CN111709361B - Method for processing inspection data of unmanned aerial vehicle of power transmission line - Google Patents
Method for processing inspection data of unmanned aerial vehicle of power transmission line Download PDFInfo
- Publication number
- CN111709361B CN111709361B CN202010548758.4A CN202010548758A CN111709361B CN 111709361 B CN111709361 B CN 111709361B CN 202010548758 A CN202010548758 A CN 202010548758A CN 111709361 B CN111709361 B CN 111709361B
- Authority
- CN
- China
- Prior art keywords
- defect
- picture
- line
- information
- inspection
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 93
- 230000005540 biological transmission Effects 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000012545 processing Methods 0.000 title claims abstract description 25
- 230000007547 defect Effects 0.000 claims abstract description 254
- 238000012423 maintenance Methods 0.000 claims abstract description 36
- 238000004458 analytical method Methods 0.000 claims abstract description 34
- 230000008569 process Effects 0.000 claims description 30
- 238000003672 processing method Methods 0.000 claims description 12
- 238000004519 manufacturing process Methods 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 5
- 101100074336 Xenopus laevis ripply2.1 gene Proteins 0.000 claims description 3
- 238000010276 construction Methods 0.000 claims description 3
- 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
- 238000000605 extraction Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 210000000709 aorta Anatomy 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000005304 joining Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—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 inspection data of an electric transmission line unmanned aerial vehicle, which is used for collecting inspection pictures and laser point cloud analysis reports shot by a daily operation and maintenance unmanned aerial vehicle; renaming the picture of the inspection picture through a picture naming, and carrying out defect identification on the renamed picture; renaming related pictures and carrying out defect identification on the renamed pictures by using a report analyzer for the laser point cloud analysis report; performing manual checking on defects; generating defect-related information using a defect generator; the RPA robot is used to enter the defect and notify team management personnel. The invention effectively improves the intelligent and automatic level of the operation and maintenance work of the transmission line, and has good popularization and application values.
Description
Technical Field
The invention relates to the field of operation and inspection of high-voltage transmission lines, in particular to a method for processing inspection data of an unmanned aerial vehicle of a transmission line.
Background
In recent years, with the economic development, the demand for power supply is also increasing year by year, and the important meaning of the high-voltage transmission line is self-evident as an aorta for ensuring the stable operation of a power grid. However, most of high-voltage transmission lines run in suburb open fields and are often influenced by changes of severe weather, geographical environment, running conditions and the like, and defects and hidden dangers endangering safe and reliable running of a power grid are unavoidable. In order to ensure safe and stable operation of the high-voltage transmission line, a series of strict operation and maintenance measures are formulated by an operation and maintenance unit of the transmission line, such as regular inspection, defect searching and the like of the transmission line. Along with the development of technology, the existing power transmission line inspection and defect searching mode is mainly carried out by means of unmanned aerial vehicles, namely, visible light unmanned aerial vehicles are utilized for line feeding and fine inspection, defect hidden dangers of equipment bodies are searched, laser radar unmanned aerial vehicles are utilized for laser modeling, and equidistant defect hidden dangers of channel tree barriers are searched. The unmanned aerial vehicle inspection operation of the power transmission line also collects a large amount of inspection data while reducing the manual inspection work burden, namely inspection photographs, laser point cloud analysis reports and other data, the existing inspection data still needs to be manually checked, renamed and filed, and defect hidden dangers are input into a company system, and a defect hidden danger flow is started. The manual processing method has the following three problems: 1. the workload is huge, and a great amount of manpower and material resources are wasted. According to statistics, more than twenty thousand inspection photographs of an unmanned aerial vehicle are acquired each year by a district office operation and maintenance unit responsible for managing a transmission line of five kilometers, thousands of laser point cloud analysis reports are acquired, and the traditional analysis method needs to rely on manual processing, so that the workload of operation and maintenance personnel is huge, and in order to ensure the accuracy and reliability of processing information, special responsible personnel and line operation and maintenance personnel are often required to repeatedly communicate and verify defect hidden danger information, so that the repeated verification work occupies the time of the operation and maintenance personnel, causes unnecessary workload and wastes a large amount of manpower and material resources; 2. the time consumption is too long, the efficiency is low, the hidden trouble of the line defect can not be treated in time, and the safe and stable operation of the line is ensured. The manual processing of the inspection data is large in workload, tens of thousands of working hours are consumed each year, and the line defect hidden danger cannot be found in time due to the overlong manual processing time, so that