CN111709361A - Unmanned aerial vehicle inspection data processing method for power transmission line - Google Patents
Unmanned aerial vehicle inspection data processing method for power transmission line Download PDFInfo
- Publication number
- CN111709361A CN111709361A CN202010548758.4A CN202010548758A CN111709361A CN 111709361 A CN111709361 A CN 111709361A CN 202010548758 A CN202010548758 A CN 202010548758A CN 111709361 A CN111709361 A CN 111709361A
- Authority
- CN
- China
- Prior art keywords
- picture
- defect
- information
- line
- aerial vehicle
- 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.)
- Granted
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 51
- 230000005540 biological transmission Effects 0.000 title claims abstract description 37
- 238000003672 processing method Methods 0.000 title claims description 20
- 230000007547 defect Effects 0.000 claims abstract description 240
- 238000000034 method Methods 0.000 claims abstract description 44
- 238000012423 maintenance Methods 0.000 claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 33
- 238000012545 processing Methods 0.000 claims abstract description 23
- 239000000284 extract Substances 0.000 claims description 10
- 238000004519 manufacturing process Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 4
- 238000007405 data analysis Methods 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 238000004801 process automation Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000003745 diagnosis Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 210000001367 artery Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- 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
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Abstract
The invention provides a method for processing routing inspection data of an unmanned aerial vehicle of a power transmission line, which is used for collecting routing inspection pictures and laser point cloud analysis reports shot by a daily operation and maintenance unmanned aerial vehicle; renaming the inspection picture through a picture name and carrying out defect identification on the renamed picture; renaming the related pictures and carrying out defect identification on the renamed pictures by using a report analyzer for the laser point cloud analysis report; manually checking defects; generating defect-related information using a defect generator; and (5) recording the defects by using the RPA robot and informing a team manager. The invention effectively improves the intelligent and automatic level of the operation and maintenance work of the power transmission line, and has good popularization and application values.
Description
Technical Field
The invention relates to the field of high-voltage transmission line operation and inspection, in particular to a transmission line unmanned aerial vehicle inspection data processing method.
Background
In recent years, with the economic development, the demand of power supply is increasing year by year, and the high-voltage transmission line has a self-evident significance as a main artery for ensuring the stable operation of a power grid. However, most of high-voltage transmission lines operate in suburb fields and are often influenced by changes of severe weather, geographic environments, operation conditions and the like, and the defects and hidden dangers that the safe and reliable operation of a power grid is endangered inevitably occur. In order to ensure the safe and stable operation of the high-voltage transmission line, a transmission line operation and maintenance unit makes a series of strict operation and maintenance measures, such as regular inspection and defect search on the transmission line. Along with the development of technique, present transmission line patrols and mainly relies on unmanned aerial vehicle to go on with the defect mode of seeking, and visible light unmanned aerial vehicle inlet line becomes more meticulous to be patrolled promptly, seeks equipment body defect hidden danger, and application laser radar unmanned aerial vehicle carries out laser modeling, seeks passageway tree obstacle equidistance class defect hidden danger. The unmanned aerial vehicle inspection operation of the power transmission line reduces the workload of manual inspection work, and simultaneously acquires a large amount of inspection data, namely data such as inspection photos and laser point cloud analysis reports, the existing inspection data still need to be checked manually, renames and files the inspection data and inputs the defect hidden danger into a company system, and a defect hidden danger flow is opened. The manual processing method has the following three problems: firstly, the workload is huge, and a large amount of manpower and material resources are wasted. According to statistics, more than twenty thousand unmanned aerial vehicle routing inspection pictures are acquired every year by a local office operation and maintenance unit responsible for managing five thousand kilometers of power transmission lines, thousands of laser point cloud analysis reports are obtained, the traditional analysis method needs manual processing, the workload of operation and maintenance personnel is huge, special responsible personnel and line operation and maintenance personnel need to repeatedly communicate and verify defect hidden danger information to ensure the accuracy and reliability of processing information, the repeated verification work occupies the time of the operation and maintenance personnel, unnecessary work burden is caused, and a large amount of manpower and material resources are wasted; and secondly, the time consumption is too long, the efficiency is low, the hidden danger of the line defect cannot be timely treated, and the safe and stable operation of the line is ensured. The manual processing of the routing inspection data not only has large workload, but also takes tens of thousands of working hours every year, and the overlong manual processing time causes that the hidden danger of the line defect cannot be found in time, thereby influencing the rectification and the modification of the hidden danger of the power transmission line defect and failing to ensure the safe and stable operation of the line; and thirdly, errors and omissions are easy to occur, so that the defect hidden danger exists, and the defect processing flow is not actually recorded into a system and rectified and processed, or is wrongly developed due to the identification errors. Through investigation, one operation and maintenance person often needs to be responsible for the operation and maintenance of four fifty kilometers transmission lines, the defect hidden dangers of the lines are more than four or five hundred, the excessive workload and the quality of the operation and maintenance person are uneven, and part of persons do not know about part of the defect hidden dangers, so that the line defect hidden dangers are easily found and recorded incompletely, or the situation that discrimination errors occur and then defect hidden danger processing procedures are carried out mistakenly occurs. According to statistics of thousands of defect hidden dangers every year, the error leakage is approximately 30%, and the safe and stable operation of the line is influenced. Therefore, a flexible and efficient intelligent processing method for routing inspection data of the unmanned aerial vehicle of the power transmission line is urgently needed, so that the working efficiency of routing inspection data processing is improved, a large amount of manpower and material resources are saved, the timely discovery and processing of hidden defects and hidden dangers are guaranteed, the overall safety factor of the power transmission line is improved, and the safe and stable operation of the line is guaranteed.
