CN114744756A - Intelligent power transmission line inspection system based on machine vision - Google Patents
Intelligent power transmission line inspection system based on machine vision Download PDFInfo
- Publication number
- CN114744756A CN114744756A CN202210310526.4A CN202210310526A CN114744756A CN 114744756 A CN114744756 A CN 114744756A CN 202210310526 A CN202210310526 A CN 202210310526A CN 114744756 A CN114744756 A CN 114744756A
- Authority
- CN
- China
- Prior art keywords
- intelligent
- module
- power transmission
- deep learning
- transmission line
- 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.)
- Withdrawn
Links
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02G—INSTALLATION OF ELECTRIC CABLES OR LINES, OR OF COMBINED OPTICAL AND ELECTRIC CABLES OR LINES
- H02G1/00—Methods or apparatus specially adapted for installing, maintaining, repairing or dismantling electric cables or lines
- H02G1/02—Methods or apparatus specially adapted for installing, maintaining, repairing or dismantling electric cables or lines for overhead lines or cables
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
- H02J13/00022—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment using wireless data transmission
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04W—WIRELESS COMMUNICATION NETWORKS
- H04W4/00—Services specially adapted for wireless communication networks; Facilities therefor
- H04W4/30—Services specially adapted for particular environments, situations or purposes
- H04W4/38—Services specially adapted for particular environments, situations or purposes for collecting sensor information
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
-
- 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
- Y04S40/00—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them
- Y04S40/12—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment
- Y04S40/126—Systems for electrical power generation, transmission, distribution or end-user application management characterised by the use of communication or information technologies, or communication or information technology specific aspects supporting them characterised by data transport means between the monitoring, controlling or managing units and monitored, controlled or operated electrical equipment using wireless data transmission
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Signal Processing (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention provides a machine vision-based intelligent power transmission line inspection system which comprises an unmanned aerial vehicle control system, an intelligent inspection terminal and an intelligent control platform, wherein the unmanned aerial vehicle control system and the intelligent inspection terminal are installed on an unmanned aerial vehicle body, and the unmanned aerial vehicle control system and the intelligent inspection terminal are in wireless communication through a communication module; the intelligent inspection terminal is connected with the intelligent management and control platform through a wireless sensing network; the intelligent management and control platform comprises a storage database, an intelligent processing server and a visual terminal, wherein the storage database, the intelligent processing server and the visual terminal are connected with one another through an optical fiber communication network. The intelligent power transmission line inspection system formed by the intelligent inspection terminal, the unmanned aerial vehicle control system and the intelligent control platform can realize ubiquitous Internet of things of power equipment, inspection personnel and inspection data, and effectively improves the integration, informatization and intelligentization levels of intelligent power transmission line inspection.
Description
Technical Field
The invention relates to the technical field of power transmission line inspection, in particular to a power transmission line intelligent inspection system based on machine vision.
Background
The transmission line is an important component of the power system, is responsible for the transmission and distribution tasks of electric energy, and has a self-evident significance on the safety and stability of power supply. With the rapid development of national economy, the total mileage of the power transmission line also rapidly increases year by year, and the types of power equipment on the power transmission line are more, referring to national power grid "overhead power transmission line operation and maintenance management regulations (national grid (operation and maintenance/4) 305-2014"), the overhead power transmission line equipment defect management system is divided into a large category of foundations, towers, ground wires, insulators, hardware fittings, grounding devices, channel environments and accessory facilities 8, and the overhead power transmission line power equipment is specified to contain 878 defects such as insulators, power towers and hardware fittings. Because the span of the power transmission line is long, the power equipment is exposed outdoors for a long time, and the aging, damage and corrosion of the power equipment inevitably occur, thereby leaving great hidden troubles for the safe and stable operation of the power grid. Therefore, in order to ensure continuous and reliable power transmission, power companies regularly patrol transmission lines and distribution networks in different patrol manners.
The traditional manual inspection has the defects of low working efficiency, heavy task, backward detection equipment and the like, and is difficult to effectively ensure the safe and stable operation of the power transmission line; the rolling robot can inspect the power line at a short distance, but the robot cannot penetrate through obstacles such as insulators on the power line, so that manual intervention cannot be avoided in robot inspection, and the power line can be damaged by the sliding of the robot on the power line; the helicopter carries equipment such as a camera, an infrared sensor, an ultraviolet sensor and the like to patrol the power transmission line, so that the patrol efficiency and precision can be effectively improved, but the maintenance cost of the helicopter is higher; compare the helicopter and patrol and examine, unmanned aerial vehicle patrols and examines transmission line and has advantage with low costs, efficient, and the flexibility is big on space and time, operates safer, convenient under the complex environment. However, unmanned aerial vehicle patrols and examines and must produce the massive image of patrolling and examining, if the mode that mainly adopts manual detection to the power equipment detection in a large amount of images of patrolling and examining, not only consume a large amount of manpower resources, moreover because factor influences such as subjective easily cause lou to examine or misjudge.
With the gradual maturity of image processing technology, unmanned aerial vehicle control technology and computer vision technology, with technologies such as big data, thing networking, cloud computing, artificial intelligence as supporting, it is necessary to establish transmission line intelligence system of patrolling and examining, impels transmission line to patrol and examine towards intellectuality and automatic development.
Disclosure of Invention
Technical problem to be solved
Aiming at the problem of low automation level of the conventional power transmission line inspection, the invention provides a power transmission line intelligent inspection system based on machine vision, which effectively improves the integration, informatization and intelligentization levels of the power transmission line intelligent inspection.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
a power transmission line intelligent inspection system based on machine vision comprises an unmanned aerial vehicle control system, an intelligent inspection terminal and an intelligent control platform, wherein the unmanned aerial vehicle control system and the intelligent inspection terminal are installed on an unmanned aerial vehicle body, and the unmanned aerial vehicle control system and the intelligent inspection terminal are in wireless communication through a communication module; the intelligent inspection terminal is connected with the intelligent management and control platform through a wireless sensing network; the intelligent management and control platform comprises a storage database, an intelligent processing server and a visual terminal, wherein the storage database, the intelligent processing server and the visual terminal are connected with one another through an optical fiber communication network.
According to one embodiment of the invention, the unmanned aerial vehicle control system comprises a controller, a motion controller, a GPS positioning module, a storage module, a communication module, a GIS module and a power supply module, wherein the motion controller, the GPS positioning module, the storage module, the communication module, the GIS module and the power supply module are peripheral circuits of the controller and are respectively connected with the controller.
According to an embodiment of the invention, the intelligent inspection terminal comprises an inspection server, an image processing module, a man-machine interaction module, a storage module, a deep learning module, sensor equipment, a control signal receiving module, a line planning module, a communication module, an intelligent identity recognition module and a data signal transmitting and processing module, wherein the image processing module, the man-machine interaction module, the storage module, the deep learning module, the sensor equipment, the control signal receiving module, the line planning module, the communication module, the intelligent identity recognition module and the data signal transmitting and processing module are respectively connected with the inspection server through peripheral circuits of the inspection server.
According to one embodiment of the invention, the sensor equipment comprises tower monitoring equipment, line monitoring equipment and airborne monitoring equipment, wherein the airborne monitoring equipment comprises an optical camera, an infrared camera, an ultraviolet camera and a laser scanner.
According to an embodiment of the invention, the intelligent processing server is used for real-time online monitoring of the power transmission line through a deep learning technology, the inspection server in the intelligent inspection terminal transmits images or videos acquired by the sensor equipment to the storage database of the intelligent management and control platform and the intelligent processing server in real time through the communication system, the intelligent processing server respectively performs image-based static state detection and video-based dynamic state detection on the acquired images and videos of the power transmission line, when an emergency occurs, the intelligent processing server sends an early warning command to the visual terminal and sends specific emergency description information to the intelligent inspection terminal through a state detection result, and simultaneously the intelligent processing server sends a control signal to the intelligent inspection terminal to control the intelligent inspection terminal to perform continuous key detection on suspicious defect positions of the power transmission line.
According to an embodiment of the present invention, the intelligent processing server performs target identification and defect detection on the electrical equipment, and includes the following steps:
s1, sample preparation: selecting large-scale pictures from the pictures and videos transmitted by the inspection server to perform manual identification processing, labeling the names and positions of the power equipment of the power transmission line, taking 80% of the pictures as a training data set, taking the rest 20% of the pictures as a test data set, and establishing deep learning network models of different power equipment and defect detection;
s2, model training: inputting the manual labeling data into a deep learning network model (YOLO) for learning and training, and updating the related model parameters by a random gradient descent technology;
s3, model testing and tuning: testing the deep learning model after training to determine the model precision, and determining whether training data needs to be added continuously or whether model parameters need to be adjusted according to the precision value so as to achieve the set required precision;
s4, target detection: and applying the trained deep learning model to power equipment identification and defect detection.
According to an embodiment of the invention, the intelligent processing server comprises a deep learning server, and the server comprises a Corei77820KCPU, an X299A mainboard, a DDR3240064G memory and an NVIDIAGPU.
According to an embodiment of the invention, the deep learning module in the intelligent inspection terminal comprises a deep learning network model, the deep learning network model is a network model (MobileNet-YOLO) obtained by pruning and compressing the deep learning network model trained by the intelligent processing server, and the deep learning module identifies the target of the electric power equipment from pictures or videos collected by the sensor equipment through a multi-target identification technology and judges whether the electric power equipment has defects and defect types.
According to an embodiment of the present invention, the deep learning module for multi-target defect detection includes the following steps:
1) extracting defect convolution characteristics from different power equipment defect images of the original power transmission line through a convolution neural network;
2) extracting candidate areas of the possibly defective power equipment;
3) and aiming at the extracted candidate regions, dividing the feature maps of all the candidate regions into uniform blocks by sharing convolution layers, extracting convolution features of all the divided blocks, transmitting all the candidate region feature vectors to a classifier to finish classification processing, determining the type of the power equipment, determining the defect type, wherein the regression part comprises the rectangular region coordinates of the power equipment of the power transmission line.
According to an embodiment of the present invention, the deep learning module includes a cellcept 845 processor based on an Android device.
(III) advantageous effects
The invention has the beneficial effects that: the utility model provides a transmission line intelligence system of patrolling and examining based on machine vision, the transmission line intelligence system of patrolling and examining that comprises intelligence inspection terminal, unmanned aerial vehicle control system, intelligent management and control platform can realize power equipment, patrolling and examining personnel, patrol and examine the ubiquitous thing of data and ally oneself with, promote integration, informationization, the intelligent level that transmission line intelligence was patrolled and examined effectively. According to the invention, real power transmission line inspection data are acquired by multiple means, and the intelligent control platform is utilized to perform deep fusion on the mass inspection data of the power transmission line, so that power transmission line inspection data sharing, on-line detection of power equipment and defects, real-time monitoring of an unmanned aerial vehicle and the like are realized, the inspection efficiency of the power transmission line is effectively improved, and powerful data support is provided for inspection operation and maintenance decisions.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic block diagram of an intelligent inspection system of the present invention;
FIG. 2 is a schematic block diagram of an unmanned aerial vehicle control system of the present invention;
FIG. 3 is a schematic block diagram of the intelligent inspection terminal of the present invention;
FIG. 4 is a flow chart of the intelligent processing server performing target detection;
FIG. 5 is a flow chart of the deep learning module for multi-target defect detection;
FIG. 6 is a schematic block diagram of a B/S architecture;
FIG. 7 is a schematic block diagram of a B/S architecture of an intelligent management and control platform.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
With reference to fig. 1, a transmission line intelligence system of patrolling and examining based on machine vision, patrol and examine terminal, intelligent management and control platform including unmanned aerial vehicle control system, intelligence, unmanned aerial vehicle control system, intelligence are patrolled and examined the terminal and are installed on the unmanned aerial vehicle body, unmanned aerial vehicle control system patrols and examines the terminal with intelligence and carry out wireless communication through communication module. The intelligent inspection terminal is connected with the intelligent management and control platform through a wireless sensing network; the intelligent management and control platform comprises a storage database, an intelligent processing server and a visual terminal, wherein the storage database, the intelligent processing server and the visual terminal are connected with each other through an optical fiber communication network. Unmanned aerial vehicle carries on sensor equipment and is used for patrolling and examining the transmission line.
With reference to fig. 2, the unmanned aerial vehicle control system includes controller, motion controller, GPS positioning module, storage module, communication module, GIS module, power module are connected with the controller respectively for the peripheral circuit of controller. The controller is the core of the unmanned aerial vehicle control system and is used for finishing the overall control of the unmanned aerial vehicle; the motion controller is used for finishing the motion control of the unmanned aerial vehicle; the GPS module provides position information for positioning the unmanned aerial vehicle; the storage module is used for storing control information, motion track data and the like; the communication module adopts a wireless sensing module, can be a GPRS or ZigBee routing module, and is used for the wireless communication between the unmanned aerial vehicle and the intelligent inspection terminal as well as the ground remote controller; the GIS module is used for providing a patrol operation area map; the power module is used for supplying electric energy to the unmanned aerial vehicle control system.
Four rotor unmanned aerial vehicle are the main carrier that transmission line patrolled and examined, also are the most important part, and guarantee unmanned aerial vehicle safety, reliable operation are the basis that utilizes intelligence to patrol and examine the terminal and carry out transmission line and patrol and examine on line. The unmanned aerial vehicle control system mainly refers to a control system inside the unmanned aerial vehicle and is used for self-balancing, automatic adjustment of flight angles, fault protection and the like. The navigation system is used as a positioning means for the unmanned aerial vehicle to patrol and examine the power transmission line, and the position of the unmanned aerial vehicle can be accurately positioned by means of the GPS positioning module. Return to its position and the position of the figure of shooing through intelligent management and control platform simultaneously to the personnel of patrolling and examining judge the specific position that unmanned aerial vehicle and power equipment are located. The intelligent inspection terminal and the intelligent management and control platform are main channels for processing data shot by the unmanned aerial vehicle, and the unmanned aerial vehicle uploads other information such as pictures, videos and geographical positions to the inspection server and then transmits the information to the intelligent processing server and the storage database. The intelligent processing server can judge the running state of the power equipment through image recognition or human judgment. The intelligent processing server can send control instructions to the unmanned aerial vehicle control system and the intelligent inspection terminal simultaneously, and operators can check certain power equipment more comprehensively. Geographic Information Systems (GIS) are sometimes also referred to as "Geographic Information systems". It is a specific and very important spatial information system. The system is a technical system for collecting, storing, managing, operating, analyzing, displaying and describing relevant geographic distribution data in the whole or partial earth surface (including the atmosphere) space under the support of a computer hardware and software system.
With reference to fig. 3, the intelligent inspection terminal comprises an inspection server, an image processing module, a human-computer interaction module, a storage module, a deep learning module, a sensor device, a control signal receiving module, a circuit planning module, a communication module, an intelligent identity recognition module and a data signal transmitting and processing module, wherein the image processing module, the human-computer interaction module, the storage module, the deep learning module, the sensor device, the control signal receiving module, the circuit planning module, the communication module, the intelligent identity recognition module and the data signal transmitting and processing module are respectively connected with the inspection server for a peripheral circuit of the inspection server. The inspection server is the core of the intelligent inspection terminal and is used for completing image acquisition and processing, control signal sending and receiving, data storage and transmission, power equipment target identification, defect detection and the like; the image acquired by a sensor of the image processing module is subjected to operations such as shake removal and noise reduction; the man-machine interaction module can be used for real-time picture display of power transmission line routing inspection; the storage module is used for storing the line inspection image and the video data; the deep learning module is used for inspecting images and detecting the images on line in real time; the sensor equipment is used for acquiring image and video data information of the power transmission line and the line corridor; the control signal receiving module is used for receiving control information issued by the intelligent control platform; the route planning module is used for planning the flight route of the unmanned aerial vehicle and sending a control signal to the unmanned aerial vehicle control system; the communication module can be a GPRS or ZigBee routing module, on one hand, the intelligent inspection terminal is in wireless communication with the unmanned aerial vehicle control system, and on the other hand, the intelligent inspection terminal is in communication with the intelligent management and control platform through a 4G or 5G communication network; the intelligent identity recognition module intelligently manages the identity and qualification of the operating personnel, and can adopt biological recognition technologies such as face recognition, voiceprint recognition, fingerprint recognition and the like; and the data signal transmitting and processing module is used for issuing an instruction to the unmanned aerial vehicle control system.
The sensor equipment comprises tower monitoring equipment, line monitoring equipment and airborne monitoring equipment, wherein the airborne monitoring equipment comprises an optical camera, an infrared ray camera, an ultraviolet ray camera and a laser scanner. The sensing layer of the intelligent inspection system for the power transmission line is mainly divided into three categories of pole tower monitoring, line monitoring and airborne monitoring. The tower monitoring mainly comprises monitoring states of tower settlement, inclination, lodging and the like; the line monitoring mainly comprises the monitoring of parameters of an environmental channel of the power transmission line, microclimate, wire temperature, ice coating, sag, galloping and the like. The airborne monitoring equipment such as an optical camera is used for acquiring optical images of towers, power transmission lines and line corridors, diagnosing defects such as insulator burst loss, hardware corrosion, broken strands of lead wires and the like; the infrared rays and the ultraviolet rays are used for detecting the heating conditions and abnormal discharge phenomena of hardware fittings, power lines and insulators; the laser scanner obtains high-precision cloud data of the power line corridor, generates a three-dimensional model of the line corridor, and achieves measurement of the distance between the power line and the obstacle.
The intelligent processing server is used for real-time online monitoring of the power transmission line through a deep learning technology, the inspection server in the intelligent inspection terminal transmits images or videos acquired by sensor equipment to a storage database of the intelligent management and control platform through a communication system in real time, the intelligent processing server detects static states of the acquired images or videos of the power transmission line based on the images and dynamic states of the acquired images or videos of the power transmission line based on the videos respectively, when an emergency occurs, an early warning command is sent to the visual terminal and specific emergency description information is sent through state detection results, meanwhile, the intelligent processing server sends a control signal to the intelligent inspection terminal, and the intelligent inspection terminal is controlled to conduct continuous key detection on suspicious defect positions of the power transmission line. With reference to fig. 4, the intelligent processing server performs target identification and defect detection on the electrical equipment, and includes the following steps:
s1, sample preparation: selecting large-scale pictures from the pictures and videos transmitted by the inspection server to perform manual identification processing, labeling the names and positions of the power equipment of the power transmission line, taking 80% of the pictures as a training data set, taking the rest 20% of the pictures as a test data set, and establishing deep learning network models of different power equipment and defect detection;
s2, model training: inputting manual marking data into a deep learning network model (YOLO) for learning training, and updating related model parameters by a random gradient descent technology;
s3, model testing and tuning: testing the deep learning model after training to determine the model precision, and determining whether training data needs to be added continuously or whether model parameters need to be adjusted according to the precision value so as to achieve the set required precision;
s4, target detection: and applying the trained deep learning model to power equipment identification and defect detection.
The intelligent processing server comprises a deep learning server, wherein the server comprises a Corei77820KCPU, an X299A mainboard, a DDR3240064G memory and an NVIDIAGPU. The visual terminal covers various basic service functions of power transmission inspection, detection, maintenance, project acceptance management, project management, defect and hidden danger management and the like, can replace operation instruction books and field records on site, and is convenient to use.
The intelligent management and control platform mainly depends on a storage database and an intelligent processing server, and visual achievement output and defect closed-loop management are completed by taking a visual terminal as the platform through modes of data access, image or video characteristic extraction, planning, project management, data extraction and statistics, report analysis and the like, so that management personnel are served.
With reference to fig. 6, the network structure of the intelligent management and control platform adopts a B/S (browser/server) mode, which has the advantages of being distributed, convenient for function expansion and convenient for sharing.
With reference to fig. 7, in the network system structure, the visualization terminal can be used by the system through a WWW browser interface, and includes a PC terminal and a mobile APP terminal. A part of simple business logic can be realized in a visualization terminal, and a part of complex main business logic is realized in an intelligent processing server side. The intelligent management and control platform adopts WEB page display, can realize the real-time statistics of each work development condition of power transmission mobile operation, can distribute various work tasks at a server, automatically identifies the image transmitted by the unmanned aerial vehicle, judges the defects of power equipment, and improves the efficiency of power transmission line inspection integrated management.
The deep learning module in the intelligent inspection terminal comprises a deep learning network model, the deep learning network model is a network model (Mobile Net-YOLO) obtained by pruning and compressing the deep learning network model trained by the intelligent processing server, and the deep learning module identifies the target of the electric power equipment from pictures or videos collected by the sensor equipment through a multi-target identification technology and judges whether the electric power equipment has defects and defect types.
With reference to fig. 5, the deep learning module for multi-target defect detection includes the following steps:
1) extracting defect convolution characteristics from different power equipment defect images of the original power transmission line through a convolution neural network;
2) extracting candidate areas of the possibly defective power equipment;
3) and aiming at the extracted candidate regions, dividing the feature maps of all the candidate regions into uniform blocks by sharing convolution layers, extracting convolution features of all the divided blocks, transmitting all the candidate region feature vectors to a classifier to finish classification processing, determining the type of the power equipment, determining the defect type, wherein the regression part comprises the rectangular region coordinates of the power equipment of the power transmission line.
The deep learning module includes a cellcept 845 processor based on an Android device.
In summary, according to the power transmission line intelligent inspection system based on machine vision, the power transmission line intelligent inspection system composed of the intelligent inspection terminal, the unmanned aerial vehicle control system and the intelligent control platform can realize the ubiquitous internet of things of power equipment, inspection personnel and inspection data, and effectively improve the integration, informatization and intelligentization levels of intelligent inspection of the power transmission line. According to the invention, real power transmission line inspection data are acquired by multiple means, and the intelligent control platform is utilized to perform deep fusion on the mass inspection data of the power transmission line, so that power transmission line inspection data sharing, on-line detection of power equipment and defects, real-time monitoring of an unmanned aerial vehicle and the like are realized, the inspection efficiency of the power transmission line is effectively improved, and powerful data support is provided for inspection operation and maintenance decisions.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. The utility model provides a transmission line intelligence system of patrolling and examining based on machine vision which characterized in that: the unmanned aerial vehicle system and the intelligent inspection terminal are installed on an unmanned aerial vehicle body and are in wireless communication through a communication module; the intelligent inspection terminal is connected with the intelligent management and control platform through a wireless sensing network; the intelligent management and control platform comprises a storage database, an intelligent processing server and a visual terminal, wherein the storage database, the intelligent processing server and the visual terminal are connected with each other through an optical fiber communication network.
2. The intelligent power transmission line inspection system based on machine vision according to claim 1, characterized in that: the unmanned aerial vehicle control system comprises a controller, a motion controller, a GPS positioning module, a storage module, a communication module, a GIS module and a power supply module, wherein the motion controller, the GPS positioning module, the storage module, the communication module, the GIS module and the power supply module are respectively connected with the controller for a peripheral circuit of the controller.
3. The intelligent inspection system for power transmission lines based on machine vision according to claim 1, characterized in that: the intelligent inspection terminal comprises an inspection server, an image processing module, a human-computer interaction module, a storage module, a deep learning module, sensor equipment, a control signal receiving module, a line planning module, a communication module, an intelligent identity recognition module and a data signal transmitting and processing module, wherein the image processing module, the human-computer interaction module, the storage module, the deep learning module, the sensor equipment, the control signal receiving module, the line planning module, the communication module, the intelligent identity recognition module and the data signal transmitting and processing module are respectively connected with the inspection server for peripheral circuits of the inspection server.
4. The intelligent inspection system for power transmission lines based on machine vision according to claim 3, characterized in that: the sensor device includes an onboard monitoring device including an optical camera, infrared and ultraviolet cameras, a laser scanner.
5. The intelligent inspection system for power transmission lines based on machine vision according to claim 3, characterized in that: the intelligent processing server is used for real-time online monitoring of the power transmission line through a deep learning technology, the image or video acquired by the sensor equipment is transmitted to a storage database of the intelligent management and control platform through a communication system by the inspection server in the intelligent inspection terminal in real time, the intelligent processing server detects the static state of an observation object based on the image and the dynamic state of the observation object based on the video of the acquired image or video of the power transmission line respectively, when an emergency occurs, a warning command is sent to the visual terminal and specific emergency description information is sent through a state detection result, meanwhile, the intelligent processing server sends a control signal to the intelligent inspection terminal, and the intelligent inspection terminal is controlled to continuously detect key points of suspicious defect positions of the power transmission line.
6. The intelligent inspection system for power transmission lines based on machine vision according to claim 5, characterized in that: the intelligent processing server performs target identification and defect detection on the electric power equipment, and comprises the following steps:
s1, sample preparation: selecting large-scale pictures from the pictures and videos transmitted by the inspection server to perform manual identification processing, labeling the names and positions of the power equipment of the power transmission line, taking 80% of the pictures as a training data set, taking the rest 20% of the pictures as a test data set, and establishing deep learning network models of different power equipment and defect detection;
s2, model training: inputting the manual labeling data into a deep learning network model (YOLO) for learning and training, and updating the related model parameters by a random gradient descent technology;
s3, model testing and tuning: testing the deep learning model after training to determine the model precision, and determining whether training data needs to be added continuously or whether model parameters need to be adjusted according to the precision value so as to achieve the set required precision;
s4, target detection: and applying the trained deep learning model to power equipment identification and defect detection.
7. The intelligent inspection system for power transmission lines based on machine vision according to claim 6, characterized in that: the intelligent processing server comprises a deep learning server, wherein the server comprises a Corei77820K CPU, an X299A mainboard, a DDR3240064G memory and an NVIDIA GPU.
8. The intelligent inspection system for power transmission lines based on machine vision according to claim 6, characterized in that: the deep learning module in the intelligent inspection terminal comprises a deep learning network model, the deep learning network model is a network model (Mobile Net-YOLO) obtained by pruning and compressing the deep learning network model trained by the intelligent processing server, and the deep learning module identifies the target of the electric power equipment from pictures or videos collected by the sensor equipment through a multi-target identification technology and judges whether the electric power equipment has defects and defect types.
9. The intelligent inspection system for power transmission lines based on machine vision according to claim 8, characterized in that: the deep learning module for multi-target defect detection comprises the following steps:
1) extracting defect convolution characteristics from different power equipment defect images of the original power transmission line through a convolution neural network;
2) extracting candidate areas of the possibly defective power equipment;
3) and aiming at the extracted candidate regions, dividing the feature maps of all the candidate regions into uniform blocks by sharing convolution layers, extracting convolution features of all the divided blocks, transmitting all the candidate region feature vectors to a classifier to finish classification processing, determining the type of the power equipment, determining the defect type, wherein the regression part comprises the rectangular region coordinates of the power equipment of the power transmission line.
10. The intelligent inspection system for power transmission lines based on machine vision according to claim 9, characterized in that: the deep learning module includes a cellcept 845 processor based on an Android device.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210310526.4A CN114744756A (en) | 2022-03-28 | 2022-03-28 | Intelligent power transmission line inspection system based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210310526.4A CN114744756A (en) | 2022-03-28 | 2022-03-28 | Intelligent power transmission line inspection system based on machine vision |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114744756A true CN114744756A (en) | 2022-07-12 |
Family
ID=82276240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210310526.4A Withdrawn CN114744756A (en) | 2022-03-28 | 2022-03-28 | Intelligent power transmission line inspection system based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114744756A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115589070A (en) * | 2022-11-11 | 2023-01-10 | 贵州电网有限责任公司 | Power grid risk early warning method and system based on cloud computing processing |
-
2022
- 2022-03-28 CN CN202210310526.4A patent/CN114744756A/en not_active Withdrawn
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115589070A (en) * | 2022-11-11 | 2023-01-10 | 贵州电网有限责任公司 | Power grid risk early warning method and system based on cloud computing processing |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111311597B (en) | Unmanned aerial vehicle inspection method and system for defective insulator | |
| CN106771856B (en) | Electric power transmission line lightning stroke point determination method based on unmanned aerial vehicle technology | |
| CN110865917A (en) | AR technology-based electric power machine room inspection operation method, system and application | |
| CN108957240A (en) | Electric network fault is remotely located method and system | |
| CN113781450A (en) | Automatic intelligent defect analysis system based on unmanned aerial vehicle image acquisition of power transmission and distribution line | |
| CN111555178B (en) | Sky-ground cooperative intelligent inspection method and system for power transmission line | |
| CN106710001A (en) | Substation inspection robot based centralized monitoring and simulation system and method thereof | |
| CN105574683A (en) | Omni-directional transformer station inspection system and method | |
| CN112327906A (en) | Intelligent automatic inspection system based on unmanned aerial vehicle | |
| CN112506205B (en) | Robot inspection task planning method and device | |
| CN112698618A (en) | Server alarm recognition system based on machine vision technology | |
| CN115373403B (en) | Inspection service system for construction machinery equipment | |
| CN211979511U (en) | Unmanned aerial vehicle inspection system capable of automatically identifying defective insulator strings | |
| CN112764427A (en) | Relay unmanned aerial vehicle inspection system | |
| CN116258980A (en) | Unmanned aerial vehicle distributed photovoltaic power station inspection method based on vision | |
| CN113077561A (en) | Intelligent inspection system for unmanned aerial vehicle | |
| CN113988573A (en) | Risk judgment method, system and medium for routing inspection unmanned aerial vehicle based on power system | |
| CN112446543A (en) | Urban underground comprehensive pipe gallery risk management and control system and method based on neural network | |
| CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
| CN114744756A (en) | Intelligent power transmission line inspection system based on machine vision | |
| CN117353460A (en) | Power line inspection method, device, equipment and medium | |
| CN113111714A (en) | Risk prevention and control system applied to power transmission field operation | |
| CN112269397A (en) | Unmanned aerial vehicle inspection method based on high-precision positioning and visual tracking | |
| CN114937040B (en) | Train inspection method, device and system for rail transit vehicle section and storage medium | |
| CN116866512A (en) | Photovoltaic power station inspection system and operation method thereof |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220712 |