the correction of the power transmission line defect hidden danger is affected, and the safe and stable operation of the line cannot be ensured; 3. the error is easy to miss, so that the hidden trouble of the defect exists and the system is not recorded, the process is modified, or the defect process flow is wrongly developed due to the identification error. Through investigation, an operation and maintenance person often needs to bear the operation and maintenance responsibility of a transmission line of forty-fifty kilometers, but the types of defect hidden dangers of the transmission line are as many as four to five hundred kinds, the overload workload and the uneven quality of the operation and maintenance person are carried out, and part of the personnel do not know about part of the defect hidden dangers, so that the situation that the discovery and the input of the defect hidden dangers of the transmission line are incomplete or the identification errors occur so as to falsely develop the defect hidden danger processing flow is easily caused. According to thousands of defect hidden dangers each year, the error leakage is approximately 30%, and the safe and stable operation of the circuit is affected. Therefore, a flexible and efficient intelligent processing method for the inspection data of the unmanned aerial vehicle of the power transmission line is needed, so that the working efficiency of the processing of the inspection data is improved, a great amount of manpower and material resources are saved, the timely discovery and processing of hidden defects are ensured, the overall safety coefficient of the power transmission line is improved, and the safe and stable operation of the line is ensured.
The utility model discloses unmanned aerial vehicle inspection system and method of joining in marriage network overhead transmission line in the patent specification of application number 201911266886.3, this application utilizes unmanned aerial vehicle inspection unit to acquire power equipment's inspection data, utilize ground measurement and control station and unmanned aerial vehicle inspection unit to communicate, can make the inspection data transmission that unmanned aerial vehicle obtained to ground measurement and control station, carry out data screening in ground measurement and control station, the data processing unit that reuse carries out line diagnosis to the inspection data that ground measurement and control station obtained, the whole set of screening that follows the data that patrols and examines to inspection data has been formed and has been arrived intelligent diagnostic system again. The system can save a great amount of time cost, can overcome the problems of missing detection, false detection and the like during manual detection, and greatly improves the detection precision. However, the patent fails to realize automatic naming of inspection photographs, development of inspection photograph defect identification, extraction of inspection report defects, and entry of defects into a company system.
Disclosure of Invention
The invention provides a flexible and efficient transmission line unmanned aerial vehicle inspection data processing method.
In order to achieve the technical effects, the technical scheme of the invention is as follows:
the power transmission line unmanned aerial vehicle inspection data processing method comprises the following steps:
s1: collecting inspection pictures and laser point cloud analysis reports shot by a daily operation and maintenance unmanned aerial vehicle;
s2: renaming the picture of the inspection picture in the step S1 through a picture naming, and carrying out defect identification on the renamed picture;
s3: the laser point cloud analysis report in the step S1 is used for renaming related pictures by using a report analyzer and carrying out defect identification on the renamed pictures;
s4: performing manual checking on defects;
s5: generating defect-related information using a defect generator;
s6: the RPA robot is used to enter the defect and notify team management personnel.
Further, in the step S1, the process of collecting the laser point cloud analysis report is: 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 processed and generated by laser point cloud processing software and is stored in a Word document form.
Further, in step S2, the process of renaming the picture by the picture naming is:
1) Inputting an original machine inspection picture;
2) Extracting longitude, latitude, altitude 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 of a line ledger library, and taking the minimum value of all the distances from the space distance between a computer patrol picture and the extraction ledger component; if the distance is smaller than 10 meters, the machine inspection picture shooting object is considered as the line component, and the machine inspection picture is matched with the standing account line component; if the distance is in the range of 10 meters to 200 meters, the machine inspection picture is considered as a channel picture of the line pole tower, and the machine inspection picture is matched with the standing account line pole tower; if the distance is greater than 200 meters, considering that the machine inspection picture does not belong to any return account line, and a problem exists, recording relevant information of the picture into a problem database, and additionally storing the picture for manual inspection and verification;
4) Renaming the pictures according to the matching result, renaming the machine patrol pictures according to a 'voltage grade_line name_pole number_component_timestamp and JPG' format if the machine patrol pictures are matched with the line components in the ledger, and renaming the machine patrol pictures according to a 'voltage grade_line name_pole number_channel_timestamp and JPG' format if the machine patrol pictures are matched with the ledger line pole;
5) And outputting the inspection picture of the renamer to finish the renaming workflow.