The patent specification with the application number of 201911266886.3 discloses an unmanned aerial vehicle inspection system and a method for a distribution network overhead transmission line, in the application, an unmanned aerial vehicle inspection unit is used for obtaining inspection data of power equipment, a ground measurement and control station is used for communicating with the unmanned aerial vehicle inspection unit, the inspection data obtained by the unmanned aerial vehicle can be transmitted to the ground measurement and control station, data screening is carried out in the ground measurement and control station, a ground data processing unit is used for carrying out line diagnosis on the inspection data obtained by the ground measurement and control station, and a whole set of screening from the inspection data to the inspection data is formed and then is sent to an intelligent diagnosis system. The system can save a large amount of time and cost, can overcome the problems of detection omission, false detection and the like during manual detection, and greatly improves the detection precision. However, the patent cannot realize automatic naming of inspection photos, development of inspection photo defect identification, extraction and recording of inspection report defects, and recording of defects into a company system.
Disclosure of Invention
The invention provides a flexible and efficient unmanned aerial vehicle routing inspection data processing method for a power transmission line.
In order to achieve the technical effects, the technical scheme of the invention is as follows:
a method for processing routing inspection data of an unmanned aerial vehicle of a power transmission line comprises the following steps:
s1: collecting a patrol picture and a laser point cloud analysis report shot by a daily operation and maintenance unmanned aerial vehicle;
s2: renaming the inspection picture in the step S1 through a picture name and identifying the defect of the renamed picture;
s3: renaming the related pictures and carrying out defect identification on the renamed pictures by using the report analyzer for the laser point cloud analysis report in the step S1;
s4: manually checking defects;
s5: generating defect-related information using a defect generator;
s6: and (5) recording the defects by using the RPA robot and informing a team manager.
Further, in step S1, the process of collecting the laser point cloud analysis report is as follows: and taking a point cloud data analysis report acquired by the daily operation and maintenance laser radar unmanned aerial vehicle as input data, wherein the laser point cloud analysis report is generated by processing of laser point cloud processing software and is stored in a Word document form.
Further, in step S2, the process of renaming a picture by the picture name is:
1) inputting an original machine patrol picture;
2) extracting longitude, latitude, height and shooting time information in the picture;
3) circularly extracting longitude, latitude and height information of a line A phase, a line B phase, a line C phase, a ground wire and a basic component in a line standing book library, and taking the minimum value of all distances according to the spatial distance between a computer patrol picture and the extracted standing book component; if the distance is less than 10 meters, the machine patrol picture shooting object is regarded as the line component, and the machine patrol picture is matched with the machine account line component; if the distance is within the range of 10-200 m, the machine patrol picture is considered as the channel picture of the line tower, and the machine patrol picture is matched with the machine account line tower; if the distance is more than 200 meters, the patrol picture of the machine is not considered to belong to any return account line, a problem exists, the related information of the picture is recorded into a problem database, the picture is additionally stored, and the picture is checked and examined manually;
4) renaming the picture according to the matching result, renaming the machine patrol picture according to a format JPG if the machine patrol picture is matched with a line component in the standing book, and renaming the machine patrol picture according to a format JPG if the machine patrol picture is matched with the line component in the standing book;
5) and outputting the renaming machine patrol picture to finish the renaming work flow.
Further, in step S2, the process of identifying the defect in the renamed picture is as follows:
1) inputting a machine patrol picture needing to be identified;
2) identifying components of the picture, and identifying the components of the power transmission equipment in the picture according to a previously trained Faster R-CNN power transmission equipment component identification model;
3) judging the identification result, and if the existence of the equipment part is identified, inputting the picture into S4; if the device component does not exist, recording the relevant picture information into a problem database, storing the picture in addition, and checking manually;
4) intercepting the part of the equipment component in the picture, storing the picture and inputting the picture into the step 5);
5) identifying the defects of the power transmission equipment in the picture according to a defect identification model of the Faster R-CNN power transmission equipment trained in the early stage, marking the defects if the defects exist in the picture, renaming the picture according to a ' voltage class _ line name _ pole tower number _ component _ timestamp _ defect type ' JPG ' format, and entering the step 6);
6) and outputting a defect picture to finish a defect identification working flow.
