Multi-machine cooperative automatic construction control system for intelligent building machinery

Abstract

The invention, which relates to the technical field of the building machinery control system, discloses an intelligent building machinery multi-machine cooperation automatic construction control system comprising a data acquisition unit, a risk assessment unit and an emergency response unit. Multi-source data such as construction site images, personnel and machinery positions and operation parameters can be accurately collected in real time, solid support is provided for risk assessment, a risk assessment unit is combined, a deep learning algorithm and a computer vision technology are applied, personnel identities are efficiently recognized, the safety equipment wearing condition is detected, a multi-source data fusion analysis model is constructed, and the risk assessment efficiency is improved. According to the method, the risk is quantitatively evaluated, and accurate early warning information is generated, so that all-directional and real-time monitoring and intelligent management of the construction site are realized, the construction safety is effectively improved, the accident probability is reduced, multi-machine collaborative operation is optimized, the construction efficiency is improved, and a scientific decision basis is provided for management personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of construction machinery control systems, and in particular to an intelligent construction machinery multi-machine collaborative automated construction control system. Background Art

[0002] In large-scale construction projects, multiple different types of construction machinery are often required to work together to complete complex construction tasks;

[0003] Traditional construction management methods rely primarily on manual inspections and empirical judgment, resulting in untimely and incomplete information acquisition, subjective risk assessments, and delayed emergency responses. This not only increases safety hazards during construction but also leads to low construction efficiency and severe waste of resources. For example, traditional methods often struggle to provide real-time and comprehensive monitoring of construction workers' safety equipment, resulting in disastrous consequences should a safety incident occur.

[0004] In addition, with the rapid development of technologies such as the Internet of Things, big data, and artificial intelligence, it has become possible to apply these advanced technologies to the field of construction and realize intelligent and automated management of the construction process. However, although there are some intelligent management systems for single links or single equipment on the market, there is a lack of a system solution that can integrate multi-source data to achieve multi-machine collaboration and comprehensive management of personnel and equipment safety.

[0005] In view of this, the present invention proposes an intelligent construction machinery multi-machine collaborative automated construction control system to make up for and improve the shortcomings of the existing technology. Summary of the Invention

[0006] In order to solve the above technical problems, the present invention provides an intelligent construction machinery multi-machine collaborative automated construction control system to solve the corresponding technical problems raised in the above background technology.

[0007] To achieve the above objectives, the technical solution adopted by the present invention is: an intelligent construction machinery multi-machine collaborative automated construction control system, comprising: a data acquisition unit, a risk assessment unit and an emergency response unit;

[0008] The data acquisition unit includes an image data acquisition module, a position data acquisition module and an equipment data acquisition module, which collects image data of the construction site in real time through the image data acquisition module and sends the image data to the risk assessment unit;

[0009] The location data acquisition module acquires the location information of construction personnel and construction machinery in real time, and sends the location information of construction personnel and construction machinery to the risk assessment unit;

[0010] The equipment data acquisition module monitors various operating parameters of the construction machinery in real time and outputs them as real-time operating parameters, which are then sent to the risk assessment unit;

[0011] The risk assessment unit includes a personnel identification module, a security detection module and a cross-analysis module. The personnel identification module is used to acquire image data and, in combination with a deep learning algorithm, construct a personnel target detection and identity recognition model to obtain personnel category labels and identity identification information;

[0012] The safety detection module is used to acquire and process image data, build a safety detection model based on computer vision technology, detect whether people in the image data are wearing safety equipment, and perform statistical analysis based on the safety equipment wearing detection results to generate a safety equipment wearing report;

[0013] The cross-analysis module is used to obtain the location information and real-time operating parameters of construction personnel and construction machinery, and to build a multi-source data fusion analysis model based on personnel category labels and identity information as well as safety equipment wearing status reports. It also conducts in-depth cross-analysis to calculate a comprehensive risk score R, and quantitatively assesses the risk using a preset risk threshold A to generate risk warning information.

[0014] Preferably, the image data is acquired through a high-definition camera array installed at the construction site, the location information of the construction personnel and construction machinery is acquired through various UWB base stations deployed at the construction site in combination with ultra-wideband positioning technology, and the real-time operating parameters are acquired through a sensor group installed on the construction machinery, the sensor group including an angle sensor, a speed sensor, a pressure sensor and a temperature sensor, and the real-time operating parameters include angle θ, speed v, pressure p and temperature t.