Further, in step S2, the process of performing defect recognition on the renamed picture is:
1) Inputting a machine inspection picture to be identified;
2) Performing component identification on the picture, and identifying the power transmission equipment component in the picture according to a Faster R-CNN power transmission equipment component identification model trained in the earlier stage;
3) Judging the identification result, and inputting a picture into the S4 if the equipment component is identified; if the equipment component is identified to be absent, recording the related information of the picture into a problem database, and additionally storing the picture for manual checking and auditing;
4) Intercepting a device part in the picture, saving the picture and inputting the picture into the step 5);
5) Performing defect identification on the picture, identifying the defect of the power transmission equipment in the picture according to a Faster R-CNN power transmission equipment defect identification model trained in the earlier stage, marking the defect if the defect exists in the picture, renaming the picture according to a format of 'voltage grade_line name_tower number_component_timestamp_defect type. JPG', and entering into step 6);
6) And outputting the defect picture to finish the defect identification workflow.
Further, in step S3, the laser point cloud analysis report is processed and generated by the laser point cloud processing software, and is generally stored in a Word document form, and the defect information in the document needs to be analyzed and extracted, and the laser point cloud report 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 database, if the related lines and towers exist, extracting a report corresponding defect picture, and inputting the report corresponding defect picture into S4; if the picture does not exist, recording the picture, the line, the tower and the defect related information to a problem database, and additionally storing the picture for manual checking and auditing;
4) Matching the extracted defect picture with related lines, towers and defect information, renaming the picture according to a format of 'voltage grade_line name_tower number_component_timestamp_defect type · JPG', and entering step 5);
5) And outputting the defect picture to finish the laser point cloud report analysis workflow.
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 related information of the picture into a problem database if the extracted defect picture is incorrect, and additionally storing the picture for manually analyzing and extracting error reasons to continuously perfect a system.
Further, the specific process of step S5 is:
1) Inputting a defect picture;
2) Extracting the line, the tower, the component, the defect type and the time information in the picture name;
3) Comparing the defect library, searching and checking whether related defect information exists in the history defect library after the photo time, if not, indicating that the defect is not recorded into the system, and entering S4; if the related defect information exists, the operation and maintenance personnel can record the defect into the generation management system, so that the related information of the picture is recorded into a problem database, the picture is additionally stored, and is checked and checked manually;
4) Comparing the working ticket library, searching and checking whether the historical working ticket has relevant defect elimination information after the photo time, if not, indicating that the defect is unprocessed, and entering S5; if the related defects are processed, the operation and maintenance personnel are likely to process the related defects, so that the related information of the pictures is recorded into a problem database, the pictures are additionally stored, and checked manually;
5) Comparing the personnel equipment libraries, extracting the operation and maintenance team, personnel and team leader information of the corresponding line, and entering step 6 if the line section operation and maintenance information exists; if the picture does not exist, recording the related information of the picture to a problem database, and additionally storing the picture for manual checking and auditing;
6) Comparing the defect image library, extracting a specific image of the corresponding defect type, and if the defect image exists, entering the step 7); if the picture does not exist, recording the related information of the picture to a problem database, and additionally storing the picture for manual checking and auditing;
7) Generating defect entry information, and generating relevant information including a line name, a tower number, a component, an operation and maintenance team, operation and maintenance personnel, a line team length, a defect type and a defect specific appearance which need to be entered into a production management system according to the steps, so as to generate a defect entry message, and completing a defect message generation workflow.
Further, the specific process of step S6 is:
the RPA machine operates the production system to simulate the manual defect inputting process, inputs the defects into the generation management system, simulates the manual message sending process, and sends the input defect information to related management staff through an internal communication tool. The production management system is an information system for unified construction of a power grid, the system does not open any API operation interface for ensuring safe operation of the system, and work order input can only be performed by providing front page operation input through the system, wherein RPA is robot flow automation Robotic Process Automation, and the RPA can simulate manual system operation to replace manual repeated input and message sending work.
