CN116050842B - Dynamic control method and system for urban underground engineering construction safety risk - Google Patents
Dynamic control method and system for urban underground engineering construction safety risk Download PDFInfo
- Publication number
- CN116050842B CN116050842B CN202310049276.8A CN202310049276A CN116050842B CN 116050842 B CN116050842 B CN 116050842B CN 202310049276 A CN202310049276 A CN 202310049276A CN 116050842 B CN116050842 B CN 116050842B
- Authority
- CN
- China
- Prior art keywords
- risk
- worker
- information
- cell
- risk information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000010276 construction Methods 0.000 title claims abstract description 68
- 238000000034 method Methods 0.000 title claims abstract description 25
- 230000006399 behavior Effects 0.000 claims abstract description 174
- 238000012954 risk control Methods 0.000 claims abstract description 35
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000005516 engineering process Methods 0.000 claims abstract description 5
- 239000000284 extract Substances 0.000 claims abstract description 4
- 230000002159 abnormal effect Effects 0.000 claims description 29
- 238000010801 machine learning Methods 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 10
- 238000005070 sampling Methods 0.000 claims description 4
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 2
- 238000009435 building construction Methods 0.000 abstract description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Primary Health Care (AREA)
- Remote Sensing (AREA)
- Development Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Forklifts And Lifting Vehicles (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of underground building construction safety, in particular to a dynamic control method and a system for urban underground engineering construction safety risk, which comprise the following steps: step S1: the aerial photography device continuously flies to acquire the image information of the construction area in real time; step S2: the server builds a construction area virtual space by using a 3D technology based on the construction area image information and map information acquired from a network; step S3: the data processing unit extracts the number of workers and the positions of the workers in the construction area image information according to the unit cells, and analyzes the image information to obtain the operation behaviors of the workers; step S4: an adding unit adds the worker and the risk control information to the corresponding position of the virtual space according to the position information of the worker; step S5: the calculating unit calculates worker operation risk information according to the risk control information and the worker operation behavior; the method solves the problem of accurately calculating the worker operation risk information.
Description
Technical Field
The invention relates to the technical field of underground building construction safety, in particular to a dynamic control method and a system for urban underground engineering construction safety risks.
Background
Although many safety measures are adopted at a construction site, many unsafe factors threaten personal safety of constructors, particularly at the construction site of urban underground engineering, the environment is complex, the construction difficulty is relatively high, more accurate and comprehensive risk control is needed, and therefore, the condition of the construction site is needed to be known in real time, so that worker operation risk information can be calculated timely, currently, the unmanned aerial vehicle technology is mostly adopted to collect construction information of the construction site, but a construction area is not divided into grids, more accurate aerial image can not be acquired according to the worker density and the cell risk information of the cells of the grids, the aerial frequency, the aerial time, the aerial angle and the aerial track of an unmanned aerial vehicle are not adjusted, virtual space is not established, risk information of different positions cannot be visually checked, and when worker operation risk is calculated, worker operation risk information is comprehensively judged by comparing worker operation behavior with abnormal operation behavior, standard operation behavior and historical risk incidence, so that the calculation accuracy of worker operation is never poor.
Disclosure of Invention
In order to better solve the problems, the invention provides a dynamic control method for the construction safety risk of urban underground engineering, which comprises the following steps:
step S1: the method comprises the steps that an aerial camera continuously flies to obtain construction area image information in real time, the image information comprises position information, when the aerial camera obtains the construction area image information, in an initial state, the shooting height of the aerial camera is h1, a shooting area is a circle with radius r, the construction area is divided into grids with side length of a, and a is smaller than or equal to aTaking an image by the aerial camera by taking cells of the grid as units, wherein the shooting frequency of each cell is f1;
step S2: the server builds a construction area virtual space by using a 3D technology based on the construction area image information and map information acquired from a network;
step S3: the data processing unit extracts the number of workers and the positions of the workers in the construction area image information according to the unit cells, and analyzes the image information to obtain the operation behaviors of the workers;
step S4: an adding unit adds the worker and the risk control information to the corresponding position of the virtual space according to the position information of the worker;
Step S5: the calculation unit calculates worker operation risk information according to the risk control information and the worker operation behaviors, and sends worker operation risk information with highest risk in all pieces of worker operation risk information in the unit cell to the server through the communication unit as corresponding unit cell risk information, and also sends each piece of worker operation risk information to a corresponding worker terminal;
step S6: the machine learning unit performs machine learning based on the cell risk information of each cell and the number of workers in each cell to obtain flight parameters of the aerial camera, wherein the flight parameters comprise the flight height, shooting time, shooting angle, shooting frequency and flight track of the aerial camera at the position of each cell;
step S7: the aerial photography device receives the flight parameters and adjusts shooting behaviors based on the flight parameters;
step S8: the server receives the cell risk information, marks corresponding cells of the cell risk information in the virtual space, and sends out an early warning signal when the cell risk information is high risk.
As a more preferable technical solution of the present invention, the risk control information includes standard operation behavior, abnormal operation behavior, and historical risk occurrence rate.
As a more preferable technical solution of the present invention, in the step S5, the risk information of the worker operation having the highest risk among all the workers in the cell is used as the risk information of the cell, wherein the risk information of the worker operation includes high risk and low risk, and the step of acquiring the risk information of the worker operation includes the steps of:
step S501: the calculation unit respectively acquires abnormal operation behaviors, standard operation behaviors and historical risk occurrence rate of the current operation type of the worker from the risk control information;
step S502: comparing the worker operation behaviors with the abnormal operation behaviors to obtain a first comparison result, and when the first comparison result is smaller than a first threshold value, obtaining the worker operation risk information as high risk;
step S503: when the first comparison result is larger than the first threshold value, comparing the worker operation behavior with the standard operation behavior to obtain a second comparison result, and when the second comparison result is smaller than the second threshold value, the worker operation risk information is low risk;
when the second comparison result is larger than the second threshold value, acquiring other multiple worker operation behaviors of which the operation types are the same as those of the worker at the worker position under the condition that the historical risk occurrence rate of the current operation type of the worker is smaller than a third threshold value, comparing the worker operation behaviors with the other multiple worker operation behaviors to acquire a maximum comparison result, wherein when the maximum comparison result is smaller than a fourth threshold value, the worker operation risk information is low risk, and when the maximum comparison result is larger than the fourth threshold value, the worker operation risk information is high risk;
Continuously acquiring N operation behaviors of the worker under the condition that the historical risk occurrence rate of the current operation type of the worker is greater than the third threshold value, analyzing the behavior trend of the N operation behaviors, and judging the operation risk information of the worker based on the behavior trend;
step S504: repeating the steps S501-S503 to acquire all the worker operation risk information in the unit cell, taking the highest worker operation risk information in all the worker operation risk information as the unit cell risk information of the unit cell, sending the unit cell risk information to the server through the communication unit, and sending each worker operation risk information to the corresponding worker terminal.
