A supervision risk control early warning system

Abstract

The present invention discloses a supervision risk control and early warning system, which includes: a data acquisition module, which is configured to acquire image data and natural data of a construction site; a safety distance analysis module, which is configured to calculate the safety distance between construction equipment and construction personnel based on image data and perform risk analysis to obtain a first sub-result when the construction equipment is a mobile operation type; an overall situation analysis module, which is configured to perform risk analysis based on natural data to obtain a second sub-result; a risk assessment module, which is configured to perform assessment and analysis based on the first sub-result and the second sub-result to obtain an overall rating of the construction site; and a blockchain interface module, which is configured to upload the overall rating of the construction site, the first sub-result, and the second sub-result to the blockchain for storage.

Description

Technical Field

[0001] The invention relates to the technical field of engineering supervision, and in particular to a supervision risk control early warning system. Background Art

[0002] In the field of construction, safety management of construction sites has always been a crucial issue. Traditional safety management methods mainly rely on manual inspections and empirical judgments, which is not only inefficient but also easily affected by human factors, making it difficult to timely discover and prevent potential safety hazards. With the advancement of science and technology, more and more intelligent technologies are being applied to the safety management of construction sites, aiming to improve the accuracy and real-time nature of risk assessment, protect the lives of construction workers, and improve construction efficiency.

[0003] Existing technologies conduct project supervision through manual inspections or video surveillance, but manual inspections rely on the personal experience and subjective judgment of supervisors, and are easily affected by human factors, resulting in inaccurate risk assessment results. Video surveillance technology can record the situation at the construction site in real time, but it still requires manual review of the surveillance footage, which is time-consuming and prone to negligence due to fatigue of the monitoring personnel, thus affecting the accurate judgment of construction risks. Summary of the invention

[0004] In view of the above-mentioned prior art, the present invention provides a supervision risk control early warning system, which mainly solves the technical problems existing in the above-mentioned background technology.

[0005] To achieve the above object, the technical solution of the embodiment of the present invention is implemented as follows:

[0006] A first aspect of the present invention provides a supervision risk control early warning system, the system comprising:

[0007] A data acquisition module is configured to collect image data and natural data of the construction site;

[0008] A safety distance analysis module is configured to calculate the safety distance between the construction equipment and the construction personnel based on the image data and perform risk analysis to obtain a first sub-result when the construction equipment is a mobile operation type;

[0009] The overall situation analysis module is configured to perform risk analysis based on natural data to obtain a second sub-result;

[0010] A risk assessment module is configured to perform an assessment and analysis based on the first sub-result and the second sub-result to obtain an overall rating of the construction site;

[0011] The blockchain interface module is configured to upload the overall rating of the construction site, the first sub-result, and the second sub-result to the blockchain for storage.

[0012] Optionally, the natural environment data includes the dust pollution coefficient of each construction sub-area in the construction site and the temperature, humidity, air pressure and wind speed data of each construction sub-area in the target construction site.

[0013] Optionally, the safety distance analysis module includes a YOLOv8l model and an evaluation model, and the YOLOv8l model outputs a rectangular detection box about the construction equipment and a rectangular detection box about the construction personnel respectively, and the evaluation model calculates the safety distance between the rectangular detection box about the construction equipment and the rectangular detection box about the construction personnel.

[0014] Optionally, calculating the safety distance between the rectangular detection frame of the construction equipment and the rectangular detection frame of the construction personnel by using the evaluation model specifically includes:

[0015] Obtain 2D images including construction equipment and construction personnel, as well as 3D point cloud data of the same scene;

[0016] Construct the world coordinate system in the real scene and the pixel coordinate system in the two-dimensional image, and establish a mapping relationship between the two. The established mapping relationship is:

[0017]

[0018] Where (X c , Y c , Z c ) is the coordinate of the camera coordinate system, d x is the physical size of each pixel on the x-axis of the pixel coordinate system, d y is the physical size of each pixel on the y-axis of the pixel coordinate system, f is the focal length of the camera, and f x Indicates the focal length of the camera on the x-axis, f y represents the focal length of the camera on the y-axis, (u0, v0) refers to the pixel coordinates corresponding to the optical center of the camera, R is a 3×3 rotation matrix, T is a 3×1 translation vector, D is the camera distortion coefficient, and M is a matrix composed of f x 、f y , the internal parameter matrix composed of (u0,v0);