Further, in step S3, the process of renaming the related picture and performing defect recognition on the renamed picture is as follows: and the report analyzer extracts the line, the pole tower and the defect information in the report, compares the line and the pole tower with a line account library, extracts corresponding defect pictures and renames the pictures according to fixed if the related lines and the pole towers exist, records the picture related information to a problem database if the corresponding defect pictures do not exist, and additionally stores the pictures for manual checking and auditing.
Further, the defect generator respectively judges whether related defect information exists in the historical defect and the working ticket after the photo time according to the line, the tower, the part and the defect type information in the picture, and then combines the defect library and the working ticket library, if not, the defect generator searches responsible personnel information of the related line tower and corresponding description and appearance information of the defect type according to the personnel equipment library and the defect appearance library to generate defect information, sends the defect information to the RPA robot for processing, if so, does not generate the defect information, records the related information of the picture to the problem database, otherwise stores the picture, and checks and examines the picture manually.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that:
(1) The unmanned aerial vehicle inspection data is automatically analyzed, defects are counted, the system is automatically recorded, a large amount of manpower and material resources can be saved, and the workload of personnel is reduced. By using the intelligent processing method provided by the invention, the system can automatically name the inspection photo, conduct inspection photo defect identification, extract and record inspection report defects, and enter the defects into a company system. Compared with the traditional manual reverse treatment, the method reduces the workload of personnel and saves a great amount of manpower and material resources;
(2) Shortening the working time and improving the working efficiency. According to the intelligent processing method, the program is automatically processed, the operation can be carried out for 24 hours without interruption, meanwhile, special responsible personnel and line operation and maintenance personnel are not required to repeatedly communicate and verify defect hidden danger information, the manual statistics of the mutual communication and communication verification process is omitted, a large amount of time can be saved, the timely discovery and processing of the defect hidden danger of the power transmission line are ensured, and therefore the safe and stable operation of the line is ensured;
(3) The inspection information processing is more objective and comprehensive. The intelligent processing method provided by the invention has the advantages that the processing defects are uniformly identified by the machine, the normalization of 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 omission rate are lower, the unmanned aerial vehicle inspection data can be ensured to be processed according to the requirements, and the timely and comprehensive discovery and input of line defect hidden dangers are ensured.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a picture naming 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 present patent;
for the purpose of better illustrating the embodiments, certain elements of the drawings may be omitted, enlarged or reduced and do not represent the actual product dimensions;
it will be appreciated by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The technical scheme of the invention is further described below with reference to the accompanying drawings and examples.
As shown in fig. 1, the method for processing the inspection data of the unmanned aerial vehicle of the power transmission line comprises the following steps:
s1: collecting inspection pictures and laser point cloud analysis reports shot by a daily operation and maintenance unmanned aerial vehicle;
s2: and (3) renaming the picture of the inspection picture in the step (S1) through a picture naming and carrying out defect identification on the renamed picture: sequentially carrying out component recognition, intercepting component parts in the pictures, defect recognition and marking on renamed pictures according to an AI image recognition flow, renaming the pictures according to the type of the recognized defects, and finally outputting the defective pictures;
s3: the laser point cloud analysis report in the step S1 is used for renaming related pictures by using a report analyzer and carrying out defect identification on the renamed pictures;
s4: performing manual checking on defects;
s5: generating defect-related information using a defect generator;
s6: the RPA robot is used to enter the defect and notify team management personnel.
Further, in the step S1, the process of collecting the laser point cloud analysis report is: 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 processed and generated by 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 a picture naming method is as follows:
1) Inputting an original machine inspection picture;
2) Extracting longitude, latitude, altitude 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 of a line ledger library, and taking the minimum value of all the distances from the space distance between a computer patrol picture and the extraction ledger component; if the distance is smaller than 10 meters, the machine inspection picture shooting object is considered as the line component, and the machine inspection picture is matched with the standing account line component; if the distance is in the range of 10 meters to 200 meters, the machine inspection picture is considered as a channel picture of the line pole tower, and the machine inspection picture is matched with the standing account line pole tower; if the distance is greater than 200 meters, considering that the machine inspection picture does not belong to any return account line, and a problem exists, recording relevant information of the picture into a problem database, and additionally storing the picture for manual inspection and verification;
4) Renaming the pictures according to the matching result, renaming the machine patrol pictures according to a 'voltage grade_line name_pole number_component_timestamp and JPG' format if the machine patrol pictures are matched with the line components in the ledger, and renaming the machine patrol pictures according to a 'voltage grade_line name_pole number_channel_timestamp and JPG' format if the machine patrol pictures are matched with the ledger line pole;
5) And outputting the inspection picture of the renamer to finish the renaming workflow.