[0015] As a preferred method, the specific process of obtaining the location information of construction personnel and construction machinery is as follows:

[0016] S101. Deploy UWB base stations one by one according to a construction area distribution map of the construction site, establish a three-dimensional coordinate system for the UWB base stations based on the construction area distribution map, obtain spatial coordinate data of the actual distribution locations of the UWB base stations, and mark the actual locations of the UWB base stations one by one in the three-dimensional coordinate system of the UWB base stations;

[0017] S102. Require construction workers to wear helmets and wristbands with integrated UWB tags, and install fixed UWB tags on construction machinery.

[0018] S103: The UWB base station transmits an ultra-wideband signal, and the UWB tag responds after receiving the ultra-wideband signal. The response signal is then sent back to the UWB base station. The UWB base station measures the flight time parameter of the ultra-wideband signal from the UWB base station to the UWB tag, and calculates the distance d between the UWB base station and the UWB tag. The calculation formula is:

[0019] Where c is the speed of light;

[0020] t q is the round-trip time of the UWB signal from the UWB base station to the UWB tag;

[0021] S104, combining the location coordinates (x i ,y i ,z i ) Calculate the three-dimensional coordinates (x, y, z) of the UWB tag to obtain the location information of the UWB tag, where i = 1, 2, 3, 4, ..., satisfying:

[0022] S105 . According to the three-dimensional coordinates of the UWB tag, the specific time of obtaining the location information is synchronously recorded to form location information including the three-dimensional coordinates of the UWB tag and a timestamp, and send the location information to the risk assessment unit.

[0023] As an example, the specific process of obtaining the personnel category label and identity identification information is as follows:

[0024] S201. Process the image data using a convolutional neural network, output the bounding box coordinates and person category label of the detected person target, extract facial features of the detected person target, generate a facial feature vector F, calculate the cosine similarity S between the facial feature vector F and the pre-registered person feature database D, and match the identity information. The calculation formula of the similarity S is: Among them, D i ∈D,D i is the facial feature vector of the i-th registered person;

[0025] S202, obtain the preset similarity threshold T, if the maximum similarity S max =max is greater than the similarity threshold T, the match is considered successful and the identity information of the person who successfully matched is returned.

[0026] As an example, the specific process of generating a safety equipment wearing report is as follows:

[0027] S301. Using a high-definition camera array at the construction site, collect image data containing personnel and safety equipment in real time, wherein the safety equipment includes a safety helmet and a safety belt;

[0028] S302: Use a labeling tool to pre-label the bounding boxes of the people in the image data, and label the type and location of the safety equipment worn by each person. Select YLOLv8 as the safety detection model, input the labeled image data into the safety detection model, and train the safety detection model to learn the location of the people, the type of safety equipment, and the wearing of the safety equipment.

[0029] S303: Input the real-time image data of the construction site into the trained safety detection model, detect the position of personnel in the image data, and based on the personnel position, detect the type of safety equipment worn by each person and the wearing condition of the safety equipment, identify the correct wearing of the safety equipment, and mark the personnel position and safety equipment position, as well as the type of safety equipment and the wearing condition of the safety equipment in the image data;

[0030] S304: Extract personnel location, safety equipment category, and safety equipment wearing status from the safety detection model, organize them into a table, and calculate the wearing rate W and the non-wearing rate U. The calculation formula is: Among them, wp is the number of people wearing it, wp to is the total number of people wearing it, wp is the number of people not wearing it, wp to is the total number of people who are not wearing it;

[0031] S305: Generate a safety device wearing status report based on the wearing rate W and the non-wearing rate U.

[0032] As a preferred embodiment, the specific process of generating risk warning information is as follows:

[0033] S401. Obtain personnel category labels, identity information, safety equipment wearing status reports, construction personnel and construction machinery location information, real-time operating parameters, and calculate personnel risk factor R. p , Equipment risk factor R e , spatial risk factor R m , and its calculation formula is:

[0034]

[0035] Among them, w p,i is the personnel risk index weight, S p,i is the personnel risk factor;

[0036]

[0037] Among them, w e,j is the equipment risk index weight, S e,j is the equipment risk factor;

[0038]

[0039] Among them, w m,k is the weight of the spatial risk index, and S m,k is the spatial risk factor;

[0040] S402. According to the personnel risk factor R p , equipment risk factor R<00D0020>, and spatial risk factor R m calculate the comprehensive risk score R, and its calculation formula is: R = α×R p +β×R e +γ×R m . Compare the comprehensive risk score R with the preset risk threshold A. If R > A, trigger an emergency response.