As a more preferable technical scheme of the invention, when the behavior trend is that N operation behaviors of the worker are respectively compared with the abnormal operation behaviors to obtain N comparison results, and the sizes of the N comparison results are sequentially decreased according to the sampling sequence, the worker operation risk information is high risk, otherwise, the worker operation risk information is low risk.
As a more preferable technical solution of the present invention, when the cell risk information is high risk, the machine learning unit reduces the height of the aerial camera to an aerial photographing height h2, increases the photographing frequency of the cell to a photographing frequency f2, the calculating unit further increases the value of the first threshold value, reduces the value of the second threshold value and the value of the fourth threshold value based on the cell risk information and the photographing parameter change of the aerial camera, re-acquires image information, and re-executes steps S1 to S6 to acquire the cell risk information;
When the risk information of the cell is low risk, the height of the aerial camera is raised to an aerial photographing height h3, the photographing frequency of the cell is reduced to a photographing frequency f3, and the calculation unit predicts the risk information of the cell as real-time risk information of the cell based on the operation behaviors of workers in the cell acquired last time, the risk information calculated last time by the cell and the historical risk information of the cell acquired from the server in a time period when the image information of the cell is not photographed.
As a more preferable technical scheme of the invention, when the number of workers in a cell is greater than the number of workers with a preset value, the machine learning unit reduces the flying height of the aerial camera to the aerial photographing height h4 at the position of the cell, and increases the photographing angle and the photographing duration of the aerial camera.
As a more preferable aspect of the present invention, the work behavior of the worker is added to the risk control information as an abnormal work behavior after the worker has occurred a safety event.
As a more preferable technical scheme of the present invention, after the worker terminal receives the worker operation risk information, the worker terminal transmits the worker operation risk information to a worker in the form of information display, sound or vibration.
The invention also provides a dynamic control system for the urban underground construction safety risk, which is used for realizing the dynamic control method for the urban underground construction safety risk, and comprises the following steps:
the aerial camera is used for continuously flying to obtain construction area image information, the image information comprises position information, when the aerial camera obtains the construction area image information, in an initial state, the shooting height of the aerial camera is h1, the shooting area is a circle with radius r, the construction area is divided into grids with side length of a, and a is smaller than or equal toTaking an image by the aerial camera by taking cells of the grid as units, wherein the shooting frequency of each cell is f1;
a server for constructing a construction area virtual space using a 3D technique based on the construction area image information and map information acquired from a network;
the data processing unit is used for extracting the number of workers and the positions of the workers in the construction area image information according to the unit cells, and analyzing the image information to obtain the operation behaviors of the workers;
an adding unit configured to add the worker and risk control information to corresponding positions of the virtual space according to the position information of the worker;
The calculating unit is used for calculating the worker operation risk information according to the risk control information and the worker operation behaviors;
the machine learning unit is used for carrying out machine learning based on the cell risk information of each cell and the number of workers in each cell to obtain flight parameters of the aerial camera, wherein the flight parameters comprise the flight height, the shooting frequency, the shooting time, the shooting angle and the flight track of the aerial camera at the position of each cell;
the communication unit is used for sending the worker operation risk information with the highest risk in all the worker operation risk information in the cell to the server as the cell risk information of the cell, and sending each worker operation risk information to the corresponding worker terminal; after receiving the risk information of the worker operation, the worker terminal transmits the risk information to the worker in the form of information display, sound or vibration;
the aerial camera is further used for receiving the flight parameters and adjusting shooting behaviors based on the flight parameters;
the server is further configured to receive the risk information of the cell, mark the corresponding cell in the virtual space with the risk information of the cell, and send an early warning signal when the risk information of the cell is high risk;
Wherein the risk control information includes standard work behaviors of the worker, abnormal work behaviors, and historical risk occurrence rates.
As a more preferable technical scheme of the invention, the system further comprises a worker terminal, wherein the worker terminal is used for receiving worker operation risk information;
the computing unit is further configured to: taking the worker operation risk information with the highest risk in all workers in a cell as the cell risk information of the cell, wherein the worker operation risk information comprises high risk and low risk, and respectively acquiring abnormal operation behaviors, standard operation behaviors and historical risk occurrence rate of the current operation type of the worker from risk control information;
comparing the worker operation behavior with the abnormal operation behavior to obtain a first comparison result, wherein the worker operation behavior has high risk when the first comparison result is smaller than a first threshold value;
when the first comparison result is larger than the first threshold value, comparing the worker operation behavior with the standard operation behavior to obtain a second comparison result, and when the second comparison result is smaller than the second threshold value, the worker operation behavior is low in risk; when the second comparison result is larger than the second threshold value, acquiring other multiple worker operation behaviors of which the operation types are the same as those of the worker at the worker position under the condition that the historical risk occurrence rate of the current operation type of the worker is smaller than a third threshold value, comparing the worker operation behaviors with the other multiple worker operation behaviors to acquire a maximum comparison result, wherein when the maximum comparison result is smaller than a fourth threshold value, the worker operation risk information is low risk, and when the maximum comparison result is larger than the fourth threshold value, the worker operation risk information is high risk;
Continuously acquiring N operation behaviors of the worker under the condition that the historical risk occurrence rate of the current operation type of the worker is greater than the third threshold value, analyzing the behavior trend of the N operation behaviors, and judging the operation risk information of the worker based on the behavior trend;
the computing unit is further configured to: when the risk information of the cell is low risk, predicting the risk information of the cell as real-time risk information of the cell based on the last acquired operation behavior of workers in the cell, the last calculated risk information of the cell and the historical risk information of the cell acquired from the server in a time period of the image information of the cell;
the machine learning unit is further configured to: when the cell risk information is high risk, reducing the height of the aerial photo device to an aerial photo height h2 at the cell position, increasing the shooting frequency of the cell to a shooting frequency f2, and using the highest risk worker operation information in the all worker operation risk information as the cell risk information of the cell by the calculation unit based on the cell risk information and the shooting parameter change of the aerial photo device, increasing the value of the first threshold value, reducing the value of the second threshold value and the value of the fourth threshold value, and re-acquiring image information; when the risk information of the cell is low risk, raising the height of the aerial camera to an aerial photographing height h3, and reducing the photographing frequency of the cell to a photographing frequency f3;
When the number of workers in the cell is greater than the number of workers with a preset value, the flying height of the aerial camera is reduced to the aerial photographing height h4 at the position of the cell, and the photographing angle and the photographing duration of the aerial camera are increased.