As shown in fig. 3, in step S2, the process of defect recognition on the renamed picture is as follows:
1) Inputting a machine inspection picture to be identified;
2) Performing component identification on the picture, and identifying the power transmission equipment component in the picture according to a Faster R-CNN power transmission equipment component identification model trained in the earlier stage;
3) Judging the identification result, and inputting a picture into the S4 if the equipment component is identified; if the equipment component is identified to be absent, recording the related information of the picture into a problem database, and additionally storing the picture for manual checking and auditing;
4) Intercepting a device part in the picture, saving the picture and inputting the picture into the step 5);
5) Performing defect identification on the picture, identifying the defect of the power transmission equipment in the picture according to a Faster R-CNN power transmission equipment defect identification model trained in the earlier stage, marking the defect if the defect exists in the picture, renaming the picture according to a format of 'voltage grade_line name_tower number_component_timestamp_defect type. JPG', and entering into step 6);
6) And outputting the defect picture to finish the defect identification workflow.
As shown in fig. 4, in step S3, the laser point cloud analysis report is processed and generated by the laser point cloud processing software, and is generally stored in the form of Word document, and the defect information in the document needs to be analyzed and extracted, and the laser point cloud report 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 database, if the related lines and towers exist, extracting a report corresponding defect picture, and inputting the report corresponding defect picture into S4; if the picture does not exist, recording the picture, the line, the tower and the defect related information to a problem database, and additionally storing the picture for manual checking and auditing;
4) Matching the extracted defect picture with related lines, towers and defect information, renaming the picture according to a format of 'voltage grade_line name_tower number_component_timestamp_defect type · JPG', and entering step 5);
5) And outputting the defect picture to finish the laser point cloud report analysis workflow.
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 related information of the picture into a problem database if the extracted defect picture is incorrect, and additionally storing the picture for manually analyzing and extracting error reasons to continuously perfect a system.
As shown in fig. 5, the specific procedure of step S5 is:
1) Inputting a defect picture;
2) Extracting the line, the tower, the component, the defect type and the time information in the picture name;
3) Comparing the defect library, searching and checking whether related defect information exists in the history defect library after the photo time, if not, indicating that the defect is not recorded into the system, and entering S4; if the related defect information exists, the operation and maintenance personnel can record the defect into the generation management system, so that the related information of the picture is recorded into a problem database, the picture is additionally stored, and is checked and checked manually;
4) Comparing the working ticket library, searching and checking whether the historical working ticket has relevant defect elimination information after the photo time, if not, indicating that the defect is unprocessed, and entering S5; if the related defects are processed, the operation and maintenance personnel are likely to process the related defects, so that the related information of the pictures is recorded into a problem database, the pictures are additionally stored, and checked manually;
5) Comparing the personnel equipment libraries, extracting the operation and maintenance team, personnel and team leader information of the corresponding line, and entering step 6 if the line section operation and maintenance information exists; if the picture does not exist, recording the related information of the picture to a problem database, and additionally storing the picture for manual checking and auditing;
6) Comparing the defect image library, extracting a specific image of the corresponding defect type, and if the defect image exists, entering the step 7); if the picture does not exist, recording the related information of the picture to a problem database, and additionally storing the picture for manual checking and auditing;
7) Generating defect entry information, and generating relevant information including a line name, a tower number, a component, an operation and maintenance team, operation and maintenance personnel, a line team length, a defect type and a defect specific appearance which need to be entered into a production management system according to the steps, so as to generate a defect entry message, and completing a defect message generation workflow.
The specific process of step S6 is:
the RPA machine operates the production system to simulate the manual defect inputting process, inputs the defects into the generation management system, simulates the manual message sending process, and sends the input defect information to related management staff through an internal communication tool. The production management system is an information system for unified construction of a power grid, the system does not open any API operation interface for ensuring safe operation of the system, and work order input can only be performed by providing front page operation input through the system, wherein RPA is robot flow automation Robotic Process Automation, and the RPA can simulate manual system operation to replace manual repeated input and message sending work.