Further, in step S3, the laser point cloud analysis report is generated by processing with laser point cloud processing software, and is generally stored in a Word document form, and it is necessary to analyze and extract defect information in the document, and the laser point cloud analysis workflow includes the following steps:
1) inputting a laser point cloud analysis report;
2) extracting defect information in the report, summarizing a defect information table in the laser point cloud analysis report, and analyzing and extracting the line, the tower and the defect information of the table;
3) comparing the line account library, if the relevant lines and towers exist, extracting the corresponding defect picture of the report, and inputting the defect picture into S4; if the defect information does not exist, recording the pictures and the related information of the lines, the towers and the defects into a problem database, and storing the pictures in addition and checking the pictures manually;
4) matching the extracted defect picture with related line, tower and defect information, and renaming the picture according to a ' voltage class _ line name _ tower number _ component _ timestamp _ defect type ' JPG ' format, and entering a step 5);
5) and outputting the defect picture to finish the laser point cloud report analysis working process.
Further, the specific process of step S4 is: and manually checking and judging the extracted defect picture, inputting the picture into a defect generator if the extracted defect picture is correct, recording the relevant information of the picture into a problem database if the extracted defect picture is wrong, and storing the picture in addition for manually analyzing and extracting the reason of the mistake so as to continuously perfect the system.
Further, the specific process of step S5 is:
1) inputting a defect picture;
2) extracting line, tower, component, defect type and time information in the picture name;
3) comparing the defect library, searching and checking whether the historical defect library has related defect information after the photo time, if not, indicating that the defect is not recorded into the system, and entering S4; if the relevant defect information exists, it indicates that the operation and maintenance personnel may input the defect into the generation management system, so that the picture relevant information is recorded into the problem database, and the picture is additionally stored and is checked and examined manually;
4) comparing the work ticket library, searching and checking whether the historical work tickets have related defect elimination information after the photo time, if not, indicating that the defects are not processed, and entering S5; if the relevant defects are processed, the operation and maintenance personnel are indicated to possibly process the relevant defects, so that the picture relevant information is recorded into a problem database, and the picture is additionally stored and is checked and examined manually;
5) comparing the personnel equipment base, extracting the operation and maintenance team, personnel and team leader information of the corresponding line, and entering step 6 if the operation and maintenance information of the line section exists; if the picture does not exist, recording the relevant information of the picture into a problem database, storing the picture in addition, and checking and examining the picture manually;
6) comparing the defect representation library, extracting specific representations of corresponding defect types, and entering a step 7) if the defect representations exist; if the picture does not exist, recording the relevant information of the picture into a problem database, storing the picture in addition, and checking and examining the picture manually;
7) and generating defect entry information, generating related information including line names, tower numbers, components, operation and maintenance teams, operation and maintenance personnel, line team leaders, defect types and defect specific representations needing to be entered into the production management system according to the steps, further generating the defect entry information, and finishing the defect information generation work flow.
Further, the specific process of step S6 is:
and simulating a manual defect recording process by the RPA machine operation production system, recording the defects into the generation management system, simulating a manual message sending process, and sending the recorded defect information to related managers through an internal communication tool. The production management system is an information system uniformly built for a power grid, and in consideration of ensuring the safe operation of the system, the system does not open any API operation interface, and the work order entry can only provide front-end page operation entry through the system, wherein the RPA is robot Process Automation, and can simulate manual work to carry out system operation, replace manual work to carry out repeated entry and message sending work.
Further, in step S3, the process of renaming the related picture and performing defect identification on the renamed picture is as follows: and the report analyzer extracts the line, tower and defect information in the report, compares the line, tower and defect information with a line account library, extracts a corresponding defect picture and renames the picture according to the fixation if the related line and tower exist, and records the picture related information into a problem database if the related line and tower do not exist, wherein the picture is additionally stored and is checked and examined manually.
Further, the defect generator respectively judges whether the historical defect and the work ticket have related defect information after the photo time according to the line, tower, part and defect type information in the picture and by combining a defect library and a work ticket library, if not, according to a personnel equipment library and a defect representation library, searching the responsible personnel information and the corresponding description representation information of the defect type of the related line tower, generating a defect message, sending the defect message to the RPA robot for processing, if so, not generating the defect message, recording the related information of the picture to a problem database, additionally storing the picture, and manually checking and auditing.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
(1) automatic analysis unmanned aerial vehicle patrols and examines data, and statistics defect and automatic entry system can save a large amount of manpower and materials resources, alleviate personnel's work burden. By using the intelligent processing method provided by the invention, the system can automatically name the inspection photo, carry out inspection photo defect identification, extract and record inspection report defects and record the defects into a company system. Compared with the traditional manual reverse treatment, the method reduces the workload of personnel and saves a large amount of manpower and material resources;
(2) the working time is shortened, and the working efficiency is improved. According to the intelligent processing method provided by the invention, the program is automatically processed, the uninterrupted operation can be carried out for 24 hours, meanwhile, special responsible personnel and circuit operation and maintenance personnel are not required to repeatedly communicate and verify defect hidden danger information, the mutual communication and exchange verification processes of manual statistics are omitted, a large amount of time can be saved, the defect hidden danger of the power transmission line can be timely found and processed, and the safe and stable operation of the circuit is ensured;
(3) the routing inspection information processing is more objective and comprehensive. According to the intelligent processing method provided by the invention, the machine uniformly identifies and processes the defects, the normalization of routing inspection data processing can be ensured, the accuracy of defect identification is ensured, compared with the traditional manual processing, the intelligent processing method is more objective and comprehensive, the error rate and the leakage rate are lower, the routing inspection data of the unmanned aerial vehicle can be processed according to requirements, and the timely and comprehensive discovery and input of the hidden troubles of line defects are ensured.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a picture naming tool workflow;
FIG. 3 is an image recognition workflow;
FIG. 4 is a report analyzer workflow;
fig. 5 is a defect generator workflow.