Compared with the prior art, the invention has the following beneficial effects:
according to the method, the flight parameters of the aerial photography device at the positions of the cells are dynamically adjusted through machine learning of the cell risk information of each cell and the number of workers in each cell, when the cell risk information is high risk, the flight height of the aerial photography device is reduced, shooting frequency is increased to obtain more accurate shooting images so as to obtain more accurate cell risk information, when the cell risk information is high risk, the flight height of the aerial photography device is increased, shooting frequency is reduced, and due to the fact that real-time cell images cannot be obtained, the risk information calculated last time by the workers in the cells and the historical risk information of the cells obtained from the server are predicted to serve as real-time cell risk information, so that continuity of cell risk information data is ensured; when the number of workers in the unit cell is large, the shooting time of the aerial camera needs to be increased, the shooting angle is increased, the flying speed is reduced, a more comprehensive shooting image is obtained, each worker in the unit cell is ensured to be shot, so that worker operation risk information can be accurately calculated, when the worker operation risk information is calculated, the worker operation behavior is compared with abnormal operation behavior and standard operation behavior in risk control information, more accurate worker operation risk information is obtained, and meanwhile, the history risk incidence rate, the operation behaviors of other workers at the worker position and the behavior trend of the workers are comprehensively and accurately judged, so that the worker operation risk information can be obtained through the mutual cooperation of the technical scheme.
Drawings
FIG. 1 is a flow chart of a dynamic control method for the construction safety risk of urban underground engineering;
FIG. 2 is a block diagram of a dynamic control system for the construction safety risk of urban underground works.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The invention provides a dynamic control method for urban underground engineering construction safety risk, as shown in figure 1, comprising the following steps:
step S1: the method comprises the steps that an aerial camera continuously flies to obtain construction area image information in real time, the image information comprises position information, when the aerial camera obtains the construction area image information, in an initial state, the shooting height of the aerial camera is h1, a shooting area is a circle with radius r, the construction area is divided into grids with side length of a, and a is smaller than or equal to aTaking an image by the aerial camera by taking cells of the grid as units, wherein the shooting frequency of each cell is f1;
Step S2: the server builds a construction area virtual space by using a 3D technology based on the construction area image information and map information acquired from a network; specifically, the server corresponds the construction area image information and the map information according to the image position relation, and can check the corresponding cell risk information of each cell position in real time through the construction area virtual space;
step S3: the data processing unit extracts the number of workers and the positions of the workers in the construction area image information according to the unit cells, and analyzes the image information to obtain the operation behaviors of the workers;
step S4: an adding unit adds the worker and the risk control information to the corresponding position of the virtual space according to the position information of the worker; specifically, the unit adds risk control information of the operation type at the position of the cell corresponding to the worker to the corresponding position of the virtual space according to the position information of the cell corresponding to the worker, and at the moment, the worker at each cell, the number of workers at each cell, the operation type of the worker at each cell and the risk control information corresponding to the operation type can be checked through the virtual space, and the risk control information is a rule for controlling risk occurrence;
Step S5: the calculation unit calculates worker operation risk information according to the risk control information and the worker operation behaviors, and sends worker operation risk information with highest risk in all pieces of worker operation risk information in the unit cell to the server through the communication unit as corresponding unit cell risk information, and also sends each piece of worker operation risk information to a corresponding worker terminal; specifically, comparing the operation behavior of the worker with abnormal operation behavior and standard operation behavior in the risk control information, judging worker operation risk information according to a comparison result, further judging the worker operation risk information according to historical risk occurrence rate and other multiple worker operation behaviors with the same operation type as the worker at the worker position, and sending the worker operation risk information to the server and the worker terminal through a communication unit as cell risk information corresponding to the worker position, wherein the server marks the cell risk information in the virtual space, and sends an early warning signal to prompt an administrator when the cell risk information is high risk, and the early warning signal comprises buzzer sound, high display screen or highlighting and other prompt modes;
Step S6: the machine learning unit performs machine learning based on the cell risk information of each cell and the number of workers in each cell to obtain flight parameters of the aerial camera, wherein the flight parameters comprise the flight height, shooting time, shooting angle, shooting frequency and flight track of the aerial camera at the position of each cell; specifically, when the number of workers in the cell is large and the density of workers is high, the operation behaviors of all workers in the cell can not be comprehensively shot according to a normal shooting mode, the height of an aerial camera is required to be reduced, the shooting time and the shooting angle are increased, the shooting precision is improved, a foundation is laid for accurately determining the operation behavior risk information of the workers, when the calculation result of the cell risk information is high risk, the height of the aerial camera at the cell is reduced, the shooting frequency at the cell is increased, the risk judging condition of the cell is also improved, and the cell risk information is further and more accurately calculated and determined through high-precision image acquisition and stricter judging standards;
Step S7: the aerial photography device receives the flight parameters and adjusts shooting behaviors based on the flight parameters;
step S8: the server receives the cell risk information, marks corresponding cells of the cell risk information in the virtual space, and sends out an early warning signal when the cell risk information is high risk.
