CN111724130A - Distribution network machine patrol operation management system and management method - Google Patents
Distribution network machine patrol operation management system and management method Download PDFInfo
- Publication number
- CN111724130A CN111724130A CN202010552772.1A CN202010552772A CN111724130A CN 111724130 A CN111724130 A CN 111724130A CN 202010552772 A CN202010552772 A CN 202010552772A CN 111724130 A CN111724130 A CN 111724130A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- picture
- tower
- patrol
- 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.)
- Pending
Links
- 238000009826 distribution Methods 0.000 title claims abstract description 30
- 238000007726 management method Methods 0.000 title claims description 64
- 230000007547 defect Effects 0.000 claims abstract description 34
- 238000004519 manufacturing process Methods 0.000 claims abstract description 26
- 238000000034 method Methods 0.000 claims abstract description 25
- 238000007689 inspection Methods 0.000 claims abstract description 12
- 230000006870 function Effects 0.000 claims description 14
- 238000010586 diagram Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 3
- 230000005764 inhibitory process Effects 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 claims description 3
- 238000011176 pooling Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000013475 authorization Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
Abstract
The invention relates to the technical field of power distribution networks, in particular to a distribution network machine patrol operation management system, which comprises a production system and an unmanned aerial vehicle patrol operation management system, wherein the production system is connected with the unmanned aerial vehicle patrol operation management system; unmanned aerial vehicle patrols operation management system includes that unmanned aerial vehicle patrols and removes end, the automatic instrument of categorizing of picture, the intelligent discernment instrument of image defect and machine and patrols the integrated management module. The network distribution machine inspection operation management system solves the problems of single operation and control function, low automation degree and low operation efficiency of the existing unmanned aerial vehicle remote control inspection method, and the unmanned aerial vehicle inspection operation management system is built to communicate the operation management system with the production system service to form a closed-loop integral service system, so that the inspection automation degree is improved, and the inspection work efficiency is improved.
Description
Technical Field
The invention relates to the technical field of power distribution networks, in particular to a system and a method for managing patrol operation of a distribution network machine.
Background
At present, after a production system dispatches a machine to patrol an operation task order, an operator arrives around a line tower appointed by the task according to the work order condition and takes a picture through manually controlling an unmanned aerial vehicle, for example, a power distribution network patrol unmanned aerial vehicle described in patent with the authorization publication number of CN210199580U, after the machine patrol task is completed, the taken picture is stored in a memory card of the unmanned aerial vehicle, the operator exports the picture from the memory card of the unmanned aerial vehicle through a PC, manually classifies the tower to which the picture belongs according to the taking time and field recording information, then judges the defect of the worker, and finally, manually uploads the defect record and the image to the production system to produce defect record information.
The existing unmanned aerial vehicle patrol management subsystems are not communicated with the services of a production system, and the production system builds a machine patrol work order and cannot check operation at an unmanned aerial vehicle patrol mobile application end; the data after the unmanned aerial vehicle operation is finished cannot be automatically transmitted back to the background; pictures stored in the patrol photographing cannot be automatically classified and intelligently identified; and defect records and pictures cannot be automatically returned to the production system.
The original unmanned aerial vehicle remote control inspection method has many problems, the control function is single, the in-place automatic association of the towers cannot be realized, the operation efficiency is low, the diversified customized function requirements in actual use cannot be met, and the capacity of improving the intelligent operation of electric power is not facilitated.
Disclosure of Invention
In order to solve the problems of single control function, low automation degree and low operation efficiency of the existing unmanned aerial vehicle remote control inspection method, the invention provides an operation inspection management system and a management method of a network distribution machine.
In order to solve the technical problems, the invention provides the following technical scheme:
a distribution network machine patrols the operation management system, including production system and unmanned aerial vehicle patrols the operation management system, the said production system patrols the operation management system to connect with said unmanned aerial vehicle; the unmanned aerial vehicle patrolling management system comprises an unmanned aerial vehicle patrolling moving end, an automatic picture classifying tool, an intelligent image defect identifying tool and a machine patrolling comprehensive management module; the unmanned aerial vehicle tours and removes the end with the automatic instrument of categorizing of picture is connected, the automatic instrument of categorizing of picture with the intelligent discernment instrument of image defect is connected, the intelligent discernment instrument of image defect with the machine is patrolled and is synthesized the management module and be connected, production system respectively with unmanned aerial vehicle tours and removes the end and the machine is patrolled and is synthesized the management module and be connected.