[0019] Based on the mapping relationship, the back-projection transformation formula from the pixel coordinate system to the world coordinate system is applied to calculate the vertex coordinates of the rectangular detection box about the construction equipment and the rectangular detection box about the construction personnel, wherein the back-projection transformation formula is:

[0020]

[0021] Where (X w ,Y w ,Zw ) is the three-dimensional coordinate of the world coordinate system, (u, ν) represents the coordinate position in the two-dimensional image;

[0022] The Euclidean distance between the rectangular detection frame of the construction equipment and the rectangular detection frame of the construction personnel is calculated, and the minimum distance is selected as the safety distance.

[0023] Optionally, the minimum distance is selected as the safety distance, specifically including respectively calculating the Euclidean distance between each vertex in the rectangular detection box of the construction equipment and each vertex in the rectangular detection box of the construction personnel, and selecting the minimum Euclidean distance as the safety distance.

[0024] Optionally, a risk analysis is performed on the safety distance to obtain a first sub-result, specifically including: setting a first threshold and counting the number of times in any time period that the safety distance between all construction equipment and corresponding construction personnel at the construction site is less than the first threshold, and forming the first sub-result based on different numbers of times.

[0025] Optionally, risk analysis is performed based on natural data to obtain a second sub-result, including:

[0026] The weight vector is adaptively set by the hierarchical analysis method: in Represents the weight vector of dust pollution coefficient, represents the weight vector of temperature, represents the weight vector of humidity, represents the weight vector of air pressure, A weight vector representing wind speed;

[0027] The second subresult is calculated by:

[0028]

[0029] Among them, DPI represents the dust pollution coefficient, WD represents the temperature index, SD represents the humidity index, QY represents the air pressure index, and FH represents the wind speed index.

[0030] Optionally, in the risk assessment module, the first sub-result and the second sub-result are evaluated and analyzed by a random forest algorithm to obtain an overall rating of the construction site.

[0031] Optionally, the system also includes an intelligent decision support module, which is configured to provide risk response suggestions and decision support to supervisors based on the overall rating results of the construction site output by the risk assessment module based on a decision tree algorithm.

[0032] A second aspect of the present invention provides an electronic device comprising: at least one processor; a memory; and at least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, and the at least one application is configured to: run the supervision risk control early warning system described in any one of the preceding items.

[0033] The beneficial effects of the present invention are as follows: the system provided in this embodiment collects image data and natural data of the construction site through the data acquisition module, calculates the safety distance between construction equipment and construction personnel and performs risk analysis through the safety distance analysis module to obtain a first sub-result, performs risk analysis based on natural data through the overall situation analysis module to obtain a second sub-result, and finally evaluates and analyzes the first sub-result and the second sub-result through the risk assessment module. Through the overall assessment of multiple risk situations, the overall risk rating of the construction site can be obtained. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a module diagram of the supervision risk control early warning system in the embodiment of the present application. DETAILED DESCRIPTION

[0035] The technical solution of the present invention is further elaborated in detail below in conjunction with the drawings and specific embodiments of the specification. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the present invention. In the following description, the expression "some embodiments" is related to a subset of all possible embodiments, but it should be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict.

[0036] In the following description, a large number of specific details are provided to provide a more thorough understanding of the present invention. However, it is apparent to those skilled in the art that the present invention can be implemented without one or more of these details. In other examples, in order to avoid confusion with the present invention, some technical features well known in the art are not described.

[0037] It should be understood that the present invention can be implemented in different forms and should not be interpreted as being limited to the embodiments proposed herein. On the contrary, providing these embodiments will make the disclosure thorough and complete, and the scope of the present invention will be fully conveyed to those skilled in the art. And the purpose of the terms used herein is only to describe specific embodiments and is not intended to be a limitation of the present invention. When used herein, the singular forms of "one", "one" and "said / the" are also intended to include plural forms, unless the context clearly indicates another way. It should also be understood that the terms "compose" and / or "include" when used in this specification determine the presence of the features, integers, steps, operations, elements and / or parts, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, parts and / or groups. When used herein, the term "and / or" includes any and all combinations of the relevant listed items.