Further, the risk control information includes standard work behaviors of the worker, abnormal work behaviors, and historical risk occurrence rates.
Further, in the step S5, the risk information of the worker operation having the highest risk among all the workers in the cell is taken as the risk information of the cell, wherein the risk information of the worker operation includes a high risk and a low risk, and the step of obtaining the risk information of the worker operation includes the steps of:
step S501: the calculation unit respectively acquires abnormal operation behaviors, standard operation behaviors and historical risk occurrence rate of the current operation type of the worker from the risk control information;
step S502: comparing the worker operation behaviors with the abnormal operation behaviors to obtain a first comparison result, and when the first comparison result is smaller than a first threshold value, obtaining the worker operation risk information as high risk; specifically, the smaller the first comparison result is, the closer the worker operation behavior is to the abnormal operation behavior, and the higher the risk of the worker operation behavior is;
Step S503: when the first comparison result is larger than the first threshold value, comparing the worker operation behavior with the standard operation behavior to obtain a second comparison result, and when the second comparison result is smaller than the second threshold value, the worker operation risk information is low risk; specifically, the larger the first comparison result is, the larger the difference between the worker operation behavior and the abnormal operation behavior is, the lower the risk of the worker operation behavior is, and the incomplete record in the abnormal operation behavior is possibly needed to be further judged; the smaller the second comparison result is, the closer the worker operation behavior is to the standard operation behavior, and the lower the risk of the worker operation behavior is;
when the second comparison result is larger than the second threshold value, acquiring other multiple worker operation behaviors of which the operation types are the same as those of the worker at the worker position under the condition that the historical risk occurrence rate of the current operation type of the worker is smaller than a third threshold value, comparing the worker operation behaviors with the other multiple worker operation behaviors to acquire a maximum comparison result, wherein when the maximum comparison result is smaller than a fourth threshold value, the worker operation risk information is low risk, and when the maximum comparison result is larger than the fourth threshold value, the worker operation risk information is high risk;
Specifically, the larger the second comparison result is, the larger the difference between the worker operation behavior and the standard operation behavior is, the higher the risk of the worker operation behavior may be, or the current operation type of the worker may be completed by multiple operation behaviors, and the standard operation behavior is only one of the operation behaviors, so that other worker operation behaviors of the operation type need to be combined to judge the risk information of the worker operation behavior; the maximum comparison result reflects the difference between the worker operation behaviors and the other workers operation behaviors, and the smaller the difference is, the closer the worker operation behaviors of other workers are to the operation behaviors of other workers of the operation type, and the fact that the other workers are completed by the same operation behaviors is also indicated, wherein the worker operation behaviors may be low risk;
continuously acquiring N operation behaviors of the worker under the condition that the historical risk occurrence rate of the current operation type of the worker is greater than the third threshold value, analyzing the behavior trend of the N operation behaviors, and judging the operation risk information of the worker based on the behavior trend; specifically, when the difference between the worker operation behaviors and the other plurality of worker operation behaviors is large, risk information of the worker operation behaviors cannot be determined, and judgment needs to be performed by combining the behavior trends of the N operation behaviors of the worker;
Step S504: repeating the steps S501-S503 to acquire all the worker operation risk information in the unit cell, taking the highest worker operation risk information in all the worker operation risk information as the unit cell risk information of the unit cell, sending the unit cell risk information to the server through the communication unit, and sending each worker operation risk information to the corresponding worker terminal.
Further, when the behavior trend is that the N operation behaviors of the worker are respectively compared with the abnormal operation behaviors to obtain N comparison results, and the sizes of the N comparison results are sequentially decreased according to the sampling sequence, the worker operation risk information is high risk, otherwise, the worker operation risk information is low risk. Specifically, when the sizes of the N comparison results decrease in sequence according to the sampling sequence, it is indicated that the N operation behaviors of the worker approach the abnormal behaviors gradually, so that it is determined that the worker operation behaviors have high risk.
Further, when the cell risk information is high risk, the machine learning unit reduces the height of the aerial camera to an aerial photographing height h2, increases the photographing frequency of the cell to a photographing frequency f2, and the calculating unit further reduces the values of the first threshold, the second threshold and the fourth threshold based on the cell risk information and the photographing parameter change of the aerial camera, re-acquires image information, and re-executes steps S1-S6 to acquire the cell risk information;
Specifically, when the risk information of the cell is high risk, in order to further determine the judgment accuracy of the risk information of the cell, the height of the aerial camera at the cell needs to be reduced, the shooting frequency at the cell is increased, meanwhile, the risk judgment condition of the cell is also improved, and the risk information of the cell is further and more accurately calculated and determined through high-accuracy image acquisition and stricter judgment standards;
when the risk information of the cell is low risk, the height of the aerial photo device is increased to the aerial photo height quantity, the shooting frequency of the cell is reduced to the shooting frequency f3, in a time period when the image information of the cell is not shot, the calculation unit predicts the risk information of the cell as real-time risk information of the cell based on the operation behaviors of workers in the cell acquired last time, the risk information calculated last time by the cell and the historical risk information of the cell acquired from the server, and specifically, when the risk information of the cell is low risk, the grid does not need to pay attention to, and meanwhile, in order to enable the aerial photo device to have wider shooting field of view, the height of the aerial photo device is increased to the shooting height h3, in order to enable the aerial photo device to have more time to shoot the cell with high risk, so the shooting frequency of the cell is reduced to the shooting frequency f3, and the image information of the cell cannot be acquired in real time due to the fact that the number of shooting times of the cell is reduced, the image of the cell cannot be acquired in real-time, and the risk information of the cell cannot be acquired as the risk information of the cell is predicted in real-time.
Further, when the number of workers in the unit cell is greater than the number of workers with a preset value, the machine learning unit modifies the flight parameters of the aerial photography device, reduces the flight height of the aerial photography device to the aerial photography height h4, and increases the photographing angle and the photographing duration of the aerial photography device. Specifically, when the number of workers in the cell is large and the density of workers is high, the operation behaviors of all the workers in the cell can not be comprehensively shot according to a normal shooting mode, the height of the aerial camera needs to be reduced, the shooting time and the shooting angle are increased, the shooting precision is improved, a foundation is laid for accurately determining the risk information of the operation behaviors of the workers,
further, after a worker has occurred a safety event, the worker's operation behavior is added to the risk control information as an abnormal operation behavior.