A distribution network machine patrols the homework management method of homework management system based on above-mentioned distribution network machine, including the following steps:
s1: the production system dispatches a work order;
s2: after receiving the work order, the unmanned aerial vehicle patrols the mobile terminal to execute a patrolling task, and takes and stores tower pictures;
s3: the automatic picture classifying tool classifies and stores the shot tower pictures;
s4: the image defect intelligent recognition tool carries out image defect recognition on the classified tower pictures and outputs results;
s5: and the machine patrol comprehensive management module transmits the information of the tower picture back to the production system.
Further, in step S2, the specific steps of the unmanned aerial vehicle patrol mobile terminal executing the patrol task are as follows:
s201: controlling the unmanned aerial vehicle to fly to an operation site through an unmanned aerial vehicle remote controller by utilizing a GPS and a network RTK positioning technology and acquiring an actual tower coordinate;
s202: comparing the coordinate information acquired on site with the tower coordinates of the database ledger, and automatically selecting the tower at the coordinates within the range of 5m to realize the functions of in-place reminding and automatically selecting the tower;
s203: after the unmanned aerial vehicle patrols and takes a picture, automatically associating the tower picture with the corresponding tower;
s204: after the line and the tower of the inspection task are photographed, the photographed picture information is uploaded to a background through task submission of an application end, automatic association storage of the task, the line, the tower and the picture name information is achieved, the information is used in subsequent links, photographing is safer and more reliable, and information is more accurate.
Further, in step S202, the process of implementing the automatic selection function of the tower is as follows: unmanned aerial vehicle tours and removes the platform account information of end with the circuit before the operation, download the reserve including the shaft tower coordinate, unmanned aerial vehicle carries on GPS positioner, acquire the geographical position information of self, unmanned aerial vehicle tours and removes the end and connect the unmanned aerial vehicle remote controller, obtain unmanned aerial vehicle's coordinate through remote controller wireless link, unmanned aerial vehicle tours and removes the end and contrasts the shaft tower coordinate in unmanned aerial vehicle current position coordinate and the database, the difference is less than 5 meters between two coordinates and considers the operating range that unmanned aerial vehicle has arrived this shaft tower promptly, the system then automatic selection this shaft tower, degree of automation is higher.
Further, in step S203, the process of implementing automatic association is as follows: the unmanned aerial vehicle tours and moves the end and has obtained the unmanned aerial vehicle and carried out the operation in the within range of which shaft tower, and the picture of taking at this shaft tower within range operation in-process, the system then marks this picture as belonging to this shaft tower to this realizes the automatic association of picture and shaft tower, and degree of automation is higher.
Further, in step S3, the specific steps are:
s301: importing an original picture shot by the unmanned aerial vehicle in an automatic picture classifying tool, classifying the picture according to the picture information recorded by the background by the automatic picture classifying tool, and automatically naming and sequencing the picture according to a set naming standard;
s302: the automatically classified pictures are uploaded to a background picture storage server for use in subsequent links, the shot pictures are patrolled through an automatic picture classification tool, the functions of automatic classification and uploading processing after leading in are realized, the tedious and time-consuming work that a machine patrol worker manually classifies the pictures to the affiliated line towers is avoided, the labor intensity of patrolling teams and teams is reduced, and meanwhile, the accuracy of picture classification and the automation of uploading are ensured.
Further, in step S4, the image defect identification specifically includes:
s401: the image defect intelligent recognition tool acquires a picture, performs scaling pretreatment and normalizes the picture into a picture with fixed pixels;
s402: extracting a characteristic diagram of the image through a convolution layer;
s403: the feature map is shared for an RPN network and a full connection layer, then an RPN network is used for generating a region suggestion, and a softmax classifier is used for judging whether a candidate region belongs to a foreground or a background;
s404: collecting the input feature map and the region suggestions by the pooling layer, extracting the feature map from the region suggestions after integrating the information, and sending the feature map into the full-connection layer to judge the target category;
s405: the image defect intelligent recognition tool realizes the intelligent recognition of the image defects of conventional types by using the regression of the bounding box and the non-maximum value inhibition to obtain the accurate position of the detection box and finally outputting a result, the image defect intelligent recognition tool does not need manual intervention in the process of intelligent recognition through a convolutional neural network and a deep learning intelligent recognition algorithm, the image defects can be recognized finally after the intelligent recognition is finished, the working time is saved, the labor intensity is reduced, and the accuracy of the image recognition is improved.