In step S3, the process of renaming the related picture and performing defect recognition on the renamed picture is as follows: and the report analyzer extracts the line, the pole tower and the defect information in the report, compares the line and the pole tower with a line account library, extracts corresponding defect pictures and renames the pictures according to fixed if the related lines and the pole towers exist, records the picture related information to a problem database if the corresponding defect pictures do not exist, and additionally stores the pictures for manual checking and auditing.
The defect generator respectively judges whether related defect information exists in the historical defect and the working ticket after the photo time according to the line, the tower, the part and the defect type information in the picture, and then combines the defect library and the working ticket library, if not, the defect generator searches the responsible personnel information of the related line tower and the corresponding description appearance information of the defect type according to the personnel equipment library and the defect appearance library to generate a defect message, and sends the defect message to the RPA robot for processing, if so, the defect message is not generated, the related information of the picture is recorded to the problem database, the picture is additionally stored, and is checked and checked manually.
The same or similar reference numerals correspond to the same or similar components;
the positional relationship depicted in the drawings is for illustrative purposes only and is not to be construed as limiting the present patent;
it is to be understood that the above examples of the present invention are provided by way of illustration only and not by way of limitation of the embodiments of the present invention. Other variations or modifications of the above teachings will be apparent to those of ordinary skill in the art. It is not necessary here nor is it exhaustive of all embodiments. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the invention are desired to be protected by the following claims.
Claims (9)
1. The power transmission line unmanned aerial vehicle inspection data processing method is characterized by comprising the following steps of:
s1: collecting inspection pictures and laser point cloud analysis reports shot by a daily operation and maintenance unmanned aerial vehicle;
s2: renaming the picture of the inspection picture in the step S1 through a picture naming, and carrying out defect identification on the renamed picture;
s3: the laser point cloud analysis report in the step S1 is used for renaming related pictures by using a report analyzer and carrying out defect identification on the renamed pictures;
s4: performing manual checking on defects;
s5: generating defect-related information using a defect generator; the method specifically comprises the following steps:
s5.1: inputting a defect picture;
s5.2: extracting the information of a line, a pole tower, a part, a defect type and time in the name of the defect picture;
s5.3: comparing the defect library, searching and checking whether related defect information exists in the history defect library of the defect picture, if not, indicating that the defect is not recorded into the system, and entering S5.4; if the related defect information exists, indicating that an operation and maintenance person has recorded the defect into a production management system, recording the related information of the defect picture into a problem database, and additionally storing the defect picture, and checking by manual checking;
s5.4: comparing the working ticket libraries, searching and checking whether related defect elimination information exists in the historical working tickets of the defect pictures, if not, indicating that the defects are unprocessed, and entering S5.5; if the related defects are processed, indicating that operation and maintenance personnel have processed the related defects, recording the related information of the defect pictures to a problem database, additionally storing the defect pictures, and checking by manual inspection;
s5.5: comparing the personnel equipment libraries, extracting operation and maintenance team, personnel and team leader information of the line, and entering S5.6 if the operation and maintenance information of the line section exists; if the defect picture does not exist, recording the related information of the defect picture to a problem database, and additionally storing the defect picture, and checking by manual checking;
s5.6: comparing the defect image library, extracting a specific image of the corresponding defect type, and entering S5.7 if the defect image exists; if the defect picture does not exist, recording the related information of the defect picture to a problem database, and additionally storing the defect picture, and checking by manual checking;
s5.7: generating defect entry information, namely generating relevant information including a line name, a tower number, a component, an operation and maintenance team, operation and maintenance personnel, a line team leader, a defect type and a defect specific appearance which need to be entered into a production management system according to the steps, further generating a defect entry message, and completing a defect message generation workflow;
s6: the RPA robot is used to enter the defect message and notify the team manager.
2. The transmission line unmanned aerial vehicle inspection data processing method according to claim 1, wherein in the step S1, the process of collecting the laser point cloud analysis report is: 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 processed and generated by laser point cloud processing software and is stored in a Word document form.