[0041] Preferably, the emergency response unit is used to obtain risk warning information, classify the risk warning information into low-risk, medium-risk, and high-risk levels, and execute corresponding emergency measures according to the risk warning information level. The specific classification is as follows:

[0042] When R ≤ g1, it is classified as a low-risk level, and a reminder is automatically sent to the intelligent terminals of relevant personnel. When the real-time operation parameters of construction machinery are abnormal, a self-check program is triggered;

[0043] When g1 < R ≤ g2, it is classified as a medium-risk level, the operation of relevant construction machinery is forced to pause, an electronic fence isolation area is generated, and a drone patrol is started;

[0044] When R > g2, it is classified as a high-risk level, the on-site sound and light alarm system is linked, the emergency management department is automatically notified, and the accident data is uploaded to the cloud for backup. Among them, g1 and g2 are both preset dynamic threshold parameters of risk levels.

[0045] Compared with the prior art, the beneficial effects of the present invention are as follows: Through the provided data acquisition unit, multi-source data such as construction site images, personnel and machinery positions, and operation parameters can be accurately collected in real time, providing a solid support for risk assessment. Combined with the risk assessment unit, using deep learning algorithms and computer vision technology, it can efficiently identify personnel identities, detect the wearing of safety equipment, and construct a multi-source data fusion analysis model to quantitatively evaluate risks and generate accurate warning information, thereby achieving all-round and real-time monitoring and intelligent management of the construction site, effectively improving construction safety, reducing the accident probability, optimizing multi-machine collaborative operations, enhancing construction efficiency, and providing a scientific decision-making basis for management personnel. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a schematic diagram of the overall structure of a preferred embodiment shown in the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0048] Embodiments of the present invention:

[0049] Please refer to Figure 1 As shown, an intelligent construction machinery multi-machine collaborative automated construction control system includes: a data acquisition unit, a risk assessment unit and an emergency response unit;

[0050] The data acquisition unit includes an image data acquisition module, a position data acquisition module, and an equipment data acquisition module. The image data acquisition module collects image data of the construction site in real time and sends the image data to the risk assessment unit.

[0051] The location data acquisition module acquires the location information of construction personnel and construction machinery in real time, and sends the location information of construction personnel and construction machinery to the risk assessment unit;

[0052] The equipment data acquisition module monitors various operating parameters of the construction machinery in real time and outputs them as real-time operating parameters, which are then sent to the risk assessment unit;

[0053] The risk assessment unit includes a personnel identification module, a security detection module, and a cross-analysis module. The personnel identification module is used to acquire image data and, combined with a deep learning algorithm, build a personnel target detection and identity recognition model to obtain personnel category labels and identity information.

[0054] The safety detection module is used to acquire and process image data, build a safety detection model based on computer vision technology, detect whether people in the image data are wearing safety equipment, perform statistical analysis based on the safety equipment wearing detection results, and generate a safety equipment wearing report;

[0055] The cross-analysis module is used to obtain the location information and real-time operating parameters of construction personnel and construction machinery. It combines personnel category labels and identity information with safety equipment wearing status reports to build a multi-source data fusion analysis model, conduct in-depth cross-analysis, and calculate a comprehensive risk score R. Using the preset risk threshold A, it quantitatively assesses the risk and generates risk warning information.

[0056] Image data is acquired through a high-definition camera array installed at the construction site. The location information of construction workers and construction machinery is acquired through various UWB base stations deployed at the construction site in combination with ultra-wideband positioning technology. Real-time operating parameters are acquired through a sensor group installed on the construction machinery. The sensor group includes angle sensors, speed sensors, pressure sensors, and temperature sensors. The real-time operating parameters include angle θ, speed v, pressure p, and temperature t.

[0057] The specific process of obtaining the location information of construction personnel and construction machinery is as follows:

[0058] S101. Deploy UWB base stations one by one according to a construction area distribution map of the construction site, establish a three-dimensional coordinate system for the UWB base stations based on the construction area distribution map, obtain spatial coordinate data of the actual distribution locations of the UWB base stations, and mark the actual locations of the UWB base stations one by one in the three-dimensional coordinate system of the UWB base stations;

[0059] S102. Require construction workers to wear helmets and wristbands with integrated UWB tags, and install fixed UWB tags on construction machinery.