[0038] It should also be noted that when an element is referred to as being "fixed to" another element, it may be directly on the other element or there may be a central element. When an element is considered to be "connected to" another element, it may be directly connected to the other element or there may be a central element at the same time. The terms "vertical", "horizontal", "inside", "outside", "left", "right" and similar expressions used herein are for illustrative purposes only and are not intended to be the only implementation method.

[0039] In order to fully understand the present invention, a detailed structure will be proposed in the following description to illustrate the technical solution proposed by the present invention. The optional embodiments of the present invention are described in detail as follows, but in addition to these detailed descriptions, the present invention may also have other implementations.

[0040] Please refer to the attached Figure 1 The first aspect of the present invention provides a supervision risk control early warning system, the system comprising:

[0041] A data acquisition module is configured to collect image data and natural data of the construction site;

[0042] A safety distance analysis module is configured to calculate the safety distance between the construction equipment and the construction personnel based on the image data and perform risk analysis to obtain a first sub-result when the construction equipment is a mobile operation type;

[0043] Among them, mobile operation types include excavators, bulldozers, tower cranes and concrete mixers. When the above equipment is working, construction workers should maintain a certain safe distance from them.

[0044] The overall situation analysis module is configured to perform risk analysis based on natural data to obtain a second sub-result;

[0045] A risk assessment module is configured to perform an assessment and analysis based on the first sub-result and the second sub-result to obtain an overall rating of the construction site;

[0046] The blockchain interface module is configured to upload the overall rating of the construction site, the first sub-result, and the second sub-result to the blockchain for storage.

[0047] The system provided in this embodiment collects image data and natural data of the construction site through the data acquisition module, calculates the safety distance between construction equipment and construction personnel and performs risk analysis through the safety distance analysis module to obtain a first sub-result, performs risk analysis based on natural data through the overall situation analysis module to obtain a second sub-result, and finally evaluates and analyzes the first sub-result and the second sub-result through the risk assessment module to obtain an overall rating of the construction site.

[0048] Furthermore, the natural environment data includes the dust pollution coefficient of each construction sub-area in the construction site and the temperature, humidity, air pressure, and wind speed data in each construction sub-area in the target construction site. The natural environment data can be obtained through various types of sensor networks, and the image data of the construction site is collected by cameras and drones equipped with lidar or cameras.

[0049] Furthermore, the safety distance analysis module includes a YOLOv8 l model and an evaluation model, and the YOLOv8 l model outputs a rectangular detection box about the construction equipment and a rectangular detection box about the construction personnel respectively, and the evaluation model calculates the safety distance between the rectangular detection box about the construction equipment and the rectangular detection box about the construction personnel.

[0050] The safety distance analysis module uses the advanced YOLOv8 target detection model to identify the positions of construction equipment and construction personnel, and calculate the minimum safety distance between the two. By constructing a mapping relationship between the world coordinate system in the real scene and the pixel coordinate system in the two-dimensional image, the back-projection transformation formula is applied to calculate the world coordinates of the vertices of the rectangular detection box, and then the Euclidean distance is calculated, and the minimum distance is selected as the safety distance. This process can accurately determine the relative position between construction equipment and personnel, and promptly detect and warn of possible collision risks. The system sets a safety distance threshold and counts the number of times the safety distance between all construction equipment and corresponding construction personnel is less than the threshold in any time period.

[0051] In an optional implementation, calculating the safety distance between the rectangular detection frame of the construction equipment and the rectangular detection frame of the construction personnel by the evaluation model specifically includes:

[0052] Obtain 2D images including construction equipment and construction personnel, as well as 3D point cloud data of the same scene;

[0053] Construct the world coordinate system in the real scene and the pixel coordinate system in the two-dimensional image, and establish a mapping relationship between the two. The established mapping relationship is:

[0054]

[0055] Where (X c , Y c , Z c ) is the coordinate of the camera coordinate system, d x is the physical size of each pixel on the x-axis of the pixel coordinate system, d y is the physical size of each pixel on the y-axis of the pixel coordinate system, f is the focal length of the camera, and f x Indicates the focal length of the camera on the x-axis, f y represents the focal length of the camera on the y-axis, (u0, v0) refers to the pixel coordinates corresponding to the optical center of the camera, R is a 3×3 rotation matrix, T is a 3×1 translation vector, D is the camera distortion coefficient, and M is a matrix composed of f x 、f y , the internal parameter matrix composed of (u0,v0);