Further, to the unsafe shaft tower of coordinate, through the function of editing of rectifying, realize the on-the-spot collection of shaft tower coordinate and update the platform account, according to the shaft tower type of difference, pop out the operation guide picture automatically, guide the operation personnel to carry out unmanned aerial vehicle and shoot, degree of automation is high.
Furthermore, the machine patrols the integrated management module and carries out two-dimensional code generation mark management to unmanned aerial vehicle and battery, and the personnel of patrolling and examining realize the warehouse entry and exit management of unmanned aerial vehicle and battery equipment through the two-dimensional code scanning, and it is more convenient to manage.
Furthermore, the machine patrol operation command center of the unmanned aerial vehicle patrol operation management system transmits the real-time flight environment condition of the field operation back through a live broadcast push flow technology, and machine patrol management personnel carry out remote real-time monitoring, so that the situation of the field operation can be controlled more clearly, and the remote command and scheduling of the field operation are realized.
Compared with the prior art, the invention has the following beneficial effects:
by constructing an unmanned aerial vehicle inspection operation management system and communicating the operation management system with the production system service, a closed-loop integral service system is formed, so that the machine patrol work order built by the production system can be automatically and synchronously transmitted to the unmanned aerial vehicle patrol moving end of the unmanned aerial vehicle patrol operation management system, the patrol personnel can check the task to be executed by the patrol terminal of the unmanned aerial vehicle and control the unmanned aerial vehicle to finish the patrol task, after the patrol operation of the unmanned aerial vehicle is finished, the unmanned aerial vehicle patrols the mobile terminal to submit the operation task, the picture data information shot in the patrolling process can be automatically transmitted back to the background of the unmanned aerial vehicle patrolling management system, meanwhile, the task state information is transmitted back to the production system, and the service system chain is communicated, so that the working efficiency of the personnel in the team patrolling machine is improved, the informatization level of the operation of the team patrolling machine is improved, and the promotion of lean management of the distribution network is promoted.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only 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 structural diagram of a distribution network machine patrol operation management system according to the present invention;
fig. 2 is a schematic diagram illustrating data processing and analysis in step S2 of a method for managing operation of a distribution network machine according to the present invention;
fig. 3 is a schematic diagram illustrating data processing and analysis in step S3 of the method for managing operation patrol of a distribution network machine according to the present invention;
fig. 4 is a schematic diagram of data processing and analysis in step S4 of the method for managing operation of distribution network equipment.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all embodiments. 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.
The embodiment of the invention comprises the following steps:
as shown in fig. 1, a distribution network machine patrol operation management system includes a production system and an unmanned aerial vehicle patrol operation management system, wherein the production system is connected with the unmanned aerial vehicle patrol operation management system; the unmanned aerial vehicle patrolling management system comprises an unmanned aerial vehicle patrolling moving end, an automatic picture classifying tool, an intelligent image defect identifying tool and a machine patrolling comprehensive management module; unmanned aerial vehicle tours and removes the end and is connected with the automatic instrument of categorizing of picture, and the automatic instrument of categorizing of picture is connected with the intelligent discernment instrument of image defect, and the intelligent discernment instrument of image defect is connected with the quick-witted comprehensive management module of patrolling, and production system patrols respectively with unmanned aerial vehicle and removes the end and the quick-witted comprehensive management module of patrolling is connected.
A distribution network machine patrols the homework management method of homework management system based on above-mentioned distribution network machine, including the following steps:
s1: the production system dispatches a work order;
s2: after receiving the work order, the unmanned aerial vehicle patrols the mobile terminal to execute a patrolling task, and takes and stores tower pictures;
s3: the automatic picture classifying tool classifies and stores the shot tower pictures;
s4: the image defect intelligent recognition tool carries out image defect recognition on the classified tower pictures and outputs results;
s5: and the machine patrol comprehensive management module transmits the information of the tower picture back to the production system.