3. The method for processing the inspection data of the power transmission line unmanned aerial vehicle according to claim 2, wherein in the step S2, the process of renaming the picture by the picture naming is:
inputting an original machine inspection picture;
extracting longitude, latitude, altitude and shooting time information in the machine inspection picture;
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 of a line ledger library, and taking the minimum value of all the distances from the space distance between a computer patrol picture and the ledger component; if the distance is smaller than 10 meters, the camera inspection picture shooting object is considered as a circuit component, and the camera inspection picture is matched with the circuit component in the circuit ledger library; if the distance is in the range of 10 meters to 200 meters, the machine inspection picture is considered as a channel picture of the line pole tower, and the machine inspection picture is matched with the line pole tower of the standing account in the line standing account library; if the distance is greater than 200 meters, considering that the machine inspection picture does not belong to any part in the line ledger library, and has problems, recording relevant information of the picture into a problem database, and additionally storing the picture for manual inspection and verification;
renaming pictures according to a matching result, renaming the machine patrol pictures according to a 'voltage grade_line name_pole number_component_timestamp and a' JPG 'format if the machine patrol pictures are matched with line components in a ledger, and renaming the machine patrol pictures according to a' voltage grade_line name_pole number_channel_timestamp and a 'JPG' format if the machine patrol pictures are matched with the ledger line pole;
and outputting the renaming machine inspection picture to finish the renaming workflow.
4. The method for processing inspection data of an electric power transmission line unmanned aerial vehicle according to claim 3, wherein in step S2, the process of performing defect recognition on the renamed picture is:
s2.1: inputting a machine inspection picture to be identified;
s2.2: component identification is carried out on the machine inspection picture, and the power transmission equipment component in the machine inspection picture is identified according to a Faster R-CNN power transmission equipment component identification model trained in the earlier stage;
s2.3: judging the identification result, and if the equipment component is identified, entering S2.4; if the equipment component is identified to be absent, recording the related information of the machine inspection picture to a problem database, and additionally storing the machine inspection picture, and checking by manual inspection;
s2.4: intercepting a device part in the picture, saving the picture, and entering S2.5;
s2.5: performing defect identification on the machine inspection picture, identifying the defect of the power transmission equipment in the machine inspection picture according to a fast R-CNN power transmission equipment defect identification model trained in the earlier stage, marking the defect if the defect exists in the machine inspection picture, renaming the picture according to a format of' voltage grade_line name_tower number_component_timestamp_defect type, and entering S2.6;
s2.6: and outputting the defect picture to finish the defect identification workflow.
5. The method for processing inspection data of an electric transmission line unmanned aerial vehicle according to claim 4, wherein in step S3, a laser point cloud analysis report is processed and generated by laser point cloud processing software, and stored in a Word document form, and defect information in the document needs to be analyzed and extracted, and the workflow for analyzing the laser point cloud report includes the following steps:
s3.1: inputting a laser point cloud analysis report;
s3.2: extracting defect information in a laser point cloud analysis report, summarizing a defect information table in the laser point cloud analysis report, and analyzing and extracting lines, towers and defect information of the defect information table;
s3.3: comparing the line account database, if the related lines and towers exist in the laser point cloud analysis report, extracting a corresponding defect picture in the laser point cloud analysis report, and entering S3.4; if the picture does not exist, the renamed related picture, the line, the pole tower and the defect related information are recorded into a problem database, and the machine inspection picture is additionally saved and checked by manual inspection;
s3.4: matching the extracted defect picture with related line, tower and defect information, renaming the picture according to a format of 'voltage grade_line name_tower number_component_timestamp_defect type · JPG', and entering into S3.5;
s3.5: and outputting the defect picture to finish the laser point cloud report analysis workflow.
6. The transmission line unmanned aerial vehicle inspection data processing method according to claim 5, wherein the specific process of step S4 is: and manually checking and judging the extracted defect picture, inputting the extracted defect picture into a defect generator if the extracted defect picture is correct, recording the related information of the extracted defect picture into a problem database if the extracted defect picture is incorrect, and additionally storing the extracted defect picture for manually analyzing and extracting the error reason so as to continuously perfect a system.
7. The transmission line unmanned aerial vehicle inspection data processing method according to claim 6, wherein the specific process of step S6 is:
the RPA machine operates a production system to simulate a manual defect inputting process, inputs defects into a production management system, simulates a manual message sending process, and sends the input defect information to related management staff through an internal communication tool; the production management system is an information system for unified construction of a power grid, the system does not open any API operation interface for ensuring safe operation of the system, and work order input can only be performed by providing front page operation input through the system, wherein RPA is robot flow automation Robotic Process Automation, and RPA simulates manual system operation to replace manual operation to perform repeated input and message sending work.
8. The method for processing the inspection data of the power transmission line unmanned aerial vehicle according to claim 7, wherein in the step S3, the process of renaming the related picture and performing defect recognition on the renamed picture is as follows: and the report analyzer extracts the line, the pole tower and the defect information in the report, compares the line and the pole tower with a line account library, extracts corresponding defect pictures and renames the pictures according to fixed if the related lines and the pole towers exist, records the picture related information to a problem database if the corresponding defect pictures do not exist, and additionally stores the pictures for manual checking and auditing.
9. The method for processing inspection data of unmanned aerial vehicle of transmission line according to any one of claims 1 to 8, wherein the defect generator respectively judges whether related defect information exists in the historical defect of the picture and the working ticket according to the line, the tower, the part and the defect type information in the picture, and combines the defect library and the working ticket library, if not, the defect generator searches the responsible person information and the defect type corresponding description appearance information of the related line tower according to the person equipment library and the defect appearance library, generates a defect message, sends the defect message to the RPA robot for processing, if so, does not generate the defect message, records the related information of the picture to the problem database, otherwise stores the picture, and checks and examines the picture manually.
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 CN111709361A (en) | 2020-09-25 |
| CN111709361B true 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) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| 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 |
| CN114782947B (en) * | 2022-06-22 | 2022-10-04 | 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 |
| 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 |
Citations (4)
| 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 |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10217207B2 (en) * | 2016-01-20 | 2019-02-26 | Ez3D, Llc | System and method for structural inspection and construction estimation using an unmanned aerial vehicle |
-
2020
- 2020-06-16 CN CN202010548758.4A patent/CN111709361B/en active Active
Patent Citations (4)
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111709361A (en) | 2020-09-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111709361B (en) | Method for processing inspection data of unmanned aerial vehicle of power transmission line | |
| CN111949809B (en) | Intelligent processing method for infrared inspection data of power transmission line | |
| CN111563509B (en) | Tesseract-based substation terminal row identification method and system | |
| CN108470022B (en) | Intelligent work order quality inspection method based on operation and maintenance management | |
| CN110689148A (en) | Metering equipment fault detection method based on AR technology | |
| CN112381356A (en) | Completion acceptance method, completion acceptance system, server and storage medium for engineering project | |
| CN105761016A (en) | Bridge disease inspection management system and method | |
| CN112257740B (en) | Knowledge graph-based image hidden danger identification method and system | |
| CN115395646A (en) | Intelligent operation and maintenance system of digital twin traction substation | |
| CN112598142B (en) | Wind turbine maintenance working quality inspection auxiliary method and system | |
| CN117114420A (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN116881670A (en) | Communication optical cable attachment checking method based on GIS map | |
| CN113065580A (en) | Power plant equipment management method and system based on multi-information fusion | |
| CN115858714B (en) | Unmanned aerial vehicle collected GIS data automatic modeling management system and method | |
| CN110807415A (en) | Traffic checkpoint vehicle intelligent retrieval system and method based on annual inspection marks | |
| CN115658772A (en) | Unmanned aerial vehicle photovoltaic inspection data asset management method and system | |
| CN115880803A (en) | Intelligent inspection system and method | |
| CN115345163A (en) | Outfield quality analysis method and system based on fault data | |
| CN113034021A (en) | Power transmission line defect analysis method and system based on machine patrol data | |
| CN113688987A (en) | Training method of photovoltaic monitoring model, monitoring method of photovoltaic equipment and equipment | |
| CN110826473A (en) | Neural network-based automatic insulator image identification method | |
| CN110703183A (en) | Intelligent electric energy meter fault data analysis method and system | |
| CN112801432B (en) | Intelligent inspection system for fan set blades and inspection method for fan set blades | |
| CN113573169B (en) | Unmanned aerial vehicle distribution box data reading and detecting method and system | |
| CN114548926B (en) | Rapid collection method for phenotypic characters of wheat breeding material based on machine vision |
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 |