Further, after the worker terminal receives the worker operation risk information, the worker terminal transmits the worker operation risk information to a worker in the form of information display, sound, or vibration.
The invention also provides a dynamic control system for the urban underground construction safety risk, which is used for realizing the dynamic control method for the urban underground construction safety risk, as shown in fig. 2, and comprises the following steps:
The aerial camera is used for continuously flying to obtain construction area image information, the image information comprises position information, when the aerial camera obtains the construction area image information, in an initial state, the shooting height of the aerial camera is h1, the shooting area is a circle with radius r, the construction area is divided into grids with side length of a, and a is smaller than or equal toTaking an image by the aerial camera by taking cells of the grid as units, wherein the shooting frequency of each cell is f1;
a server for constructing a construction area virtual space using a 3D technique based on the construction area image information and map information acquired from a network;
the data processing unit is used for extracting the number of workers and the positions of the workers in the construction area image information according to the unit cells, and analyzing the image information to obtain the operation behaviors of the workers;
an adding unit configured to add the worker and risk control information to corresponding positions of the virtual space according to the position information of the worker;
the calculating unit is used for calculating the worker operation risk information according to the risk control information and the worker operation behaviors;
the machine learning unit is used for carrying out machine learning based on the cell risk information of each cell and the number of workers in each cell to obtain flight parameters of the aerial camera, wherein the flight parameters comprise the flight height, the shooting frequency, the shooting time, the shooting angle and the flight track of the aerial camera at the position of each cell;
The communication unit is used for sending the worker operation risk information with the highest risk in all the worker operation risk information in the cell to the server as the cell risk information of the cell, and sending each worker operation risk information to the corresponding worker terminal; after receiving the risk information of the worker operation, the worker terminal transmits the risk information to the worker in the form of information display, sound or vibration;
the aerial camera is further used for receiving the flight parameters and adjusting shooting behaviors based on the flight parameters;
the server is further configured to receive the risk information of the cell, mark the corresponding cell in the virtual space with the risk information of the cell, and send an early warning signal when the risk information of the cell is high risk;
wherein the risk control information includes standard work behaviors of the worker, abnormal work behaviors, and historical risk occurrence rates.
Further, the system also comprises a worker terminal, wherein the worker terminal is used for receiving the worker operation risk information;
the computing unit is further configured to: taking the worker operation risk information with the highest risk in all workers in a cell as the cell risk information of the cell, wherein the worker operation risk information comprises high risk and low risk, and respectively acquiring abnormal operation behaviors, standard operation behaviors and historical risk occurrence rate of the current operation type of the worker from risk control information;
Comparing the worker operation behavior with the abnormal operation behavior to obtain a first comparison result, wherein the worker operation behavior has high risk when the first comparison result is smaller than a first threshold value;
when the first comparison result is larger than the first threshold value, comparing the worker operation behavior with the standard operation behavior to obtain a second comparison result, and when the second comparison result is smaller than the second threshold value, the worker operation behavior is low in risk; when the second comparison result is larger than the second threshold value, acquiring other multiple worker operation behaviors of which the operation types are the same as those of the worker at the worker position under the condition that the historical risk occurrence rate of the current operation type of the worker is smaller than a third threshold value, comparing the worker operation behaviors with the other multiple worker operation behaviors to acquire a maximum comparison result, wherein when the maximum comparison result is smaller than a fourth threshold value, the worker operation risk information is low risk, and when the maximum comparison result is larger than the fourth threshold value, the worker operation risk information is high risk;
continuously acquiring N operation behaviors of the worker under the condition that the historical risk occurrence rate of the current operation type of the worker is greater than the third threshold value, analyzing the behavior trend of the N operation behaviors, and judging the operation risk information of the worker based on the behavior trend;
The computing unit is further configured to: when the risk information of the cell is low risk, predicting the risk information of the cell as real-time risk information of the cell based on the last acquired operation behavior of workers in the cell, the last calculated risk information of the cell and the historical risk information of the cell acquired from the server in a time period of the image information of the cell;
the machine learning unit is further configured to: when the cell risk information is high risk, reducing the height of the aerial photo device to an aerial photo height h2 at the cell position, increasing the shooting frequency of the cell to a shooting frequency f2, and using the highest risk worker operation information in the all worker operation risk information as the cell risk information of the cell by the calculation unit based on the cell risk information and the shooting parameter change of the aerial photo device, increasing the value of the first threshold value, reducing the value of the second threshold value and the value of the fourth threshold value, and re-acquiring image information; when the risk information of the cell is low risk, raising the height of the aerial camera to an aerial photographing height h3, and reducing the photographing frequency of the cell to a photographing frequency f3;
When the number of workers in the cell is greater than the number of workers with a preset value, the flying height of the aerial camera is reduced to the aerial photographing height h4 at the position of the cell, and the photographing angle and the photographing duration of the aerial camera are increased.
In summary, the invention dynamically adjusts the flight parameters of the aerial camera at the position of each cell by machine learning the cell risk information of each cell and the number of workers in each cell, reduces the flight height of the aerial camera when the cell risk information is high risk, increases the shooting frequency to acquire more accurate shooting images so as to acquire more accurate cell risk information, increases the flight height of the aerial camera when the cell risk information is high risk, reduces the shooting frequency, predicts the cell risk information as real-time cell risk information based on the last acquired worker operation behavior in the cell, the last calculated risk information of the cell and the historical risk information of the cell acquired from the server, and ensures the continuity of cell risk information data because real-time cell images cannot be acquired. When the number of workers in the unit cell is large, the shooting time of the aerial camera needs to be increased, the shooting angle is increased, the flying speed is reduced, a more comprehensive shooting image is obtained, each worker in the unit cell is ensured to be shot, so that worker operation risk information can be accurately calculated, when the worker operation risk information is calculated, the worker operation behavior is compared with abnormal operation behavior and standard operation behavior in risk control information, more accurate worker operation risk information is obtained, and meanwhile, the history risk incidence rate, the operation behaviors of other workers at the worker position and the behavior trend of the workers are comprehensively and accurately judged, so that the worker operation risk information can be obtained through the mutual cooperation of the technical scheme.