Detailed Description
The drawings are for illustrative purposes only and are not to be construed as limiting the patent;
for the purpose of better illustrating the embodiments, certain features of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product;
it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical solution of the present invention is further described below with reference to the accompanying drawings and examples.
As shown in fig. 1, a method for processing data of unmanned aerial vehicle routing inspection of power transmission line includes the following steps:
s1: collecting a patrol picture and a laser point cloud analysis report shot by a daily operation and maintenance unmanned aerial vehicle;
s2: renaming the inspection picture in the step S1 through a picture name and carrying out defect identification on the renamed picture: according to the AI image identification process, sequentially carrying out component identification, capturing component parts in the image, identifying and marking defects on the renamed image, renaming the image according to the identified defect type, and finally outputting the defect image;
s3: renaming the related pictures and carrying out defect identification on the renamed pictures by using the report analyzer for the laser point cloud analysis report in the step S1;
s4: manually checking defects;
s5: generating defect-related information using a defect generator;
s6: and (5) recording the defects by using the RPA robot and informing a team manager.
Further, in step S1, the process of collecting the laser point cloud analysis report is as follows: and taking a point cloud data analysis report acquired by the daily operation and maintenance laser radar unmanned aerial vehicle as input data, wherein the laser point cloud analysis report is generated by processing of laser point cloud processing software and is stored in a Word document form.
As shown in fig. 2, in step S2, the process of renaming a picture by the picture name is:
1) inputting an original machine patrol picture;
2) extracting longitude, latitude, height and shooting time information in the picture;
3) circularly extracting longitude, latitude and height information of a line A phase, a line B phase, a line C phase, a ground wire and a basic component in a line standing book library, and taking the minimum value of all distances according to the spatial distance between a computer patrol picture and the extracted standing book component; if the distance is less than 10 meters, the machine patrol picture shooting object is regarded as the line component, and the machine patrol picture is matched with the machine account line component; if the distance is within the range of 10-200 m, the machine patrol picture is considered as the channel picture of the line tower, and the machine patrol picture is matched with the machine account line tower; if the distance is more than 200 meters, the patrol picture of the machine is not considered to belong to any return account line, a problem exists, the related information of the picture is recorded into a problem database, the picture is additionally stored, and the picture is checked and examined manually;
4) renaming the picture according to the matching result, renaming the machine patrol picture according to a format JPG if the machine patrol picture is matched with a line component in the standing book, and renaming the machine patrol picture according to a format JPG if the machine patrol picture is matched with the line component in the standing book;
5) and outputting the renaming machine patrol picture to finish the renaming work flow.
As shown in fig. 3, in step S2, the process of identifying the defect in the renamed picture is as follows:
1) inputting a machine patrol picture needing to be identified;
2) identifying components of the picture, and identifying the components of the power transmission equipment in the picture according to a previously trained Faster R-CNN power transmission equipment component identification model;
3) judging the identification result, and if the existence of the equipment part is identified, inputting the picture into S4; if the device component does not exist, recording the relevant picture information into a problem database, storing the picture in addition, and checking manually;
4) intercepting the part of the equipment component in the picture, storing the picture and inputting the picture into the step 5);
5) identifying the defects of the power transmission equipment in the picture according to a defect identification model of the Faster R-CNN power transmission equipment trained in the early stage, marking the defects if the defects exist in the picture, renaming the picture according to a ' voltage class _ line name _ pole tower number _ component _ timestamp _ defect type ' JPG ' format, and entering the step 6);
6) and outputting a defect picture to finish a defect identification working flow.
As shown in fig. 4, in step S3, the laser point cloud analysis report is generated by processing of laser point cloud processing software, and is generally stored in a Word document form, and it is necessary to analyze and extract defect information in the document, and the laser point cloud analysis workflow includes the following steps:
1) inputting a laser point cloud analysis report;
2) extracting defect information in the report, summarizing a defect information table in the laser point cloud analysis report, and analyzing and extracting the line, the tower and the defect information of the table;
3) comparing the line account library, if the relevant lines and towers exist, extracting the corresponding defect picture of the report, and inputting the defect picture into S4; if the defect information does not exist, recording the pictures and the related information of the lines, the towers and the defects into a problem database, and storing the pictures in addition and checking the pictures manually;
4) matching the extracted defect picture with related line, tower and defect information, and renaming the picture according to a ' voltage class _ line name _ tower number _ component _ timestamp _ defect type ' JPG ' format, and entering a step 5);
5) and outputting the defect picture to finish the laser point cloud report analysis working process.
The specific process of step S4 is: and manually checking and judging the extracted defect picture, inputting the picture into a defect generator if the extracted defect picture is correct, recording the relevant information of the picture into a problem database if the extracted defect picture is wrong, and storing the picture in addition for manually analyzing and extracting the reason of the mistake so as to continuously perfect the system.
As shown in fig. 5, the specific process of step S5 is:
1) inputting a defect picture;
2) extracting line, tower, component, defect type and time information in the picture name;
3) comparing the defect library, searching and checking whether the historical defect library has related defect information after the photo time, if not, indicating that the defect is not recorded into the system, and entering S4; if the relevant defect information exists, it indicates that the operation and maintenance personnel may input the defect into the generation management system, so that the picture relevant information is recorded into the problem database, and the picture is additionally stored and is checked and examined manually;
4) comparing the work ticket library, searching and checking whether the historical work tickets have related defect elimination information after the photo time, if not, indicating that the defects are not processed, and entering S5; if the relevant defects are processed, the operation and maintenance personnel are indicated to possibly process the relevant defects, so that the picture relevant information is recorded into a problem database, and the picture is additionally stored and is checked and examined manually;
5) comparing the personnel equipment base, extracting the operation and maintenance team, personnel and team leader information of the corresponding line, and entering step 6 if the operation and maintenance information of the line section exists; if the picture does not exist, recording the relevant information of the picture into a problem database, storing the picture in addition, and checking and examining the picture manually;
6) comparing the defect representation library, extracting specific representations of corresponding defect types, and entering a step 7) if the defect representations exist; if the picture does not exist, recording the relevant information of the picture into a problem database, storing the picture in addition, and checking and examining the picture manually;
7) and generating defect entry information, generating related information including line names, tower numbers, components, operation and maintenance teams, operation and maintenance personnel, line team leaders, defect types and defect specific representations needing to be entered into the production management system according to the steps, further generating the defect entry information, and finishing the defect information generation work flow.
The specific process of step S6 is:
and simulating a manual defect recording process by the RPA machine operation production system, recording the defects into the generation management system, simulating a manual message sending process, and sending the recorded defect information to related managers through an internal communication tool. The production management system is an information system uniformly built for a power grid, and in consideration of ensuring the safe operation of the system, the system does not open any API operation interface, and the work order entry can only provide front-end page operation entry through the system, wherein the RPA is robot Process Automation, and can simulate manual work to carry out system operation, replace manual work to carry out repeated entry and message sending work.
In step S3, the process of renaming the related picture and performing defect identification on the renamed picture is as follows: and the report analyzer extracts the line, tower and defect information in the report, compares the line, tower and defect information with a line account library, extracts a corresponding defect picture and renames the picture according to the fixation if the related line and tower exist, and records the picture related information into a problem database if the related line and tower do not exist, wherein the picture is additionally stored and is checked and examined manually.
And the defect generator respectively judges whether the historical defects and the working tickets have related defect information after the time of the picture according to the line, tower, part and defect type information in the picture and by combining the defect library and the working ticket library, if not, according to the personnel equipment library and the defect representation library, searching the corresponding description representation information of the responsible personnel information and the defect types of the related line tower, generating a defect message, sending the defect message to the RPA robot for processing, if so, not generating the defect message, recording the related information of the picture to the problem database, storing the picture additionally, and checking and auditing manually.
The same or similar reference numerals correspond to the same or similar parts;
the positional relationships depicted in the drawings are for illustrative purposes only and are not to be construed as limiting the present patent;
it should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (10)
1. The unmanned aerial vehicle inspection data processing method for the power transmission line is characterized by comprising the following steps of:
s1: collecting a patrol picture and a laser point cloud analysis report shot by a daily operation and maintenance unmanned aerial vehicle;
s2: renaming the inspection picture in the step S1 through a picture name and identifying the defect of the renamed picture;
s3: renaming the related pictures and carrying out defect identification on the renamed pictures by using the report analyzer for the laser point cloud analysis report in the step S1;
s4: manually checking defects;
s5: generating defect-related information using a defect generator;
s6: and (5) recording the defects by using the RPA robot and informing a team manager.
2. The unmanned aerial vehicle inspection data processing method according to claim 1, wherein in step S1, the process of collecting the laser point cloud analysis report is as follows: and taking a point cloud data analysis report acquired by the daily operation and maintenance laser radar unmanned aerial vehicle as input data, wherein the laser point cloud analysis report is generated by processing of laser point cloud processing software and is stored in a Word document form.