In this embodiment, in step S2, the specific steps of the unmanned aerial vehicle patrol mobile terminal executing the patrol task are as follows:
s201: controlling the unmanned aerial vehicle to fly to an operation site through an unmanned aerial vehicle remote controller by utilizing a GPS and a network RTK positioning technology and acquiring an actual tower coordinate;
s202: comparing the coordinate information acquired on site with the tower coordinates of the database ledger, and automatically selecting the tower at the coordinates within the range of 5m to realize the functions of in-place reminding and automatically selecting the tower;
s203: after the unmanned aerial vehicle patrols and takes a picture, automatically associating the tower picture with the corresponding tower;
s204: after the line and the tower of the inspection task are photographed, the photographed picture information is uploaded to a background through task submission of an application end, automatic association storage of the task, the line, the tower and the picture name information is achieved, the information is used in subsequent links, photographing is safer and more reliable, and information is more accurate.
In this embodiment, in step S202, the process of implementing the automatic selection function of the tower is as follows: unmanned aerial vehicle tours and removes the end and download the standing book information of circuit before the operation for subsequent use including the shaft tower coordinate, unmanned aerial vehicle carries on GPS positioner, acquire the geographical position information of self, unmanned aerial vehicle tours and removes the end and connect the unmanned aerial vehicle remote controller, obtain unmanned aerial vehicle's coordinate through remote controller wireless link, unmanned aerial vehicle tours and removes the end and contrasts unmanned aerial vehicle current position coordinate and the shaft tower coordinate in the database, the operating range that this shaft tower has been arrived to the unmanned aerial vehicle promptly is thought to the difference between two coordinates to be less than 5 meters, the system then automatic selection this shaft tower, degree of automation is higher, concrete processing analytic process to data, coding and decoding process and control process are as shown in figure 2.
In this embodiment, in step S203, the process of implementing automatic association is: the unmanned aerial vehicle tours and moves the end and has obtained the unmanned aerial vehicle and carried out the operation in the within range of which shaft tower, and the picture of taking at this shaft tower within range operation in-process, the system then marks this picture as belonging to this shaft tower to this realizes the automatic association of picture and shaft tower, and degree of automation is higher.
In this embodiment, in step S3, the specific steps are:
s301: importing an original picture shot by the unmanned aerial vehicle in an automatic picture classifying tool, classifying the picture according to the picture information recorded by the background by the automatic picture classifying tool, and automatically naming and sequencing the picture according to a set naming standard;
s302: the automatically classified pictures are uploaded to a background picture storage server for use in subsequent links, the shot pictures are patrolled through an automatic picture classification tool, the functions of automatic classification and uploading processing after leading in are realized, the tedious and time-consuming work that a machine patrol worker manually classifies the pictures to the affiliated line towers is avoided, the labor intensity of a patrol team is reduced, the accuracy of picture classification and the automation of uploading are ensured, and the specific processing analysis process, the coding and decoding process and the control process of data are shown in figure 3.
As shown in fig. 4, in step S4, the image defect identification specifically includes:
s401: the image defect intelligent recognition tool acquires a picture, performs scaling pretreatment and normalizes the picture into a picture with fixed pixels;
s402: extracting a characteristic diagram of the image through a convolution layer;
s403: the feature map is shared for an RPN network and a full connection layer, then an RPN network is used for generating a region suggestion, and a softmax classifier is used for judging whether a candidate region belongs to a foreground or a background;
s404: collecting the input feature map and the region suggestions by the pooling layer, extracting the feature map from the region suggestions after integrating the information, and sending the feature map into the full-connection layer to judge the target category;
s405: the image defect intelligent recognition tool realizes the intelligent recognition of the image defects of conventional types by using the regression of the bounding box and the non-maximum value inhibition to obtain the accurate position of the detection box and finally outputting a result, the image defect intelligent recognition tool does not need manual intervention in the process of intelligent recognition through a convolutional neural network and a deep learning intelligent recognition algorithm, the image defects can be recognized finally after the intelligent recognition is finished, the working time is saved, the labor intensity is reduced, and the accuracy of the image recognition is improved.