The technical features of the above embodiments may be arbitrarily combined, and for brevity, all of the possible combinations of the technical features of the above embodiments are not described, however, they should be considered as the scope of the description of the present specification as long as there is no contradiction between the combinations of the technical features.
The foregoing examples have been presented to illustrate only a few embodiments of the invention and are described in more detail and are not to be construed as limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (8)
1. The dynamic control method for the construction safety risk of the urban underground engineering is characterized by comprising the following steps of:
Step S1: the method comprises the steps that an aerial camera continuously flies to obtain construction area image information in real time, the image information comprises position information, when the aerial camera obtains the construction area image information, in an initial state, the shooting height of the aerial camera is h1, a shooting area is a circle with radius r, the construction area is divided into grids with side length of a, and a is smaller than or equal to aThe aerial camera takes the cells of the grid as units to shoot images, and the shooting frequency of each cell is f1, and the step S2 is that: the server builds a construction area virtual space by using a 3D technology based on the construction area image information and map information acquired from a network;
step S3: the data processing unit extracts the number of workers and the positions of the workers in the construction area image information according to the unit cells, and analyzes the image information to obtain the operation behaviors of the workers;
step S4: an adding unit adds the worker and the risk control information to the corresponding position of the virtual space according to the position information of the worker;
step S5: the calculation unit calculates worker operation risk information according to the risk control information and the worker operation behaviors, and sends worker operation risk information with highest risk in all pieces of worker operation risk information in the unit cell to the server through the communication unit as corresponding unit cell risk information, and also sends each piece of worker operation risk information to a corresponding worker terminal;
Step S6: the machine learning unit performs machine learning based on the cell risk information of each cell and the number of workers in each cell to obtain flight parameters of the aerial camera, wherein the flight parameters comprise the flight height, shooting time, shooting angle, shooting frequency and flight track of the aerial camera at the position of each cell;
step S7: the aerial photography device receives the flight parameters and adjusts shooting behaviors based on the flight parameters;
step S8: the server receives the cell risk information, marks corresponding cells of the cell risk information in the virtual space, and sends out an early warning signal when the cell risk information is high risk;
wherein the risk control information includes standard job behavior, abnormal job behavior, and historical risk occurrence rate.
2. The method according to claim 1, wherein in the step S5, the highest risk worker operation risk information among all the workers in the cell is used as the cell risk information, wherein the worker operation risk information includes high risk and low risk, and the obtaining of the worker operation risk information includes the steps of:
Step S501: the calculation unit respectively acquires abnormal operation behaviors, standard operation behaviors and historical risk occurrence rate of the current operation type of the worker from the risk control information;
step S502: comparing the worker operation behaviors with the abnormal operation behaviors to obtain a first comparison result, and when the first comparison result is smaller than a first threshold value, obtaining the worker operation risk information as high risk;
step S503: when the first comparison result is larger than the first threshold value, comparing the worker operation behavior with the standard operation behavior to obtain a second comparison result, and when the second comparison result is smaller than the second threshold value, the worker operation risk information is low risk;
when the second comparison result is larger than the second threshold value, acquiring other multiple worker operation behaviors of which the operation types are the same as those of the worker at the worker position under the condition that the historical risk occurrence rate of the current operation type of the worker is smaller than a third threshold value, comparing the worker operation behaviors with the other multiple worker operation behaviors to acquire a maximum comparison result, wherein when the maximum comparison result is smaller than a fourth threshold value, the worker operation risk information is low risk, and when the maximum comparison result is larger than the fourth threshold value, the worker operation risk information is high risk;
Continuously acquiring N operation behaviors of the worker under the condition that the historical risk occurrence rate of the current operation type of the worker is greater than the third threshold value, analyzing the behavior trend of the N operation behaviors, and judging the operation risk information of the worker based on the behavior trend;
step S504: repeating the steps S501-S503 to acquire all the worker operation risk information in the unit cell, taking the highest worker operation risk information in all the worker operation risk information as the unit cell risk information of the unit cell, sending the unit cell risk information to the server through the communication unit, and sending each worker operation risk information to the corresponding worker terminal.
3. The dynamic control method for the construction safety risk of the urban underground engineering according to claim 2, wherein when the behavior trend is that N operation behaviors of the workers are respectively compared with the abnormal operation behaviors to obtain N comparison results, and the sizes of the N comparison results are sequentially decreased according to the sampling sequence, the worker operation risk information is high risk, and otherwise, the worker operation risk information is low risk.
4. A method according to claim 3, wherein when the risk information of the cell is high risk, the machine learning unit reduces the height of the aerial camera to an aerial photographing height h2, increases the photographing frequency of the cell to a photographing frequency f2, and the calculating unit further increases the value of the first threshold value, decreases the value of the second threshold value and the value of the fourth threshold value based on the risk information of the cell and the change of the photographing parameter of the aerial camera, re-acquires image information, and re-executes steps S1 to S6 to acquire the risk information of the cell;
When the risk information of the cell is low risk, the height of the aerial camera is raised to an aerial photographing height h3, the photographing frequency of the cell is reduced to a photographing frequency f3, and the calculation unit predicts the risk information of the cell as real-time risk information of the cell based on the operation behaviors of workers in the cell acquired last time, the risk information calculated last time by the cell and the historical risk information of the cell acquired from the server in a time period when the image information of the cell is not photographed.
5. The dynamic control method for the construction safety risk of the urban underground engineering according to claim 3, wherein when the number of workers in a cell is greater than the number of workers with a preset value, the machine learning unit reduces the flying height of the aerial camera to an aerial photographing height h4 at the position of the cell, and increases the photographing angle and the photographing duration of the aerial camera.
6. The dynamic control method for risk of construction safety of urban underground works according to claim 1, wherein the operation behavior of the worker is added to the risk control information as an abnormal operation behavior after a safety event occurs to the worker.
7. The dynamic control method for construction safety risk of urban underground works according to claim 1, wherein the worker terminal transmits the worker operation risk information to the worker in the form of information display, sound or vibration after the worker terminal receives the worker operation risk information.
8. A dynamic control system for urban underground engineering construction safety risk, which is used for realizing a dynamic control method for urban underground engineering construction safety risk according to any one of claims 1-7, characterized in that the system comprises:
the aerial camera is used for continuously flying to obtain construction area image information, the image information comprises position information, when the aerial camera obtains the construction area image information, in an initial state, the shooting height of the aerial camera is h1, the shooting area is a circle with radius r, the construction area is divided into grids with side length of a, and a is smaller than or equal toTaking an image by the aerial camera by taking cells of the grid as units, wherein the shooting frequency of each cell is f1;
a server for constructing a construction area virtual space using a 3D technique based on the construction area image information and map information acquired from a network;
The data processing unit is used for extracting the number of workers and the positions of the workers in the construction area image information according to the unit cells, and analyzing the image information to obtain the operation behaviors of the workers;
an adding unit configured to add the worker and risk control information to corresponding positions of the virtual space according to the position information of the worker;
the calculating unit is used for calculating the worker operation risk information according to the risk control information and the worker operation behaviors;
the machine learning unit is used for carrying out machine learning based on the cell risk information of each cell and the number of workers in each cell to obtain flight parameters of the aerial camera, wherein the flight parameters comprise the flight height, the shooting frequency, the shooting time, the shooting angle and the flight track of the aerial camera at the position of each cell;
the communication unit is used for sending the worker operation risk information with the highest risk in all the worker operation risk information in the cell to the server as the cell risk information of the cell, and sending each worker operation risk information to the corresponding worker terminal; after receiving the risk information of the worker operation, the worker terminal transmits the risk information to the worker in the form of information display, sound or vibration;
The aerial camera is further used for receiving the flight parameters and adjusting shooting behaviors based on the flight parameters;
the server is further configured to receive the risk information of the cell, mark the corresponding cell in the virtual space with the risk information of the cell, and send an early warning signal when the risk information of the cell is high risk;
wherein the risk control information includes standard work behaviors of the worker, abnormal work behaviors, and historical risk occurrence rates.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310049276.8A CN116050842B (en) | 2023-02-01 | 2023-02-01 | Dynamic control method and system for urban underground engineering construction safety risk |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310049276.8A CN116050842B (en) | 2023-02-01 | 2023-02-01 | Dynamic control method and system for urban underground engineering construction safety risk |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116050842A CN116050842A (en) | 2023-05-02 |
| CN116050842B true CN116050842B (en) | 2023-08-04 |
Family
ID=86121614
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310049276.8A Active CN116050842B (en) | 2023-02-01 | 2023-02-01 | Dynamic control method and system for urban underground engineering construction safety risk |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116050842B (en) |
Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160034013A (en) * | 2014-09-19 | 2016-03-29 | 한국건설기술연구원 | System and method for construction site management by using unmaned aerial vehicle |
| FR3041746A1 (en) * | 2015-09-28 | 2017-03-31 | Aer | DEVICE FOR AIDING THE DRIVING AND DOUBT RAISING OF AN AIRCRAFT |
| KR101753515B1 (en) * | 2016-02-16 | 2017-07-05 | 정용호 | Image Recording Control System for Managing a Field Safety and Drive Method of the Same |
| CN107390613A (en) * | 2017-08-25 | 2017-11-24 | 国家电网公司 | The managing and control system and management-control method of transmission line construction process |
| CN109122633A (en) * | 2018-06-25 | 2019-01-04 | 华南农业大学 | The accurate variable-rate spraying device of the plant protection drone of Decision of Neural Network and control method |
| CN109353504A (en) * | 2018-09-05 | 2019-02-19 | 华南农业大学 | UAV Intelligent spraying system and method based on prescription map |
| CN109557935A (en) * | 2018-11-01 | 2019-04-02 | 广州圣安环保科技有限公司 | A kind of safety monitoring during construction method and system based on unmanned plane |
| CN111008669A (en) * | 2019-12-10 | 2020-04-14 | 北京航空航天大学 | Deep learning-based heavy landing prediction method |
| CN111537515A (en) * | 2020-03-31 | 2020-08-14 | 国网辽宁省电力有限公司朝阳供电公司 | Iron tower bolt defect display method and system based on three-dimensional live-action model |
| CN111667230A (en) * | 2020-04-16 | 2020-09-15 | 中国电力科学研究院有限公司 | Unmanned aerial vehicle autonomous inspection operation monitoring and analyzing system and method |
| CN112180984A (en) * | 2020-10-22 | 2021-01-05 | 江汉大学 | Unmanned aerial vehicle auxiliary flight device based on artificial intelligence and flight control method |
| KR20210014705A (en) * | 2021-01-20 | 2021-02-09 | 황보의 | www.18338891.com |
| CN113014866A (en) * | 2021-02-05 | 2021-06-22 | 中国民用航空总局第二研究所 | Airport low-altitude bird activity monitoring and risk alarming system |
| CN113822247A (en) * | 2021-11-22 | 2021-12-21 | 广东泰一高新技术发展有限公司 | Method and system for identifying illegal building based on aerial image |
| CN114359712A (en) * | 2021-12-08 | 2022-04-15 | 青岛诺诚化学品安全科技有限公司 | Safety violation analysis system based on unmanned aerial vehicle inspection |
| CN114489143A (en) * | 2022-04-02 | 2022-05-13 | 清华大学 | Unmanned aerial vehicle management system, method and device for construction safety risk monitoring |
| CN115048874A (en) * | 2022-08-16 | 2022-09-13 | 北京航空航天大学 | Aircraft design parameter estimation method based on machine learning |
| CN115086607A (en) * | 2022-06-14 | 2022-09-20 | 国网山东省电力公司电力科学研究院 | Electric power construction monitoring system, monitoring method and computer equipment |
| CN115375154A (en) * | 2022-08-29 | 2022-11-22 | 黑龙江农业工程职业学院 | Building construction quality safety online risk management system |
| CN115565330A (en) * | 2022-09-22 | 2023-01-03 | 中建八局发展建设有限公司 | Building construction site spot-distribution type fire monitoring system and method |
-
2023
- 2023-02-01 CN CN202310049276.8A patent/CN116050842B/en active Active
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20160034013A (en) * | 2014-09-19 | 2016-03-29 | 한국건설기술연구원 | System and method for construction site management by using unmaned aerial vehicle |
| FR3041746A1 (en) * | 2015-09-28 | 2017-03-31 | Aer | DEVICE FOR AIDING THE DRIVING AND DOUBT RAISING OF AN AIRCRAFT |
| KR101753515B1 (en) * | 2016-02-16 | 2017-07-05 | 정용호 | Image Recording Control System for Managing a Field Safety and Drive Method of the Same |
| CN107390613A (en) * | 2017-08-25 | 2017-11-24 | 国家电网公司 | The managing and control system and management-control method of transmission line construction process |
| CN109122633A (en) * | 2018-06-25 | 2019-01-04 | 华南农业大学 | The accurate variable-rate spraying device of the plant protection drone of Decision of Neural Network and control method |
| CN109353504A (en) * | 2018-09-05 | 2019-02-19 | 华南农业大学 | UAV Intelligent spraying system and method based on prescription map |
| CN109557935A (en) * | 2018-11-01 | 2019-04-02 | 广州圣安环保科技有限公司 | A kind of safety monitoring during construction method and system based on unmanned plane |
| CN111008669A (en) * | 2019-12-10 | 2020-04-14 | 北京航空航天大学 | Deep learning-based heavy landing prediction method |
| CN111537515A (en) * | 2020-03-31 | 2020-08-14 | 国网辽宁省电力有限公司朝阳供电公司 | Iron tower bolt defect display method and system based on three-dimensional live-action model |
| CN111667230A (en) * | 2020-04-16 | 2020-09-15 | 中国电力科学研究院有限公司 | Unmanned aerial vehicle autonomous inspection operation monitoring and analyzing system and method |
| CN112180984A (en) * | 2020-10-22 | 2021-01-05 | 江汉大学 | Unmanned aerial vehicle auxiliary flight device based on artificial intelligence and flight control method |
| KR20210014705A (en) * | 2021-01-20 | 2021-02-09 | 황보의 | www.18338891.com |
| CN113014866A (en) * | 2021-02-05 | 2021-06-22 | 中国民用航空总局第二研究所 | Airport low-altitude bird activity monitoring and risk alarming system |
| CN113822247A (en) * | 2021-11-22 | 2021-12-21 | 广东泰一高新技术发展有限公司 | Method and system for identifying illegal building based on aerial image |
| CN114359712A (en) * | 2021-12-08 | 2022-04-15 | 青岛诺诚化学品安全科技有限公司 | Safety violation analysis system based on unmanned aerial vehicle inspection |
| CN114489143A (en) * | 2022-04-02 | 2022-05-13 | 清华大学 | Unmanned aerial vehicle management system, method and device for construction safety risk monitoring |
| CN115086607A (en) * | 2022-06-14 | 2022-09-20 | 国网山东省电力公司电力科学研究院 | Electric power construction monitoring system, monitoring method and computer equipment |
| CN115048874A (en) * | 2022-08-16 | 2022-09-13 | 北京航空航天大学 | Aircraft design parameter estimation method based on machine learning |
| CN115375154A (en) * | 2022-08-29 | 2022-11-22 | 黑龙江农业工程职业学院 | Building construction quality safety online risk management system |
| CN115565330A (en) * | 2022-09-22 | 2023-01-03 | 中建八局发展建设有限公司 | Building construction site spot-distribution type fire monitoring system and method |
Non-Patent Citations (1)
| Title |
|---|
| 基于深度学习的航拍绝缘子缺陷检测研究;吴涛;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》(第02期);第C042-176页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116050842A (en) | 2023-05-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109360239B (en) | Obstacle detection method, obstacle detection device, computer device, and storage medium | |
| KR102042629B1 (en) | Situational recognition system for construction site based vision and method, and method for productivity analysis of earthwork using it | |
| CN113505499B (en) | Hydraulic engineering building full life cycle management system based on BIM and big data analysis | |
| WO2020181508A1 (en) | Digital surface model construction method, and processing device and system | |
| CN109163698A (en) | Building settlement measurement method, device and storage medium | |
| CN115546628A (en) | Hydraulic engineering dam crack monitoring method, device, equipment and medium | |
| CN114413854B (en) | Real-scene three-dimensional image checking system based on oblique photography | |
| CN116050842B (en) | Dynamic control method and system for urban underground engineering construction safety risk | |
| CN114291025A (en) | Vehicle collision detection method and system based on data segmentation aggregation distribution | |
| CN111640109B (en) | Model detection method and system | |
| CN114235082B (en) | Intelligent metering method based on sand production monitoring system | |
| CN114419112A (en) | Building construction height identification method and device and electronic equipment | |
| CN111190975A (en) | River channel patrol method for calculating task track coverage rate according to GPS data | |
| CN116137010A (en) | Pile foundation construction quality determining method and device, electronic equipment and storage medium | |
| CN114898277A (en) | Method, device, storage medium and processor for identifying pipeline security risk | |
| CN114838704A (en) | Height detection method and device and computer readable storage medium | |
| JP2022145441A (en) | Survey information management system, survey information management method, and survey information management program | |
| CN111189533B (en) | External force invasion monitoring method and device, computer equipment and storage medium | |
| CN111985358A (en) | Ship lock running state monitoring method and system, computer equipment and storage medium | |
| CN117036611B (en) | Three-dimensional scene construction method and system of non-mine safety monitoring platform | |
| CN113532283B (en) | Method for monitoring foundation pit displacement trend based on consumption-level unmanned aerial vehicle and GPS (global positioning system) | |
| CN113570122B (en) | Method, device, computer equipment and storage medium for predicting wind speed | |
| CN117492472B (en) | Area refusing method and system for low-speed unmanned aerial vehicle | |
| CN115494878B (en) | Unmanned aerial vehicle line patrol path adjustment method and device based on obstacle avoidance | |
| CN118129671A (en) | Civil air defense door position detection method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |