CN114326625B - Monitoring system and method for potential safety risk in power grid infrastructure construction - Google Patents
Monitoring system and method for potential safety risk in power grid infrastructure construction Download PDFInfo
- Publication number
- CN114326625B CN114326625B CN202111627805.5A CN202111627805A CN114326625B CN 114326625 B CN114326625 B CN 114326625B CN 202111627805 A CN202111627805 A CN 202111627805A CN 114326625 B CN114326625 B CN 114326625B
- Authority
- CN
- China
- Prior art keywords
- risk
- data
- module
- site
- target
- 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
Classifications
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Alarm Systems (AREA)
- Emergency Alarm Devices (AREA)
Abstract
The invention discloses a system and a method for monitoring potential safety risk in power grid infrastructure construction, comprising the following steps: identifying, tracking and collecting data of an operation site target; performing data matching, target detection, identification classification, region segmentation and on-site personnel identity and behavior identification on the acquired data to form target data and performing data comparison with a risk decision library; performing operation site risk judgment, audible and visual alarm and risk plan execution according to the data comparison information; judging whether the risk of the operation site is relieved or not and transmitting judging information; receiving the judging information and performing audible and visual alarm; remotely receiving a work log and monitoring; according to the invention, the on-site management and control are carried out by using the artificial intelligent software and hardware technical means, the on-site operation personnel are automatically supervised and reminded of the behavior specification, the on-site variables are timely controlled by monitoring the on-site main risk control conditions, the fundamental purpose of eliminating the construction safety risk is achieved, and the artificial intelligent auxiliary power grid construction management is realized.
Description
Technical Field
The invention relates to the technical field of power safety production risk management and control, in particular to an image recognition algorithm for autonomously recognizing potential safety risks in power grid infrastructure construction.
Background
Along with the continuous development of power grid construction, the construction task of electric power engineering construction is more and more heavy, the transmission line is developed towards multiple loops and large load directions, and especially under the construction environment of complex geographical environment and severe climate, the on-site command of key data of traditional pole and tower assembly construction is difficult to control, the safety risk of iron tower assembly is extremely high, and the construction of electric power transmission and transformation engineering, especially the construction of lines, is an important factor for accidents because the construction is field operation, complex terrain, wide in points and multiple sides, difficult to apply to traditional large machinery, extremely high in on-site variables, sudden on-site changes in the construction process and difficult to anticipate in advance.
The prior power grid construction safety management measures have a plurality of problems:
1. the resource allocation is seriously unbalanced, the line construction is long, the operation labor is more, the risk is higher, a great amount of manpower and material resources are needed to be input for process control, the wages of constructors are increased year by year at the present stage, and the ageing of the operators is serious;
2. the construction requirements of the working layer teams are high, the working layer teams are required to be provided with construction backbone staff for work such as organization, command, management and control of the work, and the like, and the construction is performed on multiple working surfaces simultaneously, so that the number and quality of the staff are difficult to meet the requirements;
3. the lack of powerful grip for personnel management, difficult field environment for line construction, long working period, easy and relaxed safety consciousness of constructors, and unacceptable for continuously improved management modes, habitual experience mistakes;
4. the ball distribution system configured on the construction site basically adopts tripod fixed ball distribution equipment, cannot move autonomously, and needs frequent manual intervention in the use process; in addition, on the aspect of data processing, the on-site risk cannot be automatically pre-judged and decided, and the on-site risk still needs to be manually managed.
Therefore, how to provide a method capable of timely finding, distinguishing and eliminating construction safety risks and realizing artificial intelligent auxiliary power grid construction management is a problem to be solved by those skilled in the art.
Disclosure of Invention
In view of the above, the invention provides a system and a method for monitoring potential safety risks in power grid infrastructure construction, which utilize artificial intelligence software and hardware technology means to perform field control so as to achieve the purposes of timely controlling construction field variables and eliminating construction safety risks.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a system for monitoring potential safety risk in power grid infrastructure construction, comprising: the intelligent infrastructure management equipment and the remote control center are used for data transmission;
the intelligent infrastructure management equipment comprises an operation site data acquisition module, a risk decision library retrieval module, a risk decision library processing module, a risk release judgment module and an audible and visual alarm module;
the operation site data acquisition module is used for identifying, tracking and acquiring data of an operation site target;
the risk decision library retrieval module is used for receiving the acquired data of the operation site data acquisition module, carrying out data matching, target detection, identification classification, region segmentation and site personnel identity and behavior identification on the acquired data, forming target data and carrying out data comparison with a risk decision library;
the risk decision library processing module is used for receiving the data comparison information of the risk decision library retrieval module and carrying out operation site risk judgment and risk plan execution according to the data comparison information;
the risk release judging module is in communication connection with the risk decision processing module and is used for judging whether the risk of the operation site is released or not and transmitting judging information to the audible and visual alarm module and the remote control center;
the audible and visual alarm module is used for receiving the judging signal of the risk decision processing module and the judging signal of the risk release judging module and performing audible and visual alarm;
the remote control center is respectively in communication connection with the risk decision library processing module and the risk release judging module and is used for receiving and monitoring the work logs of the risk decision library processing module and the risk release judging module.
Preferably, the operation site data acquisition module comprises a target tracking unit, an equipment data acquisition unit, a behavior data acquisition unit and a personnel data acquisition unit;
the target tracking unit is used for detecting a target and tracking in real time by adopting a deep source algorithm, autonomously generating a patrol path of a construction site and sending an acquisition signal;
the equipment data acquisition unit, the behavior data acquisition unit and the personnel data acquisition unit receive the acquisition signals of the target tracking unit to acquire data;
the equipment data acquisition unit is used for acquiring images and video screen data of the power grid infrastructure construction field equipment;
the behavior data acquisition unit is used for acquiring behavior data of site constructors;
the personnel data acquisition unit is used for acquiring identity and physical sign data of on-site construction personnel.
Preferably, the risk decision library retrieval module comprises a data processing sub-module and a data retrieval comparison sub-module;
the data processing sub-module comprises a data matching unit, a target detection unit, an identification classification unit, a region segmentation unit and a personnel identity and behavior identification unit;
the data matching unit receives the data acquired by the equipment data acquisition unit, the behavior data acquisition unit and the personnel data acquisition unit and is used for performing data matching on the acquired data;
the target detection unit receives the data of the data matching unit, and a YoloV5 algorithm is adopted for detecting the specific position of a target object in the data;
the identification classification unit receives the data of the data matching unit, and adopts a mask RCNN algorithm to identify the target objects and finely distinguish the target objects;
the region segmentation unit receives the data of the data matching unit, and uses an SKNet algorithm for segmenting the target object and the background;
the personnel identity and behavior recognition unit receives the data of the data matching unit and is used for the face recognition of field constructors and the recognition of specific behaviors;
the data retrieval and comparison sub-module is used for receiving the target data and carrying out retrieval and comparison with a risk decision library to obtain specific risk problems and a correction scheme.
Preferably, the risk decision processing module comprises a risk decision unit and a risk plan execution unit;
the risk determination unit is configured to determine a risk type, where the risk type includes: single risk, more than one similar risk and combined risk, and when the risk type is the combined risk, adopting an SKNet algorithm to judge the priority level of each risk in the combined risk;
the risk plan execution unit is used for executing the modification scheme of the risk decision library according to the risk problem, the modification scheme and the result of the priority level judgment;
and the audible and visual alarm module receives the judging signals of the risk judging unit and the risk relieving judging module and performs audible and visual alarm.
Preferably, the risk relieving judging module is used for judging whether the risk is relieved, if the risk is relieved, the risk relieving judging module sends an alarm ending command, the audible and visual alarm module ends the alarm, and if the risk is not relieved, the risk relieving judging module sends a continuing alarm command, the audible and visual alarm module continues to alarm, and a job site management and control personnel performs manual intervention.
The method for monitoring the potential safety risk in the construction of the power grid infrastructure is characterized by comprising the following steps of:
s1, identifying, tracking and collecting data of an operation site target;
s2, carrying out data matching, target detection, identification classification, region segmentation and on-site personnel identity and behavior identification on the acquired data to form target data and carrying out data comparison with a risk decision library;
s3, performing operation site risk judgment, audible and visual alarm and risk plan execution according to the data comparison information;
s4, judging whether the risk of the operation site is relieved or not and transmitting judging information; receiving the judging information and performing audible and visual alarm;
s5, remotely receiving the work log and monitoring.
Preferably, the specific content of S1 includes:
target tracking, namely detecting a target and tracking in real time by adopting a DeepSort algorithm, autonomously generating a patrol path for a construction site and sending a collection command;
acquiring equipment data, namely acquiring images and video screen data of power grid infrastructure construction field equipment according to the acquisition command;
acquiring behavior data of on-site constructors according to the acquired signals;
and a personnel data acquisition command for acquiring the identity and physical sign data of the on-site constructor according to the acquisition signal.
Preferably, the step S2 comprises data processing and data retrieval comparison;
the data processing concrete content comprises the following steps:
data matching, namely performing data matching on the acquired data;
detecting a target, namely detecting the specific position of a target object in matched data by adopting a YoloV5 algorithm according to the matched data;
identifying and classifying, namely identifying the target object by adopting a mask RCNN algorithm according to the matched data and finely distinguishing the target object;
region segmentation, namely segmenting a target object and a background by adopting an SKNet algorithm according to the matched data;
identifying the identity and the behaviors of the personnel, and carrying out the face recognition and the specific behavior recognition of the site constructors according to the matched data;
and the specific content of the data retrieval and comparison is that the target data is received and is retrieved and compared with the risk decision library, so that specific risk problems and correction schemes are obtained.
Preferably, the specific content of S3 includes:
determining a risk type, the risk type comprising: single risk, more than one similar risk and combined risk, and when the risk type is the combined risk, adopting an SKNet algorithm to judge the priority level of each risk in the combined risk;
performing audible and visual alarm according to the risk judgment signal;
and executing the modification scheme of the risk decision library according to the risk problems, the modification scheme and the result of the priority level judgment.
Preferably, the specific content of S4 includes: and judging whether the risk is relieved, if the risk is relieved, ending the alarm by the command, and if the risk is not relieved, continuing to maintain the audible and visual alarm by the command, and performing manual intervention by the operation site management and control personnel.
Compared with the prior art, the system and the method for monitoring the potential safety risk in the power grid infrastructure construction are disclosed, the intelligent infrastructure management unit hardware with the remote transmission function is used for completing the autonomous tracking and acquisition of the first hand real-time field device data, the personnel data and the behavior data of a modern construction team on site, realizing autonomous analysis and judgment at the first time and alarming the risky behavior in real time, so that the input quantity of field process supervision personnel is reduced.
Through the deep learning of the construction scheme, the operation site is supervised in real time, and the rigid execution construction scheme assists engineering technicians to finish the optimization and adjustment of the construction scheme, so that the consistency of the scheme and the site is practically improved, and the requirements on the professional literacy of site supervision and acceptance personnel are reduced.
Through deep learning of a plurality of modern construction data, an artificial intelligent algorithm is optimized, so that risk discovery efficiency is improved, risks are discovered even earlier than in a traditional mode, and violations and even safety accidents are avoided.
Through a series of software and hardware technological means such as autonomous identification, early warning, real-time feedback, even remote command and the like, the whole management decision-making process of the national network foundation site is shortened, unstable factors of personnel in the operation process are reduced, professional experience of professional personnel is solidified, and a data foundation is laid for future mechanized construction and intelligent construction.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic diagram of a workflow provided by the present invention;
FIG. 2 is a schematic diagram of object detection according to the present invention;
FIG. 3 is a schematic diagram of the identification classification provided by the present invention;
FIG. 4 is a schematic view of region segmentation provided by the present invention;
FIG. 5 is a schematic diagram of monitoring potential safety risks in a tower assembly construction according to an embodiment;
fig. 6 is a schematic diagram of detection of potential safety risk of heavy object lifting construction according to an embodiment.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The embodiment of the invention discloses a monitoring system for potential safety risk in power grid infrastructure construction, which is characterized by comprising the following components: the intelligent infrastructure management equipment and the remote control center are used for data transmission;
the intelligent infrastructure management equipment comprises an operation site data acquisition module, a risk decision library retrieval module, a risk decision library processing module, a risk release judgment module and an audible and visual alarm module;
the operation site data acquisition module is used for identifying, tracking and acquiring data of an operation site target;
the risk decision library retrieval module is used for receiving the acquired data of the operation site data acquisition module, carrying out data matching, target detection, identification classification, region segmentation and site personnel identity and behavior identification on the acquired data, forming target data and carrying out data comparison with the risk decision library;
the risk decision-making library processing module is used for receiving the data comparison information of the risk decision-making library retrieval module and carrying out operation site risk judgment and risk plan execution according to the data comparison information;
the risk release judging module is in communication connection with the risk decision processing module and is used for judging whether the risk of the operation site is released or not and transmitting judging information to the audible and visual alarm module and the remote control center;
the audible and visual alarm module is used for receiving the judging signal of the risk decision processing module and the judging signal of the risk release judging module and carrying out audible and visual alarm;
the remote control center is respectively in communication connection with the risk decision library processing module and the risk release judging module and is used for receiving the work logs of the risk decision library processing module and the risk release judging module and monitoring.
In order to further implement the technical scheme, the operation site data acquisition module comprises a target tracking unit, an equipment data acquisition unit, a behavior data acquisition unit and a personnel data acquisition unit;
the target tracking unit is used for detecting a target and tracking in real time by adopting a deep source algorithm, autonomously generating a patrol path of a construction site and sending an acquisition signal;
the equipment data acquisition unit, the behavior data acquisition unit and the personnel data acquisition unit receive acquisition signals of the target tracking unit to acquire data;
the equipment data acquisition unit is used for acquiring images and video screen data of the power grid foundation construction field equipment;
the behavior data acquisition unit is used for acquiring behavior data of site constructors;
and the personnel data acquisition unit is used for acquiring the identity and physical sign data of the on-site constructors.
In order to further implement the technical scheme, the risk decision-making library retrieval module comprises a data processing sub-module and a data retrieval comparison sub-module;
the data processing sub-module comprises a data matching unit, a target detection unit, an identification classification unit, a region segmentation unit and a personnel identity and behavior identification unit;
the data matching unit receives the data acquired by the equipment data acquisition unit, the behavior data acquisition unit and the personnel data acquisition unit and is used for carrying out data matching on the acquired data;
the target detection unit receives the data of the data matching unit, and uses a YoloV5 algorithm to detect the specific position of the target object in the data, as shown in fig. 2;
the identification classification unit receives the data of the data matching unit, and adopts a maskRCNN algorithm to identify the target objects and finely distinguish the target objects, as shown in figure 3;
the region segmentation unit receives the data of the data matching unit, and uses the SKNet algorithm for segmentation of the target object and the background, as shown in figure 4;
the personnel identity and behavior recognition unit receives the data of the data matching unit and is used for the face recognition of field constructors and the recognition of specific behaviors;
and the data retrieval and comparison sub-module is used for receiving the target data and carrying out retrieval and comparison with the risk decision library to obtain specific risk problems and a rectification scheme.
In order to further implement the technical scheme, the risk decision processing module comprises a risk decision unit and a risk plan execution unit;
the risk judging unit is used for judging the risk type, and the risk type comprises: single risk, more than one similar risk and combined risk, and when the risk type is the combined risk, judging each risk priority level in the combined risk by adopting an SKNet algorithm;
the risk plan execution unit is used for executing the modification scheme of the risk decision library according to the risk problems, the modification scheme and the result of priority level judgment;
and the audible and visual alarm module receives the judging signals of the risk judging unit and the risk relieving judging module and performs audible and visual alarm.
In order to further implement the technical scheme, the risk relieving alarm device is used for judging whether the risk is relieved, if the risk is relieved, the risk relieving judging module sends an alarm ending command, the audible and visual alarm module finishes the alarm, if the risk is not relieved, the risk relieving judging module sends a continuing alarm command, the audible and visual alarm module continues to alarm, and the operation site management and control personnel conduct manual intervention.
A method for monitoring potential safety risk in power grid infrastructure construction, as shown in fig. 1, comprising the following steps:
s1, identifying, tracking and collecting data of an operation site target;
s2, carrying out data matching, target detection, identification classification, region segmentation and on-site personnel identity and behavior identification on the acquired data to form target data and carrying out data comparison with a risk decision library;
s3, performing operation site risk judgment, audible and visual alarm and risk plan execution according to the data comparison information;
s4, judging whether the risk of the operation site is relieved or not and transmitting judging information; receiving the judgment information and performing audible and visual alarm;
s5, remotely receiving the work log and monitoring.
In order to further implement the above technical solution, the specific content of S1 includes:
target tracking, namely detecting a target and tracking in real time by adopting a DeepSort algorithm, autonomously generating a patrol path for a construction site and sending a collection command;
acquiring equipment data, namely acquiring images and video screen data of power grid infrastructure construction field equipment according to an acquisition command;
behavior data acquisition, namely acquiring behavior data of site constructors according to acquisition signals;
and a personnel data acquisition command for acquiring the identity and physical sign data of the on-site constructors according to the acquisition signals.
In order to further implement the above technical solution, S2 includes data processing and data retrieval comparison;
the data processing concrete content comprises:
data matching, namely performing data matching on the acquired data;
target detection, namely detecting the specific position of a target object in matched data by adopting a YoloV5 algorithm according to the matched data, as shown in figure 2;
in practical application, the method adopts a YoloV5 algorithm to detect whether a grinding machine and a position exist on site, if so, the offset distance and the angular orientation of the grinding machine and the offset distance Y from a body are recorded;
identifying and classifying, namely identifying target objects by adopting a maskRCNN algorithm according to the matched data and finely distinguishing the target objects, as shown in figure 3;
in practical application, the MASKRNN algorithm can be used for judging whether the steel cable exists on the roller or not and distinguishing the steel cable, if not, entering other risk management and identification states, and if yes, judging that the steel cable has a plurality of circles;
region segmentation, namely segmenting a target object and a background by adopting an SKNet algorithm according to the matched data, as shown in figure 4;
identifying the identity and the behaviors of the personnel, and carrying out the face recognition and the specific behavior recognition of the site constructors according to the matched data;
the specific content of the data retrieval and comparison is that the target data is received and is retrieved and compared with a risk decision library, so that specific risk problems and a correction scheme are obtained.
In order to further implement the above technical solution, the specific content of S3 includes:
determining a risk type, wherein the risk type comprises: single risk, more than one similar risk and combined risk, and when the risk type is the combined risk, judging each risk priority level in the combined risk by adopting an SKNet algorithm;
performing audible and visual alarm according to a judging signal of risk judgment;
and executing the modification scheme of the risk decision library according to the risk problems, the modification scheme and the result of the priority level judgment.
When the risk type is the combined risk, and different risks in the combined risk occur simultaneously or are close to occurring simultaneously, the body based on the AI technology can autonomously judge the priority level of the risk according to different scenes, and give priority to alarm the high-level risk and execute the rectification scheme.
In order to further implement the above technical solution, the specific content of S4 includes: and judging whether the risk is relieved, if the risk is relieved, ending the alarm by the command, and if the risk is not relieved, continuing to maintain the audible and visual alarm by the command, and performing manual intervention by the operation site management and control personnel.
As shown in fig. 5, taking as an example, the monitoring of potential safety risk in the tower assembly construction in the power grid infrastructure project is further described:
in practical application, the invention can be realized by using a mobile robot, the mobile robot collects image materials on a pole tower assembly construction site through a camera, and target data is formed through data matching, target detection, identification classification, region segmentation and on-site personnel identity and behavior identification;
the target data are searched and compared with the content of a pole tower assembly construction safety risk database in a risk decision library, the pole tower assembly safety risk data comprise the steps that the pole selection is 300 x 300 to 900 x 900, the pole length is 4.2 meters to 6.0 meters, the thickness of a steel wire rope is consistent with a construction scheme, the tower assembly mode is consistent with the construction scheme, nuts are not fastened in time after a pedal is in place, the extending part of the pole is larger than 2/3 of the total length of the pole, a wringing mill winds less than 5 circles, the distance between the wringing mill and a person is smaller than 2.5 meters, a small pole is not allowed to be fixed on a tree by using a tower material and the steel wire rope, and specific risk problems and correction schemes corresponding to the risk database are obtained through search and comparison;
performing risk type judgment and audible and visual alarm, when the risk type is judged to be single risk and multiple similar risks, executing modification according to specific risk problems and modification schemes, and when the risk type is judged to be combined risk, judging a priority level according to high-level risk decision, and executing the modification scheme again;
and the mobile robot approaches to a preset position to observe and judge whether the risk is relieved, if the risk is not relieved, the mobile robot continues to give an alarm and intervene and rectify the risk manually, and if the risk is relieved, the mobile robot returns to the original position to continue monitoring the construction.
As shown in fig. 6, the potential safety risk monitoring during the hoisting of heavy objects in the grid infrastructure is further described as an example:
the crane starts an automatic lifting weight mode, a mobile robot automatically searches the position of a tower to judge the distance and moves a chassis to a proper position, the chassis is opposite to the tower, edge columns of the tower are detected to coincide, a camera adjusts the focal length and the angle, the weight and the lower part of the weight are detected and image materials are acquired, the acquired image materials are processed and are searched and compared with the safety risk database content of the lifted weight in a risk decision library to judge whether the lower part of the weight has a person's risk, if the risk is detected, an audible and visual alarm is carried out, a corresponding correction scheme is started according to a risk priority decision logic, a background management center is called and a field manager is notified to perform manual intervention, then whether the risk is relieved is judged, if the risk is not relieved, the alarm is continued and the correction is carried out, and if the risk is relieved, the audible and visual alarm is relieved and the monitoring is continued.
In the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, and identical and similar parts between the embodiments are all enough to refer to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A system for monitoring potential safety risk in power grid infrastructure construction, comprising: the intelligent infrastructure management equipment and the remote control center are used for data transmission;
the intelligent infrastructure management equipment comprises an operation site data acquisition module, a risk decision library retrieval module, a risk decision library processing module, a risk release judgment module and an audible and visual alarm module;
the operation site data acquisition module is used for identifying, tracking and acquiring data of an operation site target;
the risk decision library retrieval module is used for receiving the acquired data of the operation site data acquisition module, carrying out data matching, target detection, identification classification, region segmentation and site personnel identity and behavior identification on the acquired data, forming target data and carrying out data comparison with a risk decision library;
the risk decision library processing module is used for receiving the data comparison information of the risk decision library retrieval module and carrying out operation site risk judgment and risk plan execution according to the data comparison information;
the risk release judging module is in communication connection with the risk decision processing module and is used for judging whether the risk of the operation site is released or not and transmitting judging information to the audible and visual alarm module and the remote control center;
the audible and visual alarm module is used for receiving the judging signal of the risk decision processing module and the judging signal of the risk release judging module and performing audible and visual alarm;
the remote control center is respectively in communication connection with the risk decision library processing module and the risk release judging module and is used for receiving and monitoring the work logs of the risk decision library processing module and the risk release judging module;
the operation site data acquisition module comprises a target tracking unit, an equipment data acquisition unit, a behavior data acquisition unit and a personnel data acquisition unit;
the risk decision library retrieval module comprises a data processing sub-module and a data retrieval comparison sub-module;
the data processing sub-module comprises a data matching unit, a target detection unit, an identification classification unit, a region segmentation unit and a personnel identity and behavior identification unit;
the data matching unit receives the data acquired by the equipment data acquisition unit, the behavior data acquisition unit and the personnel data acquisition unit and is used for performing data matching on the acquired data;
the target detection unit receives the data of the data matching unit, and a YoloV5 algorithm is adopted for detecting the specific position of a target object in the data;
the identification classification unit receives the data of the data matching unit, and adopts a mask RCNN algorithm to identify the target objects and finely distinguish the target objects;
the region segmentation unit receives the data of the data matching unit, and uses an SKNet algorithm for segmenting the target object and the background;
the personnel identity and behavior recognition unit receives the data of the data matching unit and is used for the face recognition of field constructors and the recognition of specific behaviors;
the data retrieval and comparison sub-module is used for receiving the target data and carrying out retrieval and comparison with a risk decision library to obtain specific risk problems and a correction scheme.
2. A system for monitoring potential safety risk in electrical grid construction according to claim 1,
the target tracking unit is used for detecting a target and tracking in real time by adopting a deep source algorithm, autonomously generating a patrol path of a construction site and sending an acquisition signal;
the equipment data acquisition unit, the behavior data acquisition unit and the personnel data acquisition unit receive the acquisition signals of the target tracking unit to acquire data;
the equipment data acquisition unit is used for acquiring image and video data of the power grid infrastructure construction field equipment;
the behavior data acquisition unit is used for acquiring behavior data of site constructors;
the personnel data acquisition unit is used for acquiring identity and physical sign data of on-site construction personnel.
3. The system for monitoring potential safety risk in power grid infrastructure construction according to claim 1, wherein the risk decision processing module comprises a risk decision unit and a risk plan execution unit;
the risk determination unit is configured to determine a risk type, where the risk type includes: single risk, more than one similar risk and combined risk, and when the risk type is the combined risk, adopting an SKNet algorithm to judge the priority level of each risk in the combined risk;
the risk plan execution unit is used for executing the modification scheme of the risk decision library according to the risk problem, the modification scheme and the result of the priority level judgment;
and the audible and visual alarm module receives the judging signals of the risk judging unit and the risk relieving judging module and performs audible and visual alarm.
4. A system for monitoring potential safety risk in electrical network infrastructure construction according to claim 3, wherein the system is used for judging whether the risk is released, if the risk is released, the risk release judging module sends an alarm ending command, the audible and visual alarm module ends the alarm, if the risk is not released, the risk release judging module sends a continue alarm command, the audible and visual alarm module continues the alarm, and the operation site management personnel performs manual intervention.
5. The method for monitoring the potential safety risk in the construction of the power grid infrastructure is characterized by comprising the following steps of:
s1, identifying, tracking and collecting data of an operation site target;
s2, carrying out data matching, target detection, identification classification, region segmentation and on-site personnel identity and behavior identification on the acquired data to form target data and carrying out data comparison with a risk decision library;
s3, performing operation site risk judgment, audible and visual alarm and risk plan execution according to the data comparison information;
s4, judging whether the risk of the operation site is relieved or not and transmitting judging information; receiving the judging information and performing audible and visual alarm;
s5, remotely receiving the work log and monitoring;
s2 comprises data processing and data retrieval comparison;
the data processing concrete content comprises the following steps:
data matching, namely performing data matching on the acquired data;
detecting a target, namely detecting the specific position of a target object in matched data by adopting a YoloV5 algorithm according to the matched data;
identifying and classifying, namely identifying the target object by adopting a mask RCNN algorithm according to the matched data and finely distinguishing the target object;
region segmentation, namely segmenting a target object and a background by adopting an SKNet algorithm according to the matched data;
identifying the identity and the behaviors of the personnel, and carrying out the face recognition and the specific behavior recognition of the site constructors according to the matched data;
and the specific content of the data retrieval and comparison is that the target data is received and is retrieved and compared with the risk decision library, so that specific risk problems and correction schemes are obtained.
6. The method for monitoring potential safety risk in power grid infrastructure construction according to claim 5, wherein the S1 concrete content comprises:
target tracking, namely detecting a target and tracking in real time by adopting a DeepSort algorithm, autonomously generating a patrol path for a construction site and sending a collection command;
acquiring equipment data, namely acquiring image and video data of power grid infrastructure construction field equipment according to the acquisition command;
behavior data acquisition, namely acquiring behavior data of site constructors according to acquisition signals;
and acquiring personnel data, namely acquiring the identity and physical sign data of the site constructors according to the acquired signals.
7. The method for monitoring potential safety risk in power grid infrastructure construction according to claim 5, wherein the S3 concrete content comprises:
determining a risk type, the risk type comprising: single risk, more than one similar risk and combined risk, and when the risk type is the combined risk, adopting an SKNet algorithm to judge the priority level of each risk in the combined risk;
performing audible and visual alarm according to the risk judgment signal;
and executing the modification scheme of the risk decision library according to the risk problems, the modification scheme and the result of the priority level judgment.
8. The method for monitoring potential safety risk in power grid infrastructure construction according to claim 7, wherein the S4 concrete content comprises: and judging whether the risk is relieved, if the risk is relieved, ending the alarm by the command, and if the risk is not relieved, continuing to maintain the audible and visual alarm by the command, and performing manual intervention by the operation site management and control personnel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111627805.5A CN114326625B (en) | 2021-12-28 | 2021-12-28 | Monitoring system and method for potential safety risk in power grid infrastructure construction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111627805.5A CN114326625B (en) | 2021-12-28 | 2021-12-28 | Monitoring system and method for potential safety risk in power grid infrastructure construction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114326625A CN114326625A (en) | 2022-04-12 |
| CN114326625B true CN114326625B (en) | 2023-08-25 |
Family
ID=81015340
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111627805.5A Active CN114326625B (en) | 2021-12-28 | 2021-12-28 | Monitoring system and method for potential safety risk in power grid infrastructure construction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114326625B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115050160B (en) * | 2022-05-31 | 2024-02-23 | 中冶华天南京工程技术有限公司 | Intelligent safety supervision device for industrial unmanned production site |
| CN116245369A (en) * | 2023-03-28 | 2023-06-09 | 江苏鼎达电气科技有限公司 | Digital intelligent construction management system and method for hydraulic engineering |
| CN116797031B (en) * | 2023-08-25 | 2023-10-31 | 深圳市易图资讯股份有限公司 | Safety production management method and system based on data acquisition |
Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102201061A (en) * | 2011-06-24 | 2011-09-28 | 常州锐驰电子科技有限公司 | Intelligent safety monitoring system and method based on multilevel filtering face recognition |
| CA2821820A1 (en) * | 2012-03-14 | 2013-09-14 | South East Water Corporation | Pressure sewer control system and method |
| CN105205624A (en) * | 2015-10-29 | 2015-12-30 | 云南电网有限责任公司昆明供电局 | Enterprise probity risk monitoring system |
| CN107939447A (en) * | 2017-12-07 | 2018-04-20 | 重庆天府矿业有限责任公司 | A kind of safety of coal mines risk stratification early warning management-control method and system |
| CN110524559A (en) * | 2019-08-30 | 2019-12-03 | 成都未至科技有限公司 | Intelligent human-machine interaction system and method based on human behavior data |
| CN111445106A (en) * | 2020-03-02 | 2020-07-24 | 国网辽宁省电力有限公司电力科学研究院 | Power utilization acquisition equipment fault processing operation site safety control method and system |
| WO2020222392A1 (en) * | 2019-04-29 | 2020-11-05 | 경희대학교산학협력단 | Method for robot safety evaluation on basis of collision force bigdata that enables real-time robot collision risk monitoring using graphic information |
| CN112112629A (en) * | 2019-06-19 | 2020-12-22 | 中国石油化工股份有限公司 | Safety business management system and method in drilling operation process |
| CN112152314A (en) * | 2020-08-13 | 2020-12-29 | 国网浙江省电力有限公司 | Centralized monitoring transformer substation risk identification early warning system and working method thereof |
| CN112185515A (en) * | 2020-10-12 | 2021-01-05 | 安徽动感智能科技有限公司 | Patient auxiliary system based on action recognition |
| CN112218811A (en) * | 2018-03-09 | 2021-01-12 | 瑞泰控股公司 | Method and apparatus for monitoring and managing loading station and facility operation |
| CN112819374A (en) * | 2021-02-26 | 2021-05-18 | 南京理工大学 | System and method for risk management of railway bridge constructors |
| KR102291259B1 (en) * | 2020-02-28 | 2021-08-20 | 주식회사 그릿테크 | Ai system based on edge-computing for reinforcing safe-management in industrial site |
| CN113837657A (en) * | 2021-10-15 | 2021-12-24 | 山东联安信息科技有限责任公司 | Live working risk identification early warning and emergency disposal method |
-
2021
- 2021-12-28 CN CN202111627805.5A patent/CN114326625B/en active Active
Patent Citations (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102201061A (en) * | 2011-06-24 | 2011-09-28 | 常州锐驰电子科技有限公司 | Intelligent safety monitoring system and method based on multilevel filtering face recognition |
| CA2821820A1 (en) * | 2012-03-14 | 2013-09-14 | South East Water Corporation | Pressure sewer control system and method |
| CN105205624A (en) * | 2015-10-29 | 2015-12-30 | 云南电网有限责任公司昆明供电局 | Enterprise probity risk monitoring system |
| CN107939447A (en) * | 2017-12-07 | 2018-04-20 | 重庆天府矿业有限责任公司 | A kind of safety of coal mines risk stratification early warning management-control method and system |
| CN112218811A (en) * | 2018-03-09 | 2021-01-12 | 瑞泰控股公司 | Method and apparatus for monitoring and managing loading station and facility operation |
| WO2020222392A1 (en) * | 2019-04-29 | 2020-11-05 | 경희대학교산학협력단 | Method for robot safety evaluation on basis of collision force bigdata that enables real-time robot collision risk monitoring using graphic information |
| CN112112629A (en) * | 2019-06-19 | 2020-12-22 | 中国石油化工股份有限公司 | Safety business management system and method in drilling operation process |
| CN110524559A (en) * | 2019-08-30 | 2019-12-03 | 成都未至科技有限公司 | Intelligent human-machine interaction system and method based on human behavior data |
| KR102291259B1 (en) * | 2020-02-28 | 2021-08-20 | 주식회사 그릿테크 | Ai system based on edge-computing for reinforcing safe-management in industrial site |
| CN111445106A (en) * | 2020-03-02 | 2020-07-24 | 国网辽宁省电力有限公司电力科学研究院 | Power utilization acquisition equipment fault processing operation site safety control method and system |
| CN112152314A (en) * | 2020-08-13 | 2020-12-29 | 国网浙江省电力有限公司 | Centralized monitoring transformer substation risk identification early warning system and working method thereof |
| CN112185515A (en) * | 2020-10-12 | 2021-01-05 | 安徽动感智能科技有限公司 | Patient auxiliary system based on action recognition |
| CN112819374A (en) * | 2021-02-26 | 2021-05-18 | 南京理工大学 | System and method for risk management of railway bridge constructors |
| CN113837657A (en) * | 2021-10-15 | 2021-12-24 | 山东联安信息科技有限责任公司 | Live working risk identification early warning and emergency disposal method |
Non-Patent Citations (1)
| Title |
|---|
| 钻井过程人员异常行为视频智能识别系统;王文正;吴德松;李千登;;安全、健康和环境(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114326625A (en) | 2022-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114326625B (en) | Monitoring system and method for potential safety risk in power grid infrastructure construction | |
| CN112785798B (en) | Behavior analysis method for constructors of power substation engineering construction project | |
| US20210349476A1 (en) | Method and apparatus for controlling cruise of unmanned air vehicle based on prefabricated construction platform | |
| CN112149522A (en) | Intelligent visual external-damage-prevention monitoring system and method for cable channel | |
| CN211509189U (en) | Electric power operation field supervision equipment and system | |
| CN110765848A (en) | Chemical plant personnel safety guarantee system and early warning method based on artificial intelligence image processing algorithm | |
| CN112613454A (en) | Electric power infrastructure construction site violation identification method and system | |
| CN115527340A (en) | Intelligent construction site safety monitoring system and method based on unmanned aerial vehicle and surveillance camera | |
| CN117035419B (en) | Intelligent management system and method for enterprise project implementation | |
| CN112651642A (en) | Hydraulic engineering field personnel safety management system based on multi-device perception | |
| CN117474321B (en) | BIM model-based construction site risk intelligent identification method and system | |
| CN112798979A (en) | System and method for detecting state of grounding wire of transformer substation based on deep learning technology | |
| CN115494802A (en) | Flow operation multi-level safety digital intelligent monitoring system | |
| CN116193083A (en) | Safety identification system based on artificial intelligence | |
| CN116993665A (en) | Intelligent detection method for construction progress of construction engineering working face based on computer vision | |
| CN112036336B (en) | Engineering monitoring method and system based on AI intelligent image analysis | |
| CN113177475A (en) | Building site distribution box on-off state identification method based on deep learning target detection | |
| CN218214363U (en) | Smart pile terminal equipment of smart multipurpose | |
| CN111860202A (en) | Beam yard pedestal state identification method and system combining image identification and intelligent equipment | |
| CN116668637A (en) | Beam field video safety monitoring system and method | |
| CN115471911A (en) | Power grid operation field violation action identification method and system | |
| CN108399389B (en) | Multi-machine monitoring system and method for machine vision, client, server and storage medium | |
| CN114821459A (en) | Substation construction safety detection system and algorithm based on AI technology | |
| CN116030405A (en) | Pedestrian target safety protection tool wearing monitoring method based on artificial intelligence | |
| CN116030404A (en) | Artificial intelligence-based construction and safety monitoring method for electronic warning fence of operation area |
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 |