit, an equipment risk identification unit and an electric power risk identification unit; The personnel risk identification unit is used to pre-demarcate an electronic fence in each area as a dangerous work area during each construction phase, analyze the image data of each area of ​​the construction site, determine whether the construction personnel are wearing compliant clothing, and determine whether the construction personnel have invaded the dangerous work area based on the pre-demarcated electronic fence. When a construction personnel invades the dangerous work area, the alarm device in the dangerous work area is controlled to send a corresponding alarm message; The equipment risk identification unit is connected to all construction equipment at the construction site. It is used to determine whether the operating data of each construction equipment exceeds the threshold at each construction stage, and when the operating data of a certain construction equipment exceeds the threshold, control the alarm device in the area where the construction equipment is located to send out corresponding alarm information; The power risk identification unit is connected to all distribution boxes at the construction site. It is used to analyze the fluctuations in the current and voltage data of the distribution boxes and the temperature data of key points at each construction stage. When the current or voltage data of a distribution box fluctuates abnormally, or the temperature of the key point exceeds the threshold, it is judged that there is a fire risk. At this time, the main power supply of the distribution box is disconnected, and the alarm equipment in the area to which the distribution box belongs is controlled to send out corresponding alarm information.

5. The artificial intelligence-based construction safety early warning system according to claim 4 is characterized in that: The personnel risk identification unit is also used to identify the facial image information of the construction personnel in each area and determine whether there are illegal intruders in each area.

6. The artificial intelligence-based construction safety early warning system according to claim 4 is characterized in that: The conventional risk identification module further includes: an environmental risk identification unit; The environmental risk identification unit is used to calculate the environmental safety risk assessment value of each area based on the dust, noise, temperature, wind speed and frequency of construction personnel activities in each area of ​​the construction site. If the environmental safety risk assessment value of an area exceeds the threshold, it is considered that there is an environmental safety risk in the area.

7. The artificial intelligence-based construction safety early warning system according to claim 5 is characterized in that: For a certain area, the environmental safety risk assessment value is calculated as follows: F i =α1D i +α2N i +α3T i +α4W i +α5P i +ξ; Among them, F i represents the environmental safety risk assessment value of the ith region, D i represents the dust data of the ith area, N i represents the noise data of the ith region, T i represents the degree data of the ith region, W i represents the wind speed data of the ith area, P i represents the activity frequency of construction workers in the ith area; α1, α2, α3, α4, and α5 represent the weight coefficients of dust, noise, temperature, wind speed, and activity frequency of construction workers, respectively; ξ represents the error term.

8. The artificial intelligence-based construction safety early warning system according to claim 1 is characterized in that: The visualization display layer includes a three-dimensional model generation module, a spatial association module and a warning module; The 3D model generation module is used to generate BIM 3D models of various areas of the construction site at different construction stages according to a preset scale; The spatial association module is used to identify the real spatial position of each construction worker and construction equipment according to the positioning devices equipped by the construction workers and construction equipment, convert the real spatial position according to the scale, or identify the pixel position of each construction worker and construction equipment from the image data of each area of ​​the construction site, convert the pixel position into a spatial position according to the coordinate conversion formula and the scale, obtain the spatial position of the construction workers and construction equipment in the BIM three-dimensional model, and dynamically update it; The warning module is used to render the corresponding position of the three-dimensional model in color when there is a safety risk in a certain area, and pop up a warning information list to display the location, category and construction personnel information of the safety risk area in the list.

9. A construction safety early warning method based on artificial intelligence, characterized in that: It is applicable to the system according to any one of claims 1 to 8, comprising the following steps: Collect various construction data from different areas of the construction site in real time; According to the construction stage and construction data category, the corresponding AI model is called up to identify the potential safety risks in each area. When there is a safety risk in a certain area, the on-site alarm equipment in the area is controlled to send out an alarm message; Generate a three-dimensional model of the construction site at different construction stages, identify the spatial positions of construction personnel and construction equipment on the construction site based on construction data, and dynamically display the spatial position relationship between construction personnel and construction equipment in the three-dimensional model; when there is a safety risk in a certain area, display relevant warning information at the corresponding position of the three-dimensional model.

Images