CN117115755B - Power operation site violation monitoring alarm recognition system based on image recognition - Google Patents
Power operation site violation monitoring alarm recognition system based on image recognition Download PDFInfo
- Publication number
- CN117115755B CN117115755B CN202311371606.1A CN202311371606A CN117115755B CN 117115755 B CN117115755 B CN 117115755B CN 202311371606 A CN202311371606 A CN 202311371606A CN 117115755 B CN117115755 B CN 117115755B
- Authority
- CN
- China
- Prior art keywords
- safety
- image
- safety terminal
- terminal
- data server
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 40
- 230000009471 action Effects 0.000 claims abstract description 20
- 230000006399 behavior Effects 0.000 claims abstract description 8
- 230000008859 change Effects 0.000 claims abstract description 5
- 238000009825 accumulation Methods 0.000 claims abstract description 4
- 238000000034 method Methods 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 8
- 238000012502 risk assessment Methods 0.000 claims description 5
- 238000004891 communication Methods 0.000 claims description 4
- 238000011217 control strategy Methods 0.000 claims description 4
- 230000007613 environmental effect Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 239000012535 impurity Substances 0.000 claims description 3
- 230000009191 jumping Effects 0.000 claims description 3
- 238000004806 packaging method and process Methods 0.000 claims description 3
- 238000010276 construction Methods 0.000 description 9
- 230000001174 ascending effect Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 238000007689 inspection Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 230000005611 electricity Effects 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000001788 irregular Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002650 habitual effect Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000007789 sealing Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- 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
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/94—Hardware or software architectures specially adapted for image or video understanding
- G06V10/95—Hardware or software architectures specially adapted for image or video understanding structured as a network, e.g. client-server architectures
-
- 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
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- 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
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Economics (AREA)
- Human Computer Interaction (AREA)
- Software Systems (AREA)
- Human Resources & Organizations (AREA)
- Psychiatry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Social Psychology (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Alarm Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of power engineering, in particular to a power operation site violation monitoring alarm recognition system based on image recognition, which comprises an image acquisition module, a safety terminal, a data server and a power remote supervision platform; the image acquisition module is responsible for acquiring operation images and face images of field workers and transmitting an image sequence to the safety terminal module; the safety terminal analyzes the safety risk and the operation specification of the image sequence, and if the safety risk and the operation non-specification are identified, the safety terminal executes early warning action; the power remote supervision platform takes over the safety terminal through the data server and remotely refrains or corrects the unnormal behaviors of staff through voice; and the data server can optimize the identification algorithm and the database along with the accumulation of data and the change of operation specifications, so that the security terminal software can be optimized and upgraded. The invention carries out comprehensive and omnibearing real-time early warning and real-time management and control on the electric power operation site, and can provide operation prompts.
Description
Technical Field
The invention relates to the technical field of power engineering, in particular to an image-based power operation site violation monitoring alarm recognition system.
Background
In the actual electric energy metering professional field operation process, due to the lack of effective field real-time monitoring, real-time discovery and real-time early warning means and wide metering field operation points, irregular habitual violations occur, and even casualties are caused. In addition, because on-site construction personnel are numerous, the construction of operators is complex, the quality of service is uneven, the safety consciousness is weak, and the construction operation is easy to be carried out without the standardization for convenience and rapidness. If the manual safety inspection is completely relied on, the workload is huge, the subjective feeling of the personnel is too strong, and the potential safety hazard is easily ignored.
Disclosure of Invention
In order to solve the problems, the invention realizes real-time control and early warning of site safety and site operation flow, utilizes advanced technologies such as artificial intelligent recognition, big data analysis, intelligent algorithm and the like, provides a monitoring alarm recognition system for electric power operation site violation based on image recognition, automatically recognizes nonstandard behaviors of site safety and site operation, executes early warning actions, achieves comprehensive and omnibearing real-time early warning and real-time control of site safety, site operation and auxiliary monitoring, and can provide operation prompts. In order to achieve the above purpose, the technical scheme of the invention is as follows:
the system is characterized by comprising an image acquisition module, a safety terminal, a data server and a power remote supervision platform; the image acquisition module is responsible for acquiring operation images and face images of field workers and transmitting an image sequence to the safety terminal module; the security terminal analyzes the operation specification and the security risk of the image sequence, and if the operation specification is not specified and the security risk exists, the security terminal sends out a voice prompt and/or executes an early warning action; the power remote supervision platform takes over the safety terminal through the data server, and remotely refrains or corrects the unnormal behaviors of staff through voice.
Preferably, the image acquisition module adopts at least one camera and is fixedly installed by using a long triangular bracket.
Preferably, the safety terminal stores a database including employee, temporary job identity information, face data information, tool information, environment information and safety operation specifications; the safety terminal is connected with the image acquisition module through a data hard wire and exchanges data with the data server through a 5G network.
Preferably, the operation specification analysis comprises the steps of:
s1, a worker performs information input through a safety terminal module to establish a standing book;
s2, the security module verifies the identity of the staff through the face image information, and when the identity passes the verification, the next step is carried out; otherwise, sending out a voice prompt and prohibiting operation;
and S3, after the worker selects the work type through the safety module, the safety terminal actively acquires the work ticket from the data server, forms a control strategy of the current work operation specification and monitors the work of the worker.
Preferably, the control strategy comprises:
the safety terminal records and stores images of each operation step of the staff according to the collected image data, and synchronously records the time stamp of each step; when the jumping step operation is monitored, the safety module prompts the staff step error through voice and gives step guidance; if the steps are not carried out twice in succession, executing early warning actions: the method comprises the steps of storing and packaging a current image sequence, triggering an early warning signal and sending the early warning signal to a data server.
Preferably, the security risk analysis includes: the safety terminal analyzes and detects the identities of field personnel, the dressing of the staff, the number of the staff, the use of tools and environmental impurities through an image sequence.
Preferably, the system further comprises an auxiliary monitoring function: the power remote supervision platform can send a monitoring request to one or more safety terminal modules through the data server, when the corresponding safety terminal receives the monitoring request, a communication link is established with the remote supervision platform, and a safety supervisor invokes a real-time image of the corresponding safety terminal through the power remote supervision platform to monitor an operation site in real time and send an instruction to a worker through the safety terminal module.
Preferably, the safety terminal is provided with a positioning system, time, personnel information and position information are packaged and transmitted to the data server, and the remote supervision platform visually displays the working range of the personnel through a GPS map.
Preferably, the data server regularly optimizes the identification algorithm and updates the database along with the accumulation of the image data and the change of the power safety standard, the field operation requirement and the tool, and pushes the identification algorithm and the update database to the safety terminal module for the optimization and the upgrading of the software of each terminal module.
Compared with the prior art, the application has the following advantages:
the image acquisition module is flexible to install, monitors the operation site in all directions, is convenient to carry and can provide operation prompts for staff when operation standard analysis is carried out;
the system can be a safety supervisor auxiliary monitoring function, can remotely guide or stop the operation of staff, has a positioning function, and can effectively prevent the behavior of enlarging the working range without permission; in case of emergency, location information can be provided for the rescue workers;
and C, the data server regularly optimizes the identification algorithm and updates the database along with the accumulation of the acquired data, the electric power safety specification, the field operation requirement and the change of tools, so that the safety identification and specification identification of the safety terminal can be more accurate, and the adaptation of the algorithm to the environment is enhanced.
Drawings
FIG. 1 is a schematic diagram of an image-based system for identifying a power operation site violation monitoring alarm identification system;
FIG. 2 is a direct access electrical energy metering device installation step;
Detailed Description
The following detailed description is exemplary and is intended to provide further explanation of the present application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments in accordance with the present application.
It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for analysis, stored data, presented data, etc.) referred to in the present application are information and data authorized by the user or sufficiently authorized by each party, and the collection, use and processing of the related data are required to comply with the related laws and regulations and standards of the related countries and regions.
Example 1
The system for monitoring, alarming and identifying the violations of the electric power operation site based on the image identification is shown in fig. 1, and comprises at least one image acquisition module, at least one safety terminal, a data server and an electric power remote supervision platform; wherein the parts are described in detail as follows:
the image acquisition module adopts at least one camera, adopts long tripod fixed mounting, adopts tripod fixed mounting to avoid the staff to carry the interference to the operation. Meanwhile, if the working range of the target staff is complex, for clearer all-round monitoring, a camera can be added, the height of the long tripod can be adjusted, and the working site can be monitored.
The safety terminal is a mobile terminal, and is convenient to carry and place. A safety terminal is connected with at least one image acquisition module through a data hard line, and can improve the transmission rate of images and the instantaneity through the data hard line. The safety terminal stores a database including employee, temporary identity information, face data information, tool information, environment information and safety operation specifications, and the database package is downloaded through a data server.
The data server exchanges data with the safety terminal through a 5G network and is connected with the electric power remote supervision platform through hardware.
The power remote supervision platform comprises a power amplifier, a display, a keyboard mouse and a microphone. The power remote supervision platform can send a monitoring request to one or more of the safety terminal modules through the data server, when the corresponding safety terminal receives the monitoring request, a video communication link is established with the remote supervision platform, a monitoring person invokes the corresponding safety terminal through the power remote supervision platform to monitor the operation site in real time, and an instruction is sent to the working person through the safety terminal module.
The working principle of the system is as follows: the image acquisition module is responsible for acquiring operation images and face images of field workers and transmitting an image sequence to the safety terminal module; the safety terminal is provided with an identification algorithm downloaded from the data server, the identification algorithm can analyze the safety risk and the operation specification of the image sequence, if the safety risk and the operation specification are not recognized, a voice prompt is sent out and/or an early warning action is executed, the early warning action comprises storing and packaging the current image sequence, triggering an early warning signal and sending the early warning signal to the data server; when the server receives the early warning signal, the electric power remote monitoring platform can receive the voice prompt; in addition, the power remote supervision platform can take over the safety terminal through the data server, and remotely stop or correct the irregular behaviors of the staff through voice. The stored image sequence can be used as a safety supervisor for inspection and used as image data for optimizing training by an identification algorithm.
When a worker enters an operation site, an image acquisition module is placed, a safety terminal is started, and the safety terminal performs operation standard analysis on the site worker, and the method comprises the following steps:
s1, a worker performs information input through a safety terminal module to establish a standing book;
s2, the security module verifies the identity of the staff through the face image information, and when the identity passes the verification, the next step is carried out; otherwise, sending out a voice prompt and prohibiting operation;
and S3, after the worker selects the work type through the safety module, the safety terminal actively acquires the work ticket from the data server, forms a control strategy of the current work operation standard and monitors the field operation of the worker.
In the embodiment, the type of the staff selects the direct access type electric energy metering device to install, and the safety terminal monitors whether the operation of the staff is analyzed according to the safety operation specification of the direct access type electric energy metering device in real time.
The safety terminal shoots and records each step point and synchronously records the time of each step; when the jumping step operation is monitored, the on-site staff is prompted by sound for step errors, and step guidance is given; if the pre-warning operation is not performed according to the steps, the pre-warning operation is performed (because the memory of the data server is larger, more data can be stored, the post-data processing analysis can be performed, the occupied storage space of the safety terminal is reduced, and the calculation force is saved). And when the construction is finished, the site sanitation is collected, and the safety module terminal is closed.
Fig. 2 shows the steps for installing the direct access type electric energy metering device, which specifically include the following steps:
SS1 electroscope: sampling hand information of a worker, extracting whether the hand holds an article of an electroscope model in a tool library, and analyzing whether the article contacts equipment; if the tool is an unqualified electroscope, the on-site staff is prompted by voice to use the qualified electroscope; if the cabinet body is identified to be touched without the electricity checking operation, the on-site staff is prompted by voice to check electricity in time; and (5) detecting no electricity inspection operation, and executing early warning action.
SS2 hanging sign: the method comprises the steps of requiring hanging a signboard, identifying signboard elements in a real-time video according to various signboard models stored by a safety terminal, and extracting signboard font information; in the field work, the fact that the signboard is not hung is not recognized, the field staff is prompted to hang the signboard in time by voice, the fact that the signboard is not hung is detected after 10 minutes after prompting, the field staff is prompted to stop working by voice, and early warning actions are executed.
SS3 installs the electric energy meter: the electric energy meter is installed for reverse operation of removing the electric energy meter, and the monitoring is conventional operation monitoring.
Inspection after SS4 installation is completed: after the safety terminal recognizes that the electric energy meter is installed, monitoring whether a worker has checking operation, wherein the checking operation is various in actual operation, the safety terminal is put into use in the early stage and adopts a conventional action model as a standard sample, and the optimization comparison sample is updated in real time according to the operation condition of the worker in the later use process; when the sampling number exceeds the time or the number of times set (modifiable) by the system, comparing by using the optimized sample as a standard; and recognizing that no inspection operation is performed after the installation is finished, considering that the site construction is unqualified, prompting site workers by voice, and executing early warning actions.
And (5) repeating the step (1) by SS5 to perform electroscope operation.
SS6 seal identification: storing various lead sealing samples in a safety terminal database, and monitoring whether the equipment is sealed; when the equipment door is closed, the fact that no lead seal is added is monitored, and on-site operators are prompted by voice to timely add the lead seal.
SS7 door closing identification: the door opening mode is various in the field construction process, one device can be provided with a plurality of doors, the safety terminal monitors the position of the opened door, records the relative position point, monitors the state of the door at the relative position point, and when the state of the door is changed from open to closed, the door is regarded as the completion of the field construction work; if no lead seal is added in one working period, the working personnel are prompted by voice when the machine is started next time, and early warning actions are executed.
And after the SS8 finishes the task, finally taking a picture and storing.
And in the working process of the staff, safety risk analysis can be performed at the same time.
Example 2
Based on embodiment 1, a monitoring alarm recognition system based on image recognition electric power operation scene violating regulations still includes the security analysis, and the security risk analysis includes: the method comprises the steps of analyzing and detecting the identities of field personnel, the dressing of the staff, the number of the staff, the use of tools and environmental impurities. The safety analysis and detection process comprises the following steps:
the on-site personnel identity, the image acquisition module acquires on-site working videos in real time, face information of personnel in the videos is accurately captured, the safety terminal recognizes identity information of operators by using face recognition technology, non-dispatch personnel are detected to enter a working area, the on-site personnel are prompted by voice, and operation safety of a monitoring operation area is guaranteed.
The worker dressing, the safety terminal accurately grabs the worker dressing and compares the worker dressing with a database dressing sample; the main detection point is whether an operator wears working clothes of a national power grid logo, whether the operator wears the safety helmet correctly according to the standard wearing safety helmet specification, whether the safety helmet is a unified safety helmet printed with the national power grid logo, whether goggles are worn or not is also required to be monitored when the working type (uninterrupted operation) has the goggles requirement, and when the fact that the dressing test elements are inconsistent with the models in the database is monitored, the on-site operator is prompted by voice to standardize dressing, and early warning actions are executed. To a power remote monitoring platform; when the working scene is at low pressure, shoe information is extracted and compared with slippers and sandals in a model library, the field construction of the sandals and the slippers worn by staff is monitored, the staff is prompted by voice, and early warning actions are executed; when the high-voltage working scene is adopted, shoe information is extracted and compared with insulating boots in a model library, the fact that staff does not wear the insulating boots is monitored, voice prompt is sent out, and early warning action is executed.
The personnel number of the workers, the safety terminal detects the configuration condition of the site workers through the YOLO5 target, the maximum number of the workers in the detection condition statistics setting time is determined as the standard, the personnel identity verification is synchronously used to remove the non-workers, the requirement of the site workers is forced to be more than or equal to 2, when the condition that the workers are in one work for a long time is detected, the sound alarm prompts the site workers to pay attention to the unreasonable configuration of the current workers, if the workers are continuous for a plurality of times, the voice prompts the site workers to stop operation, and early warning actions are executed.
When the ascending sample is an ascending ladder, a model of the ascending ladder and the ground angle is built; when the type of the ascending ladder is a single ladder, measuring and calculating the inclination angle of the ladder and the ground, when the inclination angle is larger than 60 degrees, the safety terminal sends out a voice prompt to remind on-site staff of the ascending ladder exceeding the ground angle, timing is started, the ascending ladder with the exceeding of the personnel angle stays for more than 30 seconds, and the voice prompt staff stops working and executes early warning actions; if the type of the ascending ladder is a herringbone ladder, comparing the model with various herringbone ladder models with opening limitation in the library, and if no matched model is found, the model is regarded as the herringbone ladder without the opening limitation, and the voice prompt staff stops working and executes early warning actions.
The method comprises the steps that environmental sundries are placed on the periphery of equipment, a safety terminal monitors the placement of articles on the periphery of the equipment, a non-article placement model on the periphery of the equipment is built, when the placement of the articles on the periphery of the equipment is monitored, on-site staff is prompted by voice to timely clean the sundries when the placement of the sundries on the periphery of the equipment is monitored, and when the cleaning of the sundries is completed, the voice prompt is released; and when the sundries are not cleaned, the equipment is closed, and when the equipment is opened again, a voice prompt is sent out, and an early warning action is executed.
Example 3
Based on embodiment 1, an image-based power operation site violation monitoring alarm recognition system comprises an auxiliary monitoring function:
when the server receives the early warning signal, the electric power remote supervision platform display sends out a voice prompt, the safety supervisor operates the electric power remote supervision platform, a monitoring request is sent to the safety terminal module sending out the early warning signal through the data server, when the corresponding safety terminal receives the monitoring request, a communication link is established with the remote supervision platform, the safety supervisor invokes a real-time image of the corresponding safety terminal through the electric power remote supervision platform, the construction site is monitored in real time, and an instruction is sent to site workers through the safety terminal module. The safety supervisor monitors the scene of the field work in real time through the remote supervision platform display, discovers that the monitoring field staff has illegal operation behaviors, can stop and guide in time, and saves manpower and material resources.
In addition, the safety terminal is provided with a positioning system, and corresponding time, personnel information and position information are packaged and transmitted to the data server. The working area of the operator is positioned and visually displayed through the GPS map, and the working range of the operator can be supervised through positioning, so that the behavior of enlarging the working range without permission can be effectively prevented; the safety supervisor can randomly check the staff according to the work type or the position information, and can effectively control the constructor to arrive at the appointed site for operation. In addition, when an emergency occurs, the system positioning information can provide rescue information for rescue workers.
Preferably, because the electric power safety specification, the field operation requirement and the operator information are not constant, the identification method of the safety terminal needs to be updated, the safety terminal adopts the identification method based on the YOLO5, and a large amount of picture information is required to train a model of the YOLO5 so as to achieve a better identification effect, and the identification method is optimized. Meanwhile, the server collects a large number of operation images uploaded by the security terminal, so that the identification method can be optimized by utilizing the image data, and the method is better suitable for changing the environment. Therefore, the data server can process the accumulated image data at regular intervals, can optimize the identification algorithm and the database by combining the power safety specification, the field operation requirement and the change of tools, and can push the safety terminal system optimization package to each terminal module at regular intervals for the terminal module software to be optimized and upgraded.
The foregoing description is only of the preferred embodiments of the present application and is not intended to limit the same, but rather, various modifications and variations may be made by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.
Claims (7)
1. The system is characterized by comprising an image acquisition module, a safety terminal, a data server and a power remote supervision platform; the image acquisition module is responsible for acquiring operation images and face images of field workers and transmitting an image sequence to the safety terminal module; the security terminal performs operation specification and security risk analysis on the image sequence, wherein the operation specification analysis comprises the following steps:
s1, a worker performs information input through a safety terminal module to establish a standing book;
s2, the security module verifies the identity of the staff through the face image information, and when the identity passes the verification, the next step is carried out; otherwise, sending out a voice prompt and prohibiting operation;
s3, after the worker selects a working type through the safety module, the safety terminal actively acquires a working ticket from the data server and forms a control strategy of the working operation standard, and the safety terminal records and stores images of each operation step of the worker according to the acquired image data and synchronously records time stamps of each step; when the jumping step operation is monitored, the safety module prompts the staff step error through voice and gives step guidance; if the steps are not carried out twice in succession, executing early warning actions: the method comprises the steps of storing and packaging a current image sequence, triggering an early warning signal, sending the early warning signal to a data server, and monitoring the operation of a worker;
if the operation is not standard and the safety risk is recognized, a voice prompt is sent out and/or an early warning action is executed; the power remote supervision platform takes over the safety terminal through the data server, and remotely refrains or corrects the unnormal behaviors of staff through voice.
2. The system for monitoring and alarming and identifying violations on an electric power operation site based on image identification according to claim 1, wherein the image acquisition module adopts at least one camera and is fixedly installed by using a long triangular bracket.
3. The image-based power operation site violation monitoring alarm recognition system according to claim 1, wherein the safety terminal stores a database including employee, temporary identity information, face data information, tool information and environment information, and safety operation specifications; the safety terminal is connected with the image acquisition module through a data hard wire and exchanges data with the data server through a 5G network.
4. The image-based power job site violation monitoring alarm identification system of claim 1, wherein the security risk analysis comprises: the safety terminal analyzes and detects the identities of field personnel, the dressing of the staff, the number of the staff, the use of tools and environmental impurities through an image sequence.
5. The image-based power operation site violation monitoring alarm recognition system according to claim 1, further comprising an auxiliary monitoring function: the power remote supervision platform can send a monitoring request to one or more safety terminal modules through the data server, when the corresponding safety terminal receives the monitoring request, a communication link is established with the remote supervision platform, and a safety supervisor invokes a real-time image of the corresponding safety terminal through the power remote supervision platform to monitor an operation site in real time and send an instruction to a worker through the safety terminal module.
6. The system for monitoring and alarming and identifying the violations of the power operation site based on the image identification according to claim 5, wherein the safety terminal is provided with a positioning system, time, personnel information and position information are packaged and transmitted to the data server, and the remote supervision platform visually displays the operation range of the personnel through a GPS map.
7. The system for monitoring and alarming and identifying the violations of the electric power operation site based on image identification according to any of claims 1-6, wherein the data server periodically optimizes the identification algorithm and updates the database along with the accumulation of image data and the change of electric power safety standards, site operation requirements and tools, and pushes the identification algorithm and the update database to the safety terminal module for the software optimization and upgrading of each terminal module.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311371606.1A CN117115755B (en) | 2023-10-23 | 2023-10-23 | Power operation site violation monitoring alarm recognition system based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311371606.1A CN117115755B (en) | 2023-10-23 | 2023-10-23 | Power operation site violation monitoring alarm recognition system based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117115755A CN117115755A (en) | 2023-11-24 |
| CN117115755B true CN117115755B (en) | 2024-01-23 |
Family
ID=88809509
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311371606.1A Active CN117115755B (en) | 2023-10-23 | 2023-10-23 | Power operation site violation monitoring alarm recognition system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117115755B (en) |
Citations (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003162460A (en) * | 2001-11-22 | 2003-06-06 | Densei Lambda Kk | Operational status monitoring system for uninterruptible power supply units |
| CN110070694A (en) * | 2019-04-23 | 2019-07-30 | 国网上海市电力公司 | A kind of safe auxiliary control system of camera fuzzy diagnosis |
| CN110245630A (en) * | 2019-06-18 | 2019-09-17 | 广东中安金狮科创有限公司 | Monitoring data processing method, device and readable storage medium storing program for executing |
| CN110795989A (en) * | 2019-08-28 | 2020-02-14 | 广东电网有限责任公司 | Intelligent safety monitoring system for electric power operation and monitoring method thereof |
| CN111080147A (en) * | 2019-12-20 | 2020-04-28 | 国网湖北省电力公司咸宁供电公司 | Operating personnel state risk management and control system based on Internet of things technology |
| CN111428617A (en) * | 2020-03-20 | 2020-07-17 | 广东电网有限责任公司 | Video image-based distribution network violation maintenance behavior identification method and system |
| CN111479089A (en) * | 2020-04-15 | 2020-07-31 | 云南电网有限责任公司曲靖供电局 | Power grid construction monitoring method and system based on Beidou positioning |
| CN211827324U (en) * | 2019-11-27 | 2020-10-30 | 广西电网有限责任公司电力科学研究院 | Operation risk remote monitoring system based on image recognition technology |
| CN112153345A (en) * | 2020-09-25 | 2020-12-29 | 内蒙古蒙达发电有限责任公司 | On-site intelligent anti-violation management and control platform based on 5G application operation |
| CN112488483A (en) * | 2020-11-25 | 2021-03-12 | 上上德盛集团股份有限公司 | AI technology-based EHS transparent management system and management method |
| CN212933544U (en) * | 2020-09-29 | 2021-04-09 | 山东科曼智能科技有限公司 | On-site operation safety identification system based on edge calculation |
| CN212936047U (en) * | 2020-07-10 | 2021-04-09 | 重庆市科源能源技术发展有限公司 | Personnel safety management and control system |
| CN112927464A (en) * | 2020-11-23 | 2021-06-08 | 北京宏链科技有限公司 | Job site macro-chain safety management and control system based on edge intelligence |
| CN113158752A (en) * | 2021-02-05 | 2021-07-23 | 国网河南省电力公司鹤壁供电公司 | Intelligent safety management and control system for electric power staff approach operation |
| CN113239750A (en) * | 2021-04-27 | 2021-08-10 | 西安咏圣达电子科技有限公司 | System, method, equipment and application for detecting personnel behaviors in electric power business hall |
| KR102291259B1 (en) * | 2020-02-28 | 2021-08-20 | 주식회사 그릿테크 | Ai system based on edge-computing for reinforcing safe-management in industrial site |
| CN113610011A (en) * | 2021-09-22 | 2021-11-05 | 国网江苏省电力有限公司太仓市供电分公司 | AI identification system for distribution network operation site personnel management and control |
| CN113705372A (en) * | 2021-08-10 | 2021-11-26 | 国网江苏省电力有限公司太仓市供电分公司 | AI identification system for join in marriage net job site violating regulations |
| CN113761989A (en) * | 2020-06-05 | 2021-12-07 | 腾讯科技（深圳）有限公司 | Behavior monitoring method and device, computer and readable storage medium |
| CN114821406A (en) * | 2022-04-12 | 2022-07-29 | 福建亿榕信息技术有限公司 | Method and system for judging electric power operation field violation behaviors |
| CN114971320A (en) * | 2022-05-30 | 2022-08-30 | 国网江苏省电力有限公司超高压分公司 | Transformer substation work auxiliary processing system and self-service processing method |
| CN115632484A (en) * | 2022-11-10 | 2023-01-20 | 福建亿榕信息技术有限公司 | Power grid operation site safety management and control system and method |
| CN115733951A (en) * | 2021-08-27 | 2023-03-03 | 国家电网有限公司 | All-round monitored control system is used at electric power construction scene |
| CN115802002A (en) * | 2022-10-12 | 2023-03-14 | 国网思极位置服务有限公司 | Safety monitoring method for electric power operation |
| CN115860979A (en) * | 2022-11-26 | 2023-03-28 | 国网河北省电力有限公司营销服务中心 | Artificial intelligence management system for field operation of power grid |
| WO2023061239A1 (en) * | 2021-10-14 | 2023-04-20 | 珠海许继芝电网自动化有限公司 | Intelligent power distribution room safety management system |
| CN116016857A (en) * | 2022-12-15 | 2023-04-25 | 中知信(山东)科技服务有限公司 | Abnormal behavior early warning system based on big data |
| CN116193083A (en) * | 2023-03-03 | 2023-05-30 | 武昌理工学院 | Safety identification system based on artificial intelligence |
| CN116310979A (en) * | 2023-03-16 | 2023-06-23 | 国网甘肃省电力公司电力科学研究院 | Image identification method, risk management and control platform and method, and safety management and control platform |
| CN116634098A (en) * | 2023-04-23 | 2023-08-22 | 国能信控互联技术有限公司 | Power production operation ticket operation risk identification system and method based on video monitoring |
| CN116781862A (en) * | 2023-06-20 | 2023-09-19 | 重庆中科摇橹船信息科技有限公司 | Abnormal behavior detection system for automobile production line workers based on video monitoring |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102282433B1 (en) * | 2021-03-03 | 2021-07-26 | 방재웅 | Smart supervision system |
-
2023
- 2023-10-23 CN CN202311371606.1A patent/CN117115755B/en active Active
Patent Citations (31)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003162460A (en) * | 2001-11-22 | 2003-06-06 | Densei Lambda Kk | Operational status monitoring system for uninterruptible power supply units |
| CN110070694A (en) * | 2019-04-23 | 2019-07-30 | 国网上海市电力公司 | A kind of safe auxiliary control system of camera fuzzy diagnosis |
| CN110245630A (en) * | 2019-06-18 | 2019-09-17 | 广东中安金狮科创有限公司 | Monitoring data processing method, device and readable storage medium storing program for executing |
| CN110795989A (en) * | 2019-08-28 | 2020-02-14 | 广东电网有限责任公司 | Intelligent safety monitoring system for electric power operation and monitoring method thereof |
| CN211827324U (en) * | 2019-11-27 | 2020-10-30 | 广西电网有限责任公司电力科学研究院 | Operation risk remote monitoring system based on image recognition technology |
| CN111080147A (en) * | 2019-12-20 | 2020-04-28 | 国网湖北省电力公司咸宁供电公司 | Operating personnel state risk management and control system based on Internet of things technology |
| KR102291259B1 (en) * | 2020-02-28 | 2021-08-20 | 주식회사 그릿테크 | Ai system based on edge-computing for reinforcing safe-management in industrial site |
| CN111428617A (en) * | 2020-03-20 | 2020-07-17 | 广东电网有限责任公司 | Video image-based distribution network violation maintenance behavior identification method and system |
| CN111479089A (en) * | 2020-04-15 | 2020-07-31 | 云南电网有限责任公司曲靖供电局 | Power grid construction monitoring method and system based on Beidou positioning |
| CN113761989A (en) * | 2020-06-05 | 2021-12-07 | 腾讯科技（深圳）有限公司 | Behavior monitoring method and device, computer and readable storage medium |
| CN212936047U (en) * | 2020-07-10 | 2021-04-09 | 重庆市科源能源技术发展有限公司 | Personnel safety management and control system |
| CN112153345A (en) * | 2020-09-25 | 2020-12-29 | 内蒙古蒙达发电有限责任公司 | On-site intelligent anti-violation management and control platform based on 5G application operation |
| CN212933544U (en) * | 2020-09-29 | 2021-04-09 | 山东科曼智能科技有限公司 | On-site operation safety identification system based on edge calculation |
| CN112927464A (en) * | 2020-11-23 | 2021-06-08 | 北京宏链科技有限公司 | Job site macro-chain safety management and control system based on edge intelligence |
| CN112488483A (en) * | 2020-11-25 | 2021-03-12 | 上上德盛集团股份有限公司 | AI technology-based EHS transparent management system and management method |
| CN113158752A (en) * | 2021-02-05 | 2021-07-23 | 国网河南省电力公司鹤壁供电公司 | Intelligent safety management and control system for electric power staff approach operation |
| CN113239750A (en) * | 2021-04-27 | 2021-08-10 | 西安咏圣达电子科技有限公司 | System, method, equipment and application for detecting personnel behaviors in electric power business hall |
| CN113705372A (en) * | 2021-08-10 | 2021-11-26 | 国网江苏省电力有限公司太仓市供电分公司 | AI identification system for join in marriage net job site violating regulations |
| CN115733951A (en) * | 2021-08-27 | 2023-03-03 | 国家电网有限公司 | All-round monitored control system is used at electric power construction scene |
| CN113610011A (en) * | 2021-09-22 | 2021-11-05 | 国网江苏省电力有限公司太仓市供电分公司 | AI identification system for distribution network operation site personnel management and control |
| WO2023061239A1 (en) * | 2021-10-14 | 2023-04-20 | 珠海许继芝电网自动化有限公司 | Intelligent power distribution room safety management system |
| CN114821406A (en) * | 2022-04-12 | 2022-07-29 | 福建亿榕信息技术有限公司 | Method and system for judging electric power operation field violation behaviors |
| CN114971320A (en) * | 2022-05-30 | 2022-08-30 | 国网江苏省电力有限公司超高压分公司 | Transformer substation work auxiliary processing system and self-service processing method |
| CN115802002A (en) * | 2022-10-12 | 2023-03-14 | 国网思极位置服务有限公司 | Safety monitoring method for electric power operation |
| CN115632484A (en) * | 2022-11-10 | 2023-01-20 | 福建亿榕信息技术有限公司 | Power grid operation site safety management and control system and method |
| CN115860979A (en) * | 2022-11-26 | 2023-03-28 | 国网河北省电力有限公司营销服务中心 | Artificial intelligence management system for field operation of power grid |
| CN116016857A (en) * | 2022-12-15 | 2023-04-25 | 中知信(山东)科技服务有限公司 | Abnormal behavior early warning system based on big data |
| CN116193083A (en) * | 2023-03-03 | 2023-05-30 | 武昌理工学院 | Safety identification system based on artificial intelligence |
| CN116310979A (en) * | 2023-03-16 | 2023-06-23 | 国网甘肃省电力公司电力科学研究院 | Image identification method, risk management and control platform and method, and safety management and control platform |
| CN116634098A (en) * | 2023-04-23 | 2023-08-22 | 国能信控互联技术有限公司 | Power production operation ticket operation risk identification system and method based on video monitoring |
| CN116781862A (en) * | 2023-06-20 | 2023-09-19 | 重庆中科摇橹船信息科技有限公司 | Abnormal behavior detection system for automobile production line workers based on video monitoring |
Non-Patent Citations (2)
| Title |
|---|
| 李光东 ; 程进 ; 周子肖 ; 刘宝宇 ; 王骏琦 ; 史立根 ; 姚宇军 ; 常创创 ; 李文月 ; 邹小平 ; .基于深度学习的不规范驾驶行为智能识别系统.传感器世界.2020,(第02期),全文. * |
| 穆波 ; 刘超 ; 王廷春 ; 慕璘 ; 王辉 ; 王云龙 ; 李千登 ; .危化品企业人员作业安全与风险智能管控平台建设研究.安全与环境工程.2020,(第05期),全文. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117115755A (en) | 2023-11-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112183317B (en) | Live working field violation behavior detection method based on space-time diagram convolutional neural network | |
| CN109271938B (en) | Gas station oil discharge process safety monitoring method based on intelligent video analysis technology | |
| US20230012038A1 (en) | Systems and methods for automated detection of switch capacitor operation | |
| CN111080260A (en) | Wisdom building site management platform | |
| CN110795989A (en) | Intelligent safety monitoring system for electric power operation and monitoring method thereof | |
| CN112308510A (en) | Green and environment-friendly building construction management system and method | |
| CN108928700B (en) | Hospital elevator safety three-dimensional monitoring cloud platform, system and method thereof, and elevator system | |
| CN113542690B (en) | Building construction safety monitoring system and method | |
| CN114881808B (en) | Big data-based accurate identification method for electric power larceny and electric power larceny prevention system | |
| CN112004061A (en) | Oil discharge flow normative intelligent monitoring method based on computer vision | |
| CN112800910A (en) | Communication machine room maintenance operation efficiency evaluation method and system | |
| CN112001310A (en) | Transformer substation operation field safety control system based on visual perception and space positioning | |
| CN112004067A (en) | Video monitoring method, device and storage medium | |
| CN107657390A (en) | A kind of special safety equipment hidden danger management and control big data monitoring system and monitoring method | |
| CN112866647A (en) | Intelligent property management system based on smart community | |
| CN114693146A (en) | Natural protection area foreign invasive species risk early warning system and method | |
| CN109867186A (en) | A kind of elevator malfunction detection method and system based on intelligent video analysis technology | |
| CN112990586A (en) | Intelligent video monitoring method and system for distribution network operation | |
| CN112541439A (en) | Intelligent video monitoring method and system for power plant | |
| CN112819374A (en) | System and method for risk management of railway bridge constructors | |
| CN210222962U (en) | Intelligent electronic fence system | |
| CN115248873A (en) | Cable tunnel safety monitoring method and system based on data fusion | |
| CN109345787A (en) | A kind of anti-outer damage monitoring and alarming system of the transmission line of electricity based on intelligent image identification technology | |
| CN115567690A (en) | Intelligent monitoring system capable of automatically identifying dangerous points of field operation | |
| CN115100813A (en) | Intelligent community system based on digital twins |
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 |