In this embodiment, to the unsafe shaft tower of coordinate, through the function of editing of rectifying, realize the on-the-spot collection of shaft tower coordinate and update to the platform account, according to the shaft tower type of difference, pop out the operation guide picture automatically, guide the operation personnel to carry out unmanned aerial vehicle and shoot, degree of automation is high.
In this embodiment, the machine patrols the integrated management module and carries out two-dimensional code generation mark management to unmanned aerial vehicle and battery, and the personnel of patrolling and examining realize the warehouse entry and exit management of unmanned aerial vehicle and battery equipment through the two-dimensional code scanning, and it is more convenient to manage.
In this embodiment, the machine patrol operation command center of the unmanned aerial vehicle patrol operation management system transmits the real-time flight environment condition of the field operation back through a live broadcast push flow technology, and machine patrol management personnel perform remote real-time monitoring, so that the situation of the field operation can be controlled more clearly, and the remote command and scheduling of the field operation are realized.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by the present specification, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A distribution network machine patrols the operation management system, characterized by, including production system and unmanned aerial vehicle patrols the operation management system, the said production system patrols the operation management system to connect with said unmanned aerial vehicle; the unmanned aerial vehicle patrolling management system comprises an unmanned aerial vehicle patrolling moving end, an automatic picture classifying tool, an intelligent image defect identifying tool and a machine patrolling comprehensive management module; the unmanned aerial vehicle tours and removes the end with the automatic instrument of categorizing of picture is connected, the automatic instrument of categorizing of picture with the intelligent discernment instrument of image defect is connected, the intelligent discernment instrument of image defect with the machine is patrolled and is synthesized the management module and be connected, production system respectively with unmanned aerial vehicle tours and removes the end and the machine is patrolled and is synthesized the management module and be connected.
2. The distribution network machine patrol operation management method based on the distribution network machine patrol operation management system of claim 1, characterized by comprising the following steps:
s1: the production system dispatches a work order;
s2: after receiving the work order, the unmanned aerial vehicle patrols the mobile terminal to execute a patrolling task, and takes and stores tower pictures;
s3: the automatic picture classifying tool classifies and stores the shot tower pictures;
s4: the image defect intelligent recognition tool carries out image defect recognition on the classified tower pictures and outputs results;
s5: and the machine patrol comprehensive management module transmits the information of the tower picture back to the production system.
3. The method for managing routing operations of network distribution machines according to claim 2, wherein in step S2, the specific steps of the unmanned aerial vehicle routing mobile terminal executing the routing task are as follows:
s201: controlling the unmanned aerial vehicle to fly to an operation site through an unmanned aerial vehicle remote controller by utilizing a GPS and a network RTK positioning technology and acquiring an actual tower coordinate;
s202: comparing the coordinate information acquired on site with the tower coordinates of the database ledger, and automatically selecting the tower at the coordinates within the range of 5m to realize the functions of in-place reminding and automatically selecting the tower;
s203: after the unmanned aerial vehicle patrols and takes a picture, automatically associating the tower picture with the corresponding tower;
s204: after the line and the tower of the inspection task are photographed, the photographed picture information is uploaded to a background through task submission of an application end, and automatic associated storage of the task, the line, the tower and the picture name information is achieved so as to be used in subsequent links.
4. The patrol operation management method for the network distribution machine according to claim 3, wherein in step S202, the automatic selection function of the tower is implemented by the following steps: unmanned aerial vehicle tours and removes the end and download the standing book information of circuit before the operation for subsequent use including the shaft tower coordinate, unmanned aerial vehicle carries on GPS positioner, acquire the geographical position information of self, unmanned aerial vehicle tours and removes the end and connect the unmanned aerial vehicle remote controller, obtain unmanned aerial vehicle's coordinate through remote controller wireless link, unmanned aerial vehicle tours and removes the end and contrasts unmanned aerial vehicle current position coordinate and the shaft tower coordinate in the database, the difference is less than 5 meters between two coordinates and considers the operating range that unmanned aerial vehicle has arrived this shaft tower promptly, the system then automatic selection this shaft tower.
5. The patrol management method for the network distribution machine according to claim 4, wherein in step S203, the automatic association is implemented by: the unmanned aerial vehicle patrols the moving end in the last step and has obtained the range of which shaft tower the unmanned aerial vehicle carries out the operation, and the picture of shooting in this shaft tower within range operation process is then marked as belonging to this shaft tower by the system to this realizes the automatic association of picture and shaft tower.
6. The patrol management method for the network distribution machine according to claim 5, wherein in step S3, the specific steps are as follows:
s301: importing an original picture shot by the unmanned aerial vehicle in an automatic picture classifying tool, classifying the picture according to the picture information recorded by the background by the automatic picture classifying tool, and automatically naming and sequencing the picture according to a set naming standard;
s302: and uploading the automatically classified pictures to a background picture storage server for use in subsequent links.
7. The patrol operation management method of the network distributor according to claim 6, wherein in step S4, the specific steps of image defect identification are as follows:
s401: the image defect intelligent recognition tool acquires a picture, performs scaling pretreatment and normalizes the picture into a picture with fixed pixels;
s402: extracting a characteristic diagram of the image through a convolution layer;
s403: the feature map is shared for an RPN network and a full connection layer, then an RPN network is used for generating a region suggestion, and a softmax classifier is used for judging whether a candidate region belongs to a foreground or a background;
s404: collecting the input feature map and the region suggestions by the pooling layer, extracting the feature map from the region suggestions after integrating the information, and sending the feature map into the full-connection layer to judge the target category;
s405: and calculating the type of the region suggestion by using the region suggestion feature map, simultaneously obtaining the accurate position of the detection frame by using the boundary frame regression and the non-maximum value inhibition again, and finally outputting the result.
8. The patrol operation management method for the network distribution machine according to claim 4, wherein for towers with inaccurate coordinates, the coordinates of the towers are collected on site and updated to a standing book through a rectification function, and an operation guide map is automatically popped up according to different types of the towers to guide operators to take pictures of the unmanned aerial vehicle.
9. The network distribution machine patrol operation management method according to any one of claims 2 to 8, wherein the machine patrol comprehensive management module performs two-dimensional code generation mark management on the unmanned aerial vehicle and the battery, and patrol personnel realize management of the unmanned aerial vehicle and the battery equipment in and out through two-dimensional code scanning.
10. The distribution network machine patrol operation management method according to claim 9, wherein a machine patrol operation command center of the unmanned aerial vehicle patrol operation management system returns the real-time flight environment status of the field operation through a video by a live broadcast stream pushing technology, and a machine patrol manager performs remote real-time monitoring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010552772.1A CN111724130A (en) | 2020-06-17 | 2020-06-17 | Distribution network machine patrol operation management system and management method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010552772.1A CN111724130A (en) | 2020-06-17 | 2020-06-17 | Distribution network machine patrol operation management system and management method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111724130A true CN111724130A (en) | 2020-09-29 |
Family
ID=72567214
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010552772.1A Pending CN111724130A (en) | 2020-06-17 | 2020-06-17 | Distribution network machine patrol operation management system and management method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111724130A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113010719A (en) * | 2021-03-31 | 2021-06-22 | 国网江苏省电力有限公司徐州供电分公司 | Photo identification and storage method and system |
| CN114237224A (en) * | 2021-11-19 | 2022-03-25 | 深圳市鑫疆基业科技有限责任公司 | Automatic inspection method, system, terminal device and computer readable storage medium |
| CN115219852A (en) * | 2022-09-19 | 2022-10-21 | 国网江西省电力有限公司电力科学研究院 | Intelligent fault studying and judging method for distribution line of unmanned aerial vehicle |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886189A (en) * | 2014-03-07 | 2014-06-25 | 国家电网公司 | Patrolling result data processing system and method used for unmanned aerial vehicle patrolling |
| CN106504233A (en) * | 2016-10-18 | 2017-03-15 | 国网山东省电力公司电力科学研究院 | Image electric power widget recognition methodss and system are patrolled and examined based on the unmanned plane of Faster R CNN |
| JP2019009919A (en) * | 2017-06-26 | 2019-01-17 | 株式会社東芝 | Patrol inspection support system and patrol inspection support control program |
| CN110531780A (en) * | 2019-08-16 | 2019-12-03 | 国电南瑞科技股份有限公司 | Unmanned plane full-automation cruising inspection system and method based on automatic airport |
| CN209728522U (en) * | 2018-11-27 | 2019-12-03 | 深圳供电局有限公司 | A kind of unmanned machine management system of shaft tower tour |
-
2020
- 2020-06-17 CN CN202010552772.1A patent/CN111724130A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886189A (en) * | 2014-03-07 | 2014-06-25 | 国家电网公司 | Patrolling result data processing system and method used for unmanned aerial vehicle patrolling |
| CN106504233A (en) * | 2016-10-18 | 2017-03-15 | 国网山东省电力公司电力科学研究院 | Image electric power widget recognition methodss and system are patrolled and examined based on the unmanned plane of Faster R CNN |
| JP2019009919A (en) * | 2017-06-26 | 2019-01-17 | 株式会社東芝 | Patrol inspection support system and patrol inspection support control program |
| CN209728522U (en) * | 2018-11-27 | 2019-12-03 | 深圳供电局有限公司 | A kind of unmanned machine management system of shaft tower tour |
| CN110531780A (en) * | 2019-08-16 | 2019-12-03 | 国电南瑞科技股份有限公司 | Unmanned plane full-automation cruising inspection system and method based on automatic airport |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113010719A (en) * | 2021-03-31 | 2021-06-22 | 国网江苏省电力有限公司徐州供电分公司 | Photo identification and storage method and system |
| CN114237224A (en) * | 2021-11-19 | 2022-03-25 | 深圳市鑫疆基业科技有限责任公司 | Automatic inspection method, system, terminal device and computer readable storage medium |
| CN115219852A (en) * | 2022-09-19 | 2022-10-21 | 国网江西省电力有限公司电力科学研究院 | Intelligent fault studying and judging method for distribution line of unmanned aerial vehicle |
| CN115219852B (en) * | 2022-09-19 | 2023-03-24 | 国网江西省电力有限公司电力科学研究院 | Intelligent fault studying and judging method for distribution line of unmanned aerial vehicle |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111724130A (en) | Distribution network machine patrol operation management system and management method | |
| US9846915B2 (en) | Image capture system for property damage assessment | |
| US10511676B2 (en) | Image analysis system for property damage assessment and verification | |
| CN108109437B (en) | Unmanned aerial vehicle autonomous route extraction and generation method based on map features | |
| CN110703800A (en) | Unmanned aerial vehicle-based intelligent identification method and system for electric power facilities | |
| CN106547814A (en) | A kind of power transmission line unmanned machine patrols and examines the structuring automatic archiving method of image | |
| CN108365557A (en) | A kind of method and system of unmanned plane fining inspection transmission line of electricity | |
| CN112445765B (en) | Aerial line unmanned aerial vehicle inspection picture sorting and naming method based on smart phone APP | |
| CN110969719A (en) | Automatic inspection method, system, terminal equipment and storage medium | |
| CN110032654B (en) | Supermarket commodity entry method and system based on artificial intelligence | |
| CN108961276B (en) | Distribution line inspection data automatic acquisition method and system based on visual servo | |
| CN114723271A (en) | Power transmission project quality detection method and system based on image recognition | |
| CN112487894A (en) | Automatic inspection method and device for rail transit protection area based on artificial intelligence | |
| CN115865915A (en) | Unmanned aerial vehicle inspection image real-time identification method and system based on edge calculation | |
| CN110782484A (en) | Unmanned aerial vehicle video personnel identification and tracking method | |
| CN116501091B (en) | Fan inspection control method and device based on unmanned aerial vehicle automatic adjustment route | |
| CN112260402B (en) | Monitoring method for state of intelligent substation inspection robot based on video monitoring | |
| CN113554781A (en) | Remote inspection method and device for overhead transmission line and computer equipment | |
| CN112631333A (en) | Target tracking method and device of unmanned aerial vehicle and image processing chip | |
| CN115297303B (en) | Image data acquisition and processing method and device suitable for power grid power transmission and transformation equipment | |
| CN117218534A (en) | Crop leaf disease identification method | |
| CN115661694A (en) | Intelligent detection method, system, storage medium and electronic equipment for light-weight main transformer focusing on key characteristics | |
| CN114782396A (en) | Shore-based antenna detection system based on CCTV | |
| CN113298292A (en) | Power distribution line power pole tower inspection and management and control method and system based on power internet of things | |
| CN111179458A (en) | Method and device for routing inspection of rail transit equipment |
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 |