[0056] Based on the mapping relationship, the back-projection transformation formula from the pixel coordinate system to the world coordinate system is applied to calculate the vertex coordinates of the rectangular detection box about the construction equipment and the rectangular detection box about the construction personnel, wherein the back-projection transformation formula is:

[0057]

[0058] Where (X w ,Y w ,Z w ) is the three-dimensional coordinate of the world coordinate system, (u, ν) represents the coordinate position in the two-dimensional image;

[0059] The Euclidean distance between the rectangular detection frame of the construction equipment and the rectangular detection frame of the construction personnel is calculated, and the minimum distance is selected as the safety distance.

[0060] In an optional embodiment, the minimum distance is selected as the safety distance, specifically including respectively calculating the Euclidean distance between each vertex in the rectangular detection box regarding the construction equipment and each vertex in the rectangular detection box regarding the construction personnel, and selecting the minimum Euclidean distance as the safety distance.

[0061] In an optional embodiment, a risk analysis is performed on the safety distance to obtain a first sub-result, which specifically includes: setting a first threshold and counting the number of times in any time period that the safety distance between all construction equipment and corresponding construction personnel at the construction site is less than the first threshold, and forming the first sub-result based on different numbers of times.

[0062] The first sub-result directly reflects the physical collision risk at the construction site by counting the number of times the safety distance between construction equipment and construction workers is less than a threshold. Each insufficient safety distance means a potential collision event, which, when accumulated, significantly increases the likelihood of an accident.

[0063] In an optional implementation, risk analysis is performed based on natural data to obtain a second sub-result, which specifically includes:

[0064] The weight vector is adaptively set by the hierarchical analysis method: in Represents the weight vector of dust pollution coefficient, represents the weight vector of temperature, represents the weight vector of humidity, represents the weight vector of air pressure, A weight vector representing wind speed;

[0065] The second subresult is calculated by:

[0066]

[0067] Among them, DPI represents the dust pollution coefficient, WD represents the temperature index, SD represents the humidity index, QY represents the air pressure index, and FH represents the wind speed index.

[0068] The second sub-result comprehensively considers the impact of natural environmental factors (such as dust pollution coefficient, temperature, humidity, air pressure, wind speed, etc.) on construction safety. These environmental factors may indirectly affect the working conditions of construction workers and the operating status of equipment, increasing potential risks.

[0069] In an optional implementation, in the risk assessment module, the first sub-result and the second sub-result are evaluated and analyzed using a random forest algorithm to obtain an overall rating of the construction site.

[0070] Specifically, the first and second sub-results were evaluated and analyzed through the random forest algorithm, realizing the automation of the entire process from data collection to risk assessment and decision support. Special emphasis was placed on quantifying the risk level of the construction site by counting the number of risk events. The more risk events there were, the higher the risk level of the construction site.

[0071] Optionally, the system also includes an intelligent decision support module, which is configured to provide risk response suggestions and decision support to supervisors based on the overall rating results of the construction site output by the risk assessment module based on a decision tree algorithm.

[0072] A second aspect of the present invention provides an electronic device comprising: at least one processor; a memory; and at least one application, wherein the at least one application is stored in the memory and configured to be executed by the at least one processor, and the at least one application is configured to: run the supervision risk control early warning system described in any one of the preceding items.

[0073] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A supervision risk control early warning system, characterized in that: The system comprises: A data acquisition module is configured to collect image data and natural data of the construction site; A safety distance analysis module is configured to calculate the safety distance between the construction equipment and the construction personnel based on the image data and perform risk analysis to obtain a first sub-result when the construction equipment is a mobile operation type; The overall situation analysis module is configured to perform risk analysis based on natural data to obtain a second sub-result; A risk assessment module is configured to perform an assessment and analysis based on the first sub-result and the second sub-result to obtain an overall rating of the construction site; The blockchain interface module is configured to upload the overall rating of the construction site, the first sub-result, and the second sub-result to the blockchain for storage.

2. A supervision risk control early warning system according to claim 1, characterized in that: The natural environment data include the dust pollution coefficient of each construction sub-area in the construction site and the temperature, humidity, air pressure and wind speed data of each construction sub-area in the target construction site.

3. A supervision risk control early warning system according to claim 1, characterized in that: The safety distance analysis module includes a YOLOv8 l model and an evaluation model. The YOLOv8 l model outputs a rectangular detection box about construction equipment and a rectangular detection box about construction personnel respectively. The evaluation model calculates the safety distance between the rectangular detection box about construction equipment and the rectangular detection box about construction personnel.

4. A supervision risk control early warning system according to claim 3, characterized in that: Calculating the safety distance between the rectangular detection frame of the construction equipment and the rectangular detection frame of the construction personnel by using the evaluation model specifically includes: Obtain 2D images including construction equipment and construction personnel, as well as 3D point cloud data of the same scene; Construct the world coordinate system in the real scene and the pixel coordinate system in the two-dimensional image, and establish a mapping relationship between the two. The established mapping relationship is: Where (X c , Y c , Z c ) is the coordinate of the camera coordinate system, d x is the physical size of each pixel on the x-axis of the pixel coordinate system, d y is the physical size of each pixel on the y-axis of the pixel coordinate system, f is the focal length of the camera, and f x Indicates the focal length of the camera on the x-axis, f y represents the focal length of the camera on the y-axis, (u0, v0) refers to the pixel coordinates corresponding to the optical center of the camera, R is a 3×3 rotation matrix, T is a 3×1 translation vector, D is the camera distortion coefficient, and M is a matrix composed of f x 、f y , the internal parameter matrix composed of (u0,v0); Based on the mapping relationship, the back-projection transformation formula from the pixel coordinate system to the world coordinate system is applied to calculate the vertex coordinates of the rectangular detection box about the construction equipment and the rectangular detection box about the construction personnel, wherein the back-projection transformation formula is: Where (X w ,Y w ,Z w ) is the three-dimensional coordinate of the world coordinate system, (u, ν) represents the coordinate position in the two-dimensional image; The Euclidean distance between the rectangular detection frame of the construction equipment and the rectangular detection frame of the construction personnel is calculated, and the minimum distance is selected as the safety distance.

5. A supervision risk control early warning system according to claim 4, characterized in that: The minimum distance is selected as the safety distance, specifically including respectively calculating the Euclidean distance between each vertex in the rectangular detection box of the construction equipment and each vertex in the rectangular detection box of the construction personnel, and selecting the minimum Euclidean distance as the safety distance.

6. A supervision risk control early warning system according to claim 5, characterized in that: A risk analysis is performed on the safety distance to obtain a first sub-result, specifically including: setting a first threshold, and counting the number of times in any time period that the safety distance between all construction equipment and corresponding construction personnel at the construction site is less than the first threshold, and forming the first sub-result based on different numbers.

7. A supervision risk control early warning system according to claim 6, characterized in that: Based on the risk analysis of natural data, the second sub-result is obtained, including: The weight vector is adaptively set by the hierarchical analysis method: in Represents the weight vector of dust pollution coefficient, represents the weight vector of temperature, represents the weight vector of humidity, represents the weight vector of air pressure, A weight vector representing wind speed; The second subresult is calculated by: Among them, DPI represents the dust pollution coefficient, WD represents the temperature index, SD represents the humidity index, QY represents the air pressure index, and FH represents the wind speed index.

8. A supervision risk control early warning system according to claim 7, characterized in that: In the risk assessment module, the first and second sub-results are evaluated and analyzed using the random forest algorithm to obtain an overall rating of the construction site.

9. A supervision risk control early warning system according to claim 8, characterized in that: The system also includes an intelligent decision support module, which is configured to provide risk response suggestions and decision support to supervisors based on a decision tree algorithm and according to the overall rating results of the construction site output by the risk assessment module.

10. An electronic device, characterized in that: include: at least one processor; Memory; At least one application, wherein the at least one application is stored in a memory and configured to be executed by at least one processor, and the at least one application is configured to: run the supervision risk control early warning system described in any one of claims 1-9.

Images