3. The unmanned aerial vehicle inspection data processing method according to claim 2, wherein in step S2, the process of renaming the picture by the picture name is as follows:
1) inputting an original machine patrol picture;
2) extracting longitude, latitude, height and shooting time information in the picture;
3) circularly extracting longitude, latitude and height information of a line A phase, a line B phase, a line C phase, a ground wire and a basic component in a line standing book library, and taking the minimum value of all distances according to the spatial distance between a computer patrol picture and the extracted standing book component; if the distance is less than 10 meters, the machine patrol picture shooting object is regarded as the line component, and the machine patrol picture is matched with the machine account line component; if the distance is within the range of 10-200 m, the machine patrol picture is considered as the channel picture of the line tower, and the machine patrol picture is matched with the machine account line tower; if the distance is more than 200 meters, the patrol picture of the machine is not considered to belong to any return account line, a problem exists, the related information of the picture is recorded into a problem database, the picture is additionally stored, and the picture is checked and examined manually;
4) renaming the picture according to the matching result, renaming the machine patrol picture according to a format JPG if the machine patrol picture is matched with a line component in the standing book, and renaming the machine patrol picture according to a format JPG if the machine patrol picture is matched with the line component in the standing book;
5) and outputting the renaming machine patrol picture to finish the renaming work flow.
4. The unmanned aerial vehicle inspection data processing method according to claim 3, wherein in step S2, the process of identifying the renamed picture is as follows:
1) inputting a machine patrol picture needing to be identified;
2) identifying components of the picture, and identifying the components of the power transmission equipment in the picture according to a previously trained Faster R-CNN power transmission equipment component identification model;
3) judging the identification result, and if the existence of the equipment part is identified, inputting the picture into S4; if the device component does not exist, recording the relevant picture information into a problem database, storing the picture in addition, and checking manually;
4) intercepting the part of the equipment component in the picture, storing the picture and inputting the picture into the step 5);
5) identifying the defects of the power transmission equipment in the picture according to a defect identification model of the Faster R-CNN power transmission equipment trained in the early stage, marking the defects if the defects exist in the picture, renaming the picture according to a ' voltage class _ line name _ pole tower number _ component _ timestamp _ defect type ' JPG ' format, and entering the step 6);
6) and outputting a defect picture to finish a defect identification working flow.
5. The unmanned aerial vehicle inspection data processing method according to claim 4, wherein in step S3, the laser point cloud analysis report is generated by processing of laser point cloud processing software, is generally stored in a Word document form, and needs to analyze and extract defect information in the document, and the laser point cloud report analysis workflow comprises the following steps:
1) inputting a laser point cloud analysis report;
2) extracting defect information in the report, summarizing a defect information table in the laser point cloud analysis report, and analyzing and extracting the line, the tower and the defect information of the table;
3) comparing the line account library, if the relevant lines and towers exist, extracting the corresponding defect picture of the report, and inputting the defect picture into S4; if the defect information does not exist, recording the pictures and the related information of the lines, the towers and the defects into a problem database, and storing the pictures in addition and checking the pictures manually;
4) matching the extracted defect picture with related line, tower and defect information, and renaming the picture according to a ' voltage class _ line name _ tower number _ component _ timestamp _ defect type ' JPG ' format, and entering a step 5);
5) and outputting the defect picture to finish the laser point cloud report analysis working process.
6. The unmanned aerial vehicle inspection data processing method according to claim 5, wherein the specific process of step S4 is as follows: and manually checking and judging the extracted defect picture, inputting the picture into a defect generator if the extracted defect picture is correct, recording the relevant information of the picture into a problem database if the extracted defect picture is wrong, and storing the picture in addition for manually analyzing and extracting the reason of the mistake so as to continuously perfect the system.
7. The unmanned aerial vehicle inspection data processing method according to claim 6, wherein the specific process of step S5 is as follows:
1) inputting a defect picture;
2) extracting line, tower, component, defect type and time information in the picture name;
3) comparing the defect library, searching and checking whether the historical defect library has related defect information after the photo time, if not, indicating that the defect is not recorded into the system, and entering S4; if the relevant defect information exists, it indicates that the operation and maintenance personnel may input the defect into the generation management system, so that the picture relevant information is recorded into the problem database, and the picture is additionally stored and is checked and examined manually;
4) comparing the work ticket library, searching and checking whether the historical work tickets have related defect elimination information after the photo time, if not, indicating that the defects are not processed, and entering S5; if the relevant defects are processed, the operation and maintenance personnel are indicated to possibly process the relevant defects, so that the picture relevant information is recorded into a problem database, and the picture is additionally stored and is checked and examined manually;
5) comparing the personnel equipment base, extracting the operation and maintenance team, personnel and team leader information of the corresponding line, and entering step 6 if the operation and maintenance information of the line section exists; if the picture does not exist, recording the relevant information of the picture into a problem database, storing the picture in addition, and checking and examining the picture manually;
6) comparing the defect representation library, extracting specific representations of corresponding defect types, and entering a step 7) if the defect representations exist; if the picture does not exist, recording the relevant information of the picture into a problem database, storing the picture in addition, and checking and examining the picture manually;
7) and generating defect entry information, generating related information including line names, tower numbers, components, operation and maintenance teams, operation and maintenance personnel, line team leaders, defect types and defect specific representations needing to be entered into the production management system according to the steps, further generating the defect entry information, and finishing the defect information generation work flow.