[0060] S103: The UWB base station transmits an ultra-wideband signal, and the UWB tag responds after receiving the ultra-wideband signal. The response signal is then sent back to the UWB base station. The UWB base station measures the flight time parameter of the ultra-wideband signal from the UWB base station to the UWB tag, and calculates the distance d between the UWB base station and the UWB tag. The calculation formula is:

[0061] Where c is the speed of light;

[0062] t q is the round-trip time of the UWB signal from the UWB base station to the UWB tag;

[0063] S104, combining the location coordinates (x i ,y i ,z i ) Calculate the three-dimensional coordinates (x, y, z) of the UWB tag to obtain the location information of the UWB tag, where i = 1, 2, 3, 4, ..., satisfying:

[0064] S105. Synchronously record the specific time of obtaining the location information based on the three-dimensional coordinates of the UWB tag, generate location information including the three-dimensional coordinates of the UWB tag and a timestamp, and send the location information to the risk assessment unit;

[0065] The specific process of obtaining personnel category labels and identity information is as follows:

[0066] S201. Process the image data using a convolutional neural network, output the bounding box coordinates and person category label of the detected person target, extract facial features of the detected person target, generate a facial feature vector F, calculate the cosine similarity S between the facial feature vector F and the pre-registered person feature database D, and match the identity information. The calculation formula of the similarity S is: Among them, D i ∈D,D i is the facial feature vector of the i-th registered person;

[0067] S202, obtain the preset similarity threshold T, if the maximum similarity S max =max is greater than the similarity threshold T, then the match is considered successful and the identity information of the person who successfully matched is returned;

[0068] The specific process of generating a safety equipment wearing report is as follows:

[0069] S301. Using a high-definition camera array at the construction site, real-time image data of personnel and safety equipment is collected. Safety equipment includes hard hats and safety belts.

[0070] S302: Use a labeling tool to pre-label the bounding boxes of the people in the image data, and label the type and location of the safety equipment worn by each person. Select YLOLv8 as the safety detection model, input the labeled image data into the safety detection model, and train the safety detection model to learn the location of the people, the type of safety equipment, and the wearing of the safety equipment.

[0071] S303: Input the real-time image data of the construction site into the trained safety detection model, detect the position of personnel in the image data, and based on the personnel position, detect the type of safety equipment worn by each person and the wearing condition of the safety equipment, identify the correct wearing of the safety equipment, and mark the personnel position and safety equipment position, as well as the type of safety equipment and the wearing condition of the safety equipment in the image data;

[0072] S304: Extract personnel location, safety equipment category, and safety equipment wearing status from the safety detection model, organize them into a table, and calculate the wearing rate W and the non-wearing rate U. The calculation formula is: Among them, wp is the number of people wearing it, wp to is the total number of people wearing it, wp is the number of people not wearing it, wp to is the total number of people who are not wearing it;

[0073] S305: Generate a safety device wearing status report based on the wearing rate W and the non-wearing rate U;

[0074] The specific process of generating risk warning information is as follows:

[0075] S401. Obtain the personnel category label, identity identification information, safety equipment wearing situation report, the location information of construction personnel and construction machinery, and real-time operation parameters, and calculate the personnel risk factor R p , equipment risk factor R e , space risk factor R m , and its calculation formula is:

[0076]

[0077] Among them, w p,i is the personnel risk index weight, and S p,i is the personnel risk factor;

[0078]

[0079] Among them, w e,j is the equipment risk index weight, and S e,j is the equipment risk factor;

[0080]

[0081] Among them, w m,k is the space risk index weight, and S m,k is the space risk factor;

[0082] S402. Calculate the comprehensive risk score R according to the personnel risk factor R p , equipment risk factor R e , space risk factor R m , and its calculation formula is: R = α×R p +β×R e +γ×R m . Compare the comprehensive risk score R with the preset risk threshold A. If R > A, trigger an emergency response;

[0083] The emergency response unit is used to obtain risk warning information, classify the risk warning information into low risk, medium risk, and high risk levels, and execute corresponding emergency measures according to the risk warning information level. The specific classification is as follows:

[0084] When R ≤ g1, it is classified as a low risk level, and a reminder is automatically sent to the intelligent terminals of relevant personnel. When the real-time operation parameters of construction machinery are abnormal, a self-check program is triggered;

[0085] When g1 < R ≤ g2, it is classified as a medium risk level, the operation of relevant construction machinery is forcibly suspended, an electronic fence isolation area is generated, and an unmanned aerial vehicle is started for inspection;

[0086] When R>g2, it is classified as a high-risk level, the on-site sound and light alarm system is linked, the emergency management department is automatically notified, and the accident data is uploaded to the cloud for backup. Among them, g1 and g2 are both preset risk level dynamic threshold parameters.

[0087] Through the set data acquisition unit, multi-source data such as construction site images, personnel and machinery locations, and operating parameters can be accurately collected in real time, providing solid support for risk assessment. Combined with the risk assessment unit, deep learning algorithms and computer vision technology are used to efficiently identify personnel identities, detect the wearing of safety equipment, and build a multi-source data fusion analysis model to quantitatively assess risks and generate accurate early warning information, thereby realizing all-round, real-time monitoring and intelligent management of the construction site, effectively improving construction safety, reducing the probability of accidents, optimizing multi-machine collaborative operations, improving construction efficiency, and providing managers with a scientific decision-making basis.

[0088] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technical personnel in this field for each set of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0089] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by those skilled in the art according to actual conditions.

[0090] In the two embodiments provided in this application, it should be understood that the disclosed devices and systems can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the module division is merely a logical function division. In actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not implemented. In addition, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interface, and the indirect coupling or communication connection of devices or modules may be electrical, mechanical or other forms.

[0091] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. An intelligent construction machinery multi-machine collaborative automated construction control system, characterized in that: include: Data acquisition unit, risk assessment unit, and emergency response unit; The data acquisition unit includes an image data acquisition module, a position data acquisition module and an equipment data acquisition module, which collects image data of the construction site in real time through the image data acquisition module and sends the image data to the risk assessment unit; The location data acquisition module acquires the location information of construction personnel and construction machinery in real time, and sends the location information of construction personnel and construction machinery to the risk assessment unit; The equipment data acquisition module monitors various operating parameters of the construction machinery in real time and outputs them as real-time operating parameters, which are then sent to the risk assessment unit; The risk assessment unit includes a personnel identification module, a security detection module and a cross-analysis module. The personnel identification module is used to acquire image data and, in combination with a deep learning algorithm, construct a personnel target detection and identity recognition model to obtain personnel category labels and identity identification information; The safety detection module is used to acquire and process image data, build a safety detection model based on computer vision technology, detect whether people in the image data are wearing safety equipment, and perform statistical analysis based on the safety equipment wearing detection results to generate a safety equipment wearing report; The cross-analysis module is used to obtain the location information and real-time operating parameters of construction personnel and construction machinery, and to build a multi-source data fusion analysis model based on personnel category labels and identity information as well as safety equipment wearing status reports. It also conducts in-depth cross-analysis to calculate a comprehensive risk score R, and quantitatively assesses the risk using a preset risk threshold A to generate risk warning information.

2. The intelligent construction machinery multi-machine coordinated automated construction control system according to claim 1 is characterized in that: The image data is acquired through a high-definition camera array installed at the construction site. The location information of the construction workers and construction machinery is acquired through various UWB base stations deployed at the construction site in combination with ultra-wideband positioning technology. The real-time operating parameters are acquired through a sensor group installed on the construction machinery. The sensor group includes an angle sensor, a speed sensor, a pressure sensor, and a temperature sensor. The real-time operating parameters include angle θ, speed v, pressure p, and temperature t.

3. The intelligent construction machinery multi-machine coordinated automated construction control system according to claim 2 is characterized in that: The specific process of obtaining the location information of construction personnel and construction machinery is as follows: S101. Deploy UWB base stations one by one according to a construction area distribution map of the construction site, establish a three-dimensional coordinate system for the UWB base stations based on the construction area distribution map, obtain spatial coordinate data of the actual distribution locations of the UWB base stations, and mark the actual locations of the UWB base stations one by one in the three-dimensional coordinate system of the UWB base stations; S102. Require construction workers to wear helmets and wristbands with integrated UWB tags, and install fixed UWB tags on construction machinery. S103: The UWB base station transmits an ultra-wideband signal, and the UWB tag responds after receiving the ultra-wideband signal. The response signal is then sent back to the UWB base station. The UWB base station measures the flight time parameter of the ultra-wideband signal from the UWB base station to the UWB tag, and calculates the distance d between the UWB base station and the UWB tag. The calculation formula is: Where c is the speed of light; t q is the round-trip time of the UWB signal from the UWB base station to the UWB tag; S104, combining the location coordinates (x i ,y i ,z i ) Calculate the three-dimensional coordinates (x, y, z) of the UWB tag to obtain the location information of the UWB tag, where i = 1, 2, 3, 4, ..., satisfying: S105 . According to the three-dimensional coordinates of the UWB tag, the specific time of obtaining the location information is synchronously recorded to form location information including the three-dimensional coordinates of the UWB tag and a timestamp, and send the location information to the risk assessment unit.

4. The intelligent construction machinery multi-machine coordinated automated construction control system according to claim 3 is characterized in that: The specific process of obtaining personnel category labels and identity information is as follows: S201. Process the image data using a convolutional neural network, output the bounding box coordinates and person category label of the detected person target, extract facial features of the detected person target, generate a facial feature vector F, calculate the cosine similarity S between the facial feature vector F and the pre-registered person feature database D, and match the identity information. The calculation formula of the similarity S is: Among them, D i ∈D,D i is the facial feature vector of the i-th registered person; S202, obtain the preset similarity threshold T, if the maximum similarity S max =max is greater than the similarity threshold T, the match is considered successful and the identity information of the person who successfully matched is returned.

5. The intelligent construction machinery multi-machine coordinated automated construction control system according to claim 4 is characterized in that: The specific process of generating a safety equipment wearing report is as follows: S301. Real-time collect image data including personnel and safety equipment through the high-definition camera array at the construction site. The safety equipment includes safety helmets and safety belts. S302. Use annotation tools to pre-annotate the bounding boxes of personnel in the image data, and annotate the category and position of the safety equipment worn by each person. Select YLOLv8 as the safety detection model, input the annotated image data into the safety detection model, and train the safety detection model to learn the personnel position, safety equipment category, and safety equipment wearing situation. S303. Input the real-time collected image data of the construction site into the trained safety detection model, detect the personnel position in the image data, and based on the personnel position, detect the category of the safety equipment worn by each person and the safety equipment wearing situation, identify the correct wearing of the safety equipment, and annotate the personnel position and safety equipment position in the image data, as well as the safety equipment category and safety equipment wearing situation. S304: Extract personnel location, safety equipment category, and safety equipment wearing status from the safety detection model, organize them into a table, and calculate the wearing rate W and the non-wearing rate U. The calculation formula is: Among them, wp is the number of people wearing it, wp to is the total number of people wearing it, wp is the number of people not wearing it, wp to is the total number of people who are not wearing it; S305. Generate a report on the wearing situation of safety equipment according to the wearing rate W and the non-wearing rate U.

6. The intelligent construction machinery multi-machine coordinated automated construction control system according to claim 5 is characterized in that: The specific process of generating risk warning information is as follows: S401. Obtain personnel category labels, identity information, safety equipment wearing status reports, construction personnel and construction machinery location information, real-time operating parameters, and calculate personnel risk factor R. p , Equipment risk factor R e , spatial risk factor R m , and its calculation formula is: Among them, w p,i is the personnel risk index weight, S p,i is the personnel risk factor; Among them, w e,j is the equipment risk index weight, S e,j is the equipment risk factor; Among them, w m,k is the spatial risk index weight, S m,k is the spatial risk factor; S402, according to the personnel risk factor R p , Equipment risk factor R e , spatial risk factor R m Calculate the comprehensive risk score R, the calculation formula is: R = α × R p +β×R e +γ×R m , compare the comprehensive risk score R with the preset risk threshold A. If R>A, an emergency response is triggered.

7. The intelligent construction machinery multi-machine coordinated automated construction control system according to claim 6 is characterized in that: The emergency response unit is used to obtain risk warning information, classify the risk warning information into low-risk, medium-risk, and high-risk levels, and execute corresponding emergency measures according to the risk warning information level. The specific classification is as follows: When R ≤ g1, it is classified as a low-risk level, and a reminder is automatically sent to the intelligent terminal of the relevant personnel. When the real-time operation parameters of the construction machinery are abnormal, a self-check program is triggered. When g1 < R ≤ g2, it is classified as a medium-risk level, the operation of the relevant construction machinery is forced to pause, an electronic fence isolation area is generated, and an unmanned aerial vehicle is started for inspection. When R > g2, it is classified as a high-risk level, the on-site sound and light alarm system is linked, the emergency management department is automatically notified, and the accident data is uploaded to the cloud for backup. Here, g1 and g2 are both preset dynamic threshold parameters for risk levels.

Images