8. The unmanned aerial vehicle inspection data processing method according to claim 7, wherein the specific process of step S6 is as follows:
and simulating a manual defect recording process by the RPA machine operation production system, recording the defects into the generation management system, simulating a manual message sending process, and sending the recorded defect information to related managers through an internal communication tool. The production management system is an information system uniformly built for a power grid, and in consideration of ensuring the safe operation of the system, the system does not open any API operation interface, and the work order entry can only provide front-end page operation entry through the system, wherein the RPA is robot Process Automation, and can simulate manual work to carry out system operation, replace manual work to carry out repeated entry and message sending work.
9. The unmanned aerial vehicle inspection data processing method according to claim 8, wherein in step S3, the process of renaming the related pictures and performing defect identification on the renamed pictures is as follows: and the report analyzer extracts the line, tower and defect information in the report, compares the line, tower and defect information with a line account library, extracts a corresponding defect picture and renames the picture according to the fixation if the related line and tower exist, and records the picture related information into a problem database if the related line and tower do not exist, wherein the picture is additionally stored and is checked and examined manually.
10. The unmanned aerial vehicle inspection data processing method of the power transmission line according to any one of claims 1 to 9, wherein the defect generator respectively judges whether the historical defect and the work ticket have related defect information after the photo time according to the line, tower, component and defect type information in the picture and in combination with the defect library and the work ticket library, if not, according to the personnel device library and the defect representation library, the responsible personnel information and the corresponding description representation information of the defect type of the related line tower are searched, a defect message is generated and sent to the RPA robot for processing, if so, the defect message is not generated, the related picture information is recorded in the problem database, the picture is additionally stored, and the picture is manually checked and audited.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010548758.4A CN111709361B (en) | 2020-06-16 | 2020-06-16 | Method for processing inspection data of unmanned aerial vehicle of power transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010548758.4A CN111709361B (en) | 2020-06-16 | 2020-06-16 | Method for processing inspection data of unmanned aerial vehicle of power transmission line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111709361A true CN111709361A (en) | 2020-09-25 |
| CN111709361B CN111709361B (en) | 2024-01-26 |
Family
ID=72540162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010548758.4A Active CN111709361B (en) | 2020-06-16 | 2020-06-16 | Method for processing inspection data of unmanned aerial vehicle of power transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111709361B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112836471A (en) * | 2021-01-25 | 2021-05-25 | 上海微亿智造科技有限公司 | Batch labeling interface automation method and system |
| CN113052819A (en) * | 2021-03-25 | 2021-06-29 | 贵州电网有限责任公司 | Circuit defect picture acquisition and analysis system and acquisition and analysis method |
| CN113705708A (en) * | 2021-09-02 | 2021-11-26 | 国网福建省电力有限公司检修分公司 | Intelligent classification and naming method for unmanned aerial vehicle inspection pictures of power transmission line |
| CN114047779A (en) * | 2021-10-22 | 2022-02-15 | 贵州电网有限责任公司 | Defect tracking method and system based on unmanned aerial vehicle inspection |
| CN114461831A (en) * | 2022-04-13 | 2022-05-10 | 广东电网有限责任公司佛山供电局 | Automatic naming method and device for power transmission line inspection images |
| CN114782947A (en) * | 2022-06-22 | 2022-07-22 | 韶关市擎能设计有限公司 | Point cloud matching method, point cloud matching system and storage medium for power transmission and distribution line |
| CN114780685A (en) * | 2022-04-28 | 2022-07-22 | 贵州电网有限责任公司 | Method for automatically identifying defect information input condition and supplementing defect information through unmanned aerial vehicle |
| CN116303104A (en) * | 2023-05-19 | 2023-06-23 | 南方电网数字电网研究院有限公司 | Automated process defect screening management method, system and readable storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015131462A1 (en) * | 2014-03-07 | 2015-09-11 | 国家电网公司 | Centralized monitoring system and monitoring method for unmanned aerial vehicle to patrol power transmission line |
| CN106504362A (en) * | 2016-10-18 | 2017-03-15 | 国网湖北省电力公司检修公司 | Power transmission and transformation system method for inspecting based on unmanned plane |
| US20170206648A1 (en) * | 2016-01-20 | 2017-07-20 | Ez3D, Llc | System and method for structural inspection and construction estimation using an unmanned aerial vehicle |
| CN110580529A (en) * | 2019-08-16 | 2019-12-17 | 国电南瑞科技股份有限公司 | Automatic analysis management method, system and storage medium for refined inspection data of unmanned aerial vehicle of power transmission channel |
| CN110633629A (en) * | 2019-08-02 | 2019-12-31 | 广东电网有限责任公司清远供电局 | Power grid inspection method, device, equipment and storage medium based on artificial intelligence |
-
2020
- 2020-06-16 CN CN202010548758.4A patent/CN111709361B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015131462A1 (en) * | 2014-03-07 | 2015-09-11 | 国家电网公司 | Centralized monitoring system and monitoring method for unmanned aerial vehicle to patrol power transmission line |
| US20170206648A1 (en) * | 2016-01-20 | 2017-07-20 | Ez3D, Llc | System and method for structural inspection and construction estimation using an unmanned aerial vehicle |
| CN106504362A (en) * | 2016-10-18 | 2017-03-15 | 国网湖北省电力公司检修公司 | Power transmission and transformation system method for inspecting based on unmanned plane |
| CN110633629A (en) * | 2019-08-02 | 2019-12-31 | 广东电网有限责任公司清远供电局 | Power grid inspection method, device, equipment and storage medium based on artificial intelligence |
| CN110580529A (en) * | 2019-08-16 | 2019-12-17 | 国电南瑞科技股份有限公司 | Automatic analysis management method, system and storage medium for refined inspection data of unmanned aerial vehicle of power transmission channel |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112836471A (en) * | 2021-01-25 | 2021-05-25 | 上海微亿智造科技有限公司 | Batch labeling interface automation method and system |
| CN112836471B (en) * | 2021-01-25 | 2022-10-11 | 上海微亿智造科技有限公司 | Batch labeling interface automation method and system |
| CN113052819A (en) * | 2021-03-25 | 2021-06-29 | 贵州电网有限责任公司 | Circuit defect picture acquisition and analysis system and acquisition and analysis method |
| CN113705708A (en) * | 2021-09-02 | 2021-11-26 | 国网福建省电力有限公司检修分公司 | Intelligent classification and naming method for unmanned aerial vehicle inspection pictures of power transmission line |
| CN114047779A (en) * | 2021-10-22 | 2022-02-15 | 贵州电网有限责任公司 | Defect tracking method and system based on unmanned aerial vehicle inspection |
| CN114461831A (en) * | 2022-04-13 | 2022-05-10 | 广东电网有限责任公司佛山供电局 | Automatic naming method and device for power transmission line inspection images |
| CN114780685A (en) * | 2022-04-28 | 2022-07-22 | 贵州电网有限责任公司 | Method for automatically identifying defect information input condition and supplementing defect information through unmanned aerial vehicle |
| CN114782947A (en) * | 2022-06-22 | 2022-07-22 | 韶关市擎能设计有限公司 | Point cloud matching method, point cloud matching system and storage medium for power transmission and distribution line |
| CN116303104A (en) * | 2023-05-19 | 2023-06-23 | 南方电网数字电网研究院有限公司 | Automated process defect screening management method, system and readable storage medium |
| CN116303104B (en) * | 2023-05-19 | 2023-09-26 | 南方电网数字电网研究院有限公司 | Automated process defect screening management method, system and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111709361B (en) | 2024-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111709361A (en) | Unmanned aerial vehicle inspection data processing method for power transmission line | |
| CN111949809B (en) | Intelligent processing method for infrared inspection data of power transmission line | |
| CN110689148A (en) | Metering equipment fault detection method based on AR technology | |
| CN103678109A (en) | Dump document analysis method, device and system | |
| CN105761016A (en) | Bridge disease inspection management system and method | |
| CN112257740B (en) | Knowledge graph-based image hidden danger identification method and system | |
| CN112613339B (en) | Automatic identification and examination method and device for electrical drawing | |
| CN111444793A (en) | Bill recognition method, equipment, storage medium and device based on OCR | |
| CN111984788B (en) | Electric power system violation management method and device and electric power equipment | |
| CN109446689A (en) | DC converter station electrical secondary system drawing recognition methods and system | |
| CN115150589A (en) | Video monitoring operation and maintenance management system for coal mine enterprise | |
| CN111726577A (en) | Power distribution network engineering auditing method based on unmanned aerial vehicle inspection | |
| CN109949289A (en) | A kind of concrete surface defect image identifying system and method based on artificial intelligence | |
| CN113988573A (en) | Risk judgment method, system and medium for routing inspection unmanned aerial vehicle based on power system | |
| CN115395646A (en) | Intelligent operation and maintenance system of digital twin traction substation | |
| CN115034671A (en) | Secondary system information fault analysis method based on association rule and cluster | |
| CN115019294A (en) | Pointer instrument reading identification method and system | |
| CN110807415A (en) | Traffic checkpoint vehicle intelligent retrieval system and method based on annual inspection marks | |
| CN114491049A (en) | Office system asset allocation method based on information management | |
| CN109102036A (en) | A kind of image tagged method and device for transmission line malfunction identification | |
| CN112801432A (en) | Fan unit blade intelligent inspection system and fan unit blade inspection method | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN116488332A (en) | Automatic verification method for monitoring information of auxiliary control system of transformer substation | |
| CN117765375A (en) | Power grid inspection data management method and related device | |
| CN114282785A (en) | Intelligent examination management method and system for training examination in power industry |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |