CN111949809B - Intelligent processing method for infrared inspection data of power transmission line - Google Patents
Intelligent processing method for infrared inspection data of power transmission line Download PDFInfo
- Publication number
- CN111949809B CN111949809B CN202010684426.9A CN202010684426A CN111949809B CN 111949809 B CN111949809 B CN 111949809B CN 202010684426 A CN202010684426 A CN 202010684426A CN 111949809 B CN111949809 B CN 111949809B
- Authority
- CN
- China
- Prior art keywords
- picture
- defect
- ground wire
- area
- temperature
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 74
- 238000007689 inspection Methods 0.000 title claims abstract description 42
- 238000003672 processing method Methods 0.000 title claims abstract description 22
- 230000007547 defect Effects 0.000 claims abstract description 274
- 238000012545 processing Methods 0.000 claims abstract description 20
- 238000001514 detection method Methods 0.000 claims abstract description 18
- 238000004458 analytical method Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims description 47
- 239000012212 insulator Substances 0.000 claims description 30
- 238000012423 maintenance Methods 0.000 claims description 28
- 239000002131 composite material Substances 0.000 claims description 27
- 238000013519 translation Methods 0.000 claims description 18
- 239000011159 matrix material Substances 0.000 claims description 16
- 238000012546 transfer Methods 0.000 claims description 16
- 239000000725 suspension Substances 0.000 claims description 8
- 238000000605 extraction Methods 0.000 claims description 7
- 101100129500 Caenorhabditis elegans max-2 gene Proteins 0.000 claims description 4
- 101100438010 Arabidopsis thaliana BZIP11 gene Proteins 0.000 claims description 3
- 101000887307 Arabidopsis thaliana Short-chain dehydrogenase reductase ATA1 Proteins 0.000 claims description 3
- 101000713305 Homo sapiens Sodium-coupled neutral amino acid transporter 1 Proteins 0.000 claims description 3
- 101000640813 Homo sapiens Sodium-coupled neutral amino acid transporter 2 Proteins 0.000 claims description 3
- 101100424621 Schizosaccharomyces pombe (strain 972 / ATCC 24843) tub1 gene Proteins 0.000 claims description 3
- 102100036916 Sodium-coupled neutral amino acid transporter 1 Human genes 0.000 claims description 3
- 102100033774 Sodium-coupled neutral amino acid transporter 2 Human genes 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 3
- 238000003379 elimination reaction Methods 0.000 claims description 3
- 230000005484 gravity Effects 0.000 claims description 3
- 230000005855 radiation Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 2
- 239000000463 material Substances 0.000 abstract description 6
- 238000010438 heat treatment Methods 0.000 description 33
- 238000009529 body temperature measurement Methods 0.000 description 6
- WABPQHHGFIMREM-UHFFFAOYSA-N lead(0) Chemical compound [Pb] WABPQHHGFIMREM-UHFFFAOYSA-N 0.000 description 6
- 238000013527 convolutional neural network Methods 0.000 description 5
- 238000004519 manufacturing process Methods 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 101100083446 Danio rerio plekhh1 gene Proteins 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 101100074336 Xenopus laevis ripply2.1 gene Proteins 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000004801 process automation Methods 0.000 description 2
- 210000000709 aorta Anatomy 0.000 description 1
- 230000033228 biological regulation Effects 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000007557 optical granulometry Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 238000004861 thermometry Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/53—Querying
- G06F16/532—Query formulation, e.g. graphical querying
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
- G06V10/751—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Physics (AREA)
- Economics (AREA)
- Databases & Information Systems (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- General Business, Economics & Management (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Computational Linguistics (AREA)
- Multimedia (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Medical Informatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention relates to an intelligent processing method of infrared inspection data of a power transmission line, which comprises the following steps: s1: inputting an infrared inspection picture; s2: renaming the input picture; s3: carrying out component identification and area temperature detection analysis on the renamed picture; s4: manually checking defects; s5: generating defect information using a defect generator; s6: and (5) recording the defects by using the RPA robot and informing a team manager. The infrared inspection photo is automatically analyzed, whether the related components generate heat or not is detected, and the defects are automatically recorded into the system, so that a large amount of manpower and material resources can be saved, the workload of personnel is reduced, the working time is shortened, and the working efficiency is improved; the pertinence and the accuracy of intelligent processing of the infrared inspection data of the power transmission line are improved through renaming; the invention can effectively increase the efficiency of processing the infrared inspection data of the power transmission line.
Description
Technical Field
The invention relates to the field of operation and inspection of high-voltage transmission lines, in particular to an intelligent processing method for infrared inspection data of a transmission line.
Background
In recent years, the demand for power supply has increased year by year with economic development, and it is needless to say that a high-voltage power transmission line is an aorta for ensuring stable operation of a power grid. However, most of high-voltage transmission lines operate outdoors, are influenced by high-temperature severe weather, high-voltage operation conditions and the like all the year round, and are prone to causing heating defects of transmission equipment due to hidden component hazards caused by reasons such as artificial construction non-standardization and the like, so that safe and stable operation of the lines is endangered. In order to ensure the safety of the high-voltage transmission line, a strict operation and maintenance measure is made by a transmission line operation and maintenance unit, and the transmission line needs to be subjected to regular infrared temperature measurement. The infrared temperature measurement of the existing power transmission line is mainly carried out by an unmanned aerial vehicle, namely, the unmanned aerial vehicle carrying an infrared camera is used for carrying out the infrared temperature measurement of power transmission equipment and polling, and the heating defect of the equipment is searched. However, no matter the unmanned aerial vehicle infrared temperature measurement inspection operation or the manual handheld infrared temperature measurement operation of the infrared imager, a large number of infrared photos are collected, the existing infrared photos are mainly checked manually, measurement and analysis are carried out, renaming is carried out, the hidden defect danger is recorded into a company system, and the hidden defect danger flow is opened. The manual processing method has the following problems: 1. the workload is huge, and a large amount of manpower and material resources are wasted. According to statistics, more than one hundred thousand unmanned aerial vehicle infrared inspection photos acquired every year by a local city operation and maintenance unit responsible for managing five thousand kilometers of power transmission lines are counted, the traditional method needs manual renaming and filing, then temperature analysis software is used for detection and analysis, and heating defects are recorded into a company system, so that the workload of operation and maintenance personnel is huge, and in order to ensure the accuracy and reliability of information processing, special responsible personnel and line operation and maintenance personnel are often required to repeatedly communicate and verify the heating defect information, the repeated verification work occupies the time of the operation and maintenance personnel, causes unnecessary work burden, and wastes a large amount of manpower and material resources; 2. the time consumption is too long, the efficiency is low, the heating defect of the line cannot be timely processed, and the safe and stable operation of the line is ensured. The manual processing of the inspection data not only has large workload, but also has complex operation and long time consumption. The operation of manually detecting and analyzing the infrared picture by using temperature analysis software is complicated, mo Gong hours are consumed each year, and the heating defect cannot be found in time due to overlong processing time, so that the defect rectification of the power transmission line is influenced, and the safe and stable operation of the line cannot be ensured; 3. the system is easy to make mistakes and omit, so that defects exist, and the system is not actually recorded and rectified. The method for detecting and analyzing the infrared picture by manually utilizing the temperature analysis software is relatively complex, the fine heating defects of the composite insulator and other parts are difficult to find, and in addition, the quality of operation and maintenance personnel is uneven, and the infrared defect analysis is not well known by some personnel, so that the heating defects of the line are easy to find and incomplete to record. According to hundreds of heating defects counted every year, the manual treatment miss-leak is approximately 20% approximately, and the safe and stable operation of the line is influenced.
A method for intelligently diagnosing defects of a high-voltage transmission line based on infrared images is provided by Shanghai university Han Jun and the like, and mainly diagnoses heating defects through two steps, namely, a component in the line is identified through line object sensing clustering in the first step, and whether the component has the heating defects is diagnosed through a relative temperature difference method for the identified line component in the second step. Although the method can achieve the effects of automatically detecting the infrared image of the power transmission line and analyzing the heating defect to a certain extent, the following three problems still exist. 1. The recognition result is not accurate, and the error and the omission are easy to occur. Because there are many objects in the infrared image of the field operation, the method for identifying the line component based on line object perception clustering easily causes the condition of wrong component classification or missing of the component, even if the heating defect is diagnosed by correctly classifying and adopting a relative temperature difference method, the diagnosis result is also inaccurate, because the whole temperature of some heating components is higher, if the relative temperature difference is adopted, the heating defect is easily misjudged to be absent, and further the heating defect is missed. 2. The temperature extraction method is not suitable for partial infrared thermometry images, such as infrared images shot by an infrared thermal imager of the company fel FLIR, and cannot directly read the temperature value in the images, so that the method has no universality. 3. The method still needs manual processing of defects, and the detected defects still need manual entry into a company system, so the automation level of the method is not high enough.
Disclosure of Invention
The invention provides an intelligent processing method for infrared inspection data of a power transmission line, aiming at overcoming the defect that the infrared inspection efficiency of the power transmission line in the prior art is not high enough.
The method comprises the following steps:
s1: inputting the infrared inspection picture of the daily operation and maintenance power transmission line into the system;
s2: renaming the input picture by using a picture naming device;
s3: carrying out component identification and area temperature detection analysis on the renamed picture: according to the AI component identification and temperature detection working flow, sequentially carrying out component identification, region temperature detection, defect judgment and marking on the renamed picture, renaming the picture according to the identified defect type and grade, and finally outputting a defect picture;
s4: and (3) manually checking defects: manually checking and judging a defect identification result, inputting the picture into a defect generator if the identification is correct, recording picture related information into a problem database if the identification is wrong or the temperature detection is wrong, and storing the picture in addition for manually analyzing and identifying the error reason so as to continuously perfect the system;
s5: generating defect information using a defect generator: the defect generator respectively judges whether the historical defect and the working ticket have related defect information after the picture time according to the line, the tower, the component and the defect type in the picture and by combining a defect library and a working ticket library, if the historical defect and the working ticket have the related defect information, the responsible personnel information of the related line tower and the corresponding description representation information of the defect type are searched according to a personnel equipment library and a defect representation library, a defect message is generated and sent to an RPA (resilient Process Automation) robot for processing, if the responsible personnel information and the defect representation library have the defect information, the defect message is not generated, the related information of the picture is recorded into a problem database, the picture is additionally stored and is manually checked;
s6: and (5) recording the defects by using the RPA robot and informing a team manager.
According to the invention, the pertinence and the accuracy of intelligent processing of the infrared routing inspection data of the power transmission line are improved through renaming, the image processing time is reduced, and the routing inspection efficiency is improved. The defects are uniformly identified and detected through AI component identification and defect generators, the accuracy of heating defect identification and the normalization of processing are guaranteed, the method is more objective and comprehensive compared with the traditional infrared inspection data method of the power transmission line, the error rate and the leakage rate are lower than the existing intelligent diagnosis error rate and leakage rate of infrared images, and the method has higher identification efficiency.
Preferably, S2 comprises the steps of:
s2.1: extracting longitude, latitude, height and shooting time information in the picture;
s2.2: the longitude, latitude and altitude information of the components such as the A phase, the B phase, the C phase, the ground wire, the foundation and the like of the line in the line ledger library is extracted in a circulating manner;
calculating the space distance between the infrared picture and the machine account extracting component, and taking the minimum value in all the distances; if the distance is less than 10 meters, the infrared picture shooting object is considered as the line component, and the infrared picture is matched with the ledger line component; if the distance is within the range of 10-200 m, the infrared picture is considered as the whole picture of the line pole tower, and the infrared picture is matched with the account line pole tower; if the distance is more than 200 meters, the picture is not considered to belong to any return account line, a problem exists, picture related information is recorded into a problem database, the picture is additionally stored, and the picture is checked and audited manually;
s2.3: renaming the picture according to the matching result;
s2.4: and outputting the renaming infrared picture to finish the renaming work flow.
Preferably, the renaming rule in S2.3 is: and if the infrared picture is matched with the line component in the standing book, renaming the infrared picture according to the voltage level _ line name _ pole tower number _ component _ timestamp in the JPG format, and if the infrared picture is matched with the line tower of the standing book, renaming the infrared picture according to the voltage level _ line name _ pole tower number _ full tower _ timestamp in the JPG format.
Preferably, S3 comprises the steps of:
s3.1: inputting an infrared picture to be identified;
s3.2: carrying out component identification on the picture: establishing and training a power transmission equipment component identification model of the Faster R-CNN, and identifying the power transmission equipment component in the picture by using the power transmission equipment component identification model of the Faster R-CNN;
wherein the power transmission equipment component comprises: the lightning arrester comprises a composite insulator, a lightning arrester, a ground wire hardware fitting and a wire hardware fitting;
the ground wire hardware comprises a suspension wire clamp, a strain clamp splicing hardware, a connecting hardware and the like, and the wire hardware comprises a suspension wire clamp, a strain clamp, a splicing hardware and a connecting hardware;
s3.3: judging the recognition result, and if the device component is recognized to exist, inputting the picture into S3.4; if the equipment component does not exist, recording the relevant information of the picture into a problem database, and storing the picture in addition for manual inspection and verification;
s3.4: acquiring the position of a device component in a picture, extracting parameter information of the infrared picture, and calculating the temperature of each point in the picture to form a temperature matrix;
for the composite insulator and the lightning arrester obtained through identification, averagely dividing the composite insulator and the lightning arrester into three regions according to the obtained positions of the components, analyzing the temperature of all pixel points in each region, respectively extracting the highest temperature, and entering S3.6;
for the recognized ground wire hardware, according to a method for acquiring the position of the ground wire according to the spatial position relationship, judging and acquiring the position of a ground wire area through the translation of the area position of the ground wire hardware and the infrared image characteristics, and entering S3.5;
for the identified wire hardware fitting, according to a method for acquiring the position of the ground wire according to the spatial position relationship, judging and acquiring the position of the wire area through the translation of the position of the wire hardware fitting area and the infrared image characteristics, and entering S3.5;
s3.5: judging whether the obtained ground wire area is accurate or not, judging and determining whether the ground wire area is the ground wire area or not according to the infrared image characteristics of the ground wire area, if the obtained ground wire area is accurate, automatically analyzing the temperature of all points in the obtained component position area, extracting the highest temperature, simultaneously extracting the highest temperature in the ground wire area near the component area, and entering S3.6; if the situation that the ground wire area does not exist is judged, recording relevant picture information into a problem database, and storing the picture in addition and checking the picture manually;
s3.6: analyzing the extracted temperature, and judging whether the defect exists or not and the defect grade according to the defect grading standard;
s3.7: and outputting a defect picture to finish defect identification.
Preferably, S3.2 is in particular:
adopting an Faster R-CNN power transmission equipment component identification model, inputting an original infrared picture, marking the component category and the component label if a power transmission equipment component exists through identification by taking a pixel point at the upper left corner of the picture as an origin of coordinates, taking the pixel point at the right horizontal side as an X axis and taking the pixel point at the lower vertical side as a Y axis, and marking the coordinates (X) at the upper left corner of a component marking frame 1 ,y 1 ) And the coordinates (x) of the lower right corner of the part label box 2 ,y 2 ) If no recognition result is present, the part tag is written as 0.
Preferably, S3.4 is in particular:
obtaining a position [ x ] of a device component in a picture 1 ,y 1 ,x 2 ,y 2 ]And extracting parameter information of the infrared picture, wherein the parameters comprise: 16-bit RAW original value, radiation coefficient E, camera distance OD, atmospheric temperature AT, reflector surface temperature RT, refractor surface temperature IT, refractive index IRT, relative humidity RH, planck R1 constant PR1, planck B constant PB, planck F constant PF, planck shift constant PO, planck R2 constant PR2; calculating the temperature of each pixel point in the picture according to formulas (1) to (9) to form a temperature matrix;
if the pixel of the infrared picture is m x n, the temperature matrix is
Formula (1):
formula (2):
formula (3):
formula (4):
formula (5):
formula (6):
formula (7):
formula (8):
formula (9):
wherein RAW is the original value of 16 bits RAW;
ATA1 is an atmospheric heat transfer constant and is used for calculating the influence of humidity on transmission;
ATA2 is an atmospheric heat transfer constant which is used for calculating the influence of humidity on transmission;
ATB1 is an atmospheric heat transfer constant and is used for calculating the influence of humidity on transmission;
ATB2 is an atmospheric heat transfer constant used for calculating the influence of humidity on transmission;
ATX is an atmospheric heat transfer constant used for calculating the influence of humidity on transmission;
for the identified composite insulator and arrester, the composite insulator and arrester are divided into three areas according to the acquired component positions, namely, the positions [ x ] of the composite insulator and arrester 1 ,y 1 ,x 2 ,y 2 ]Judgment of x 2 -x 1 And y 2 -y 1 Size if y 2 -y 1 ≥x 2 -x 1 Then, the following three regions are divided
If y 2 -y 1 <x 2 -x 1 Then, the following three regions are divided
Analyzing the temperature of all pixel points in each region, and respectively extracting the highest temperature, namely analyzing the temperature matrix of the m x n pixel infrared picture
Highest temperature value (T) in the middle corresponding region max1 ,T max2 ,T max3 ) Entering S3.6;
for the ground wire hardware obtained by identification, according to the method for obtaining the position of the ground wire according to the spatial position relationship, the position of the ground wire area is judged and obtained through the translation of the area position of the ground wire hardware and the infrared image characteristics, namely the position [ x ] of the ground wire hardware is obtained 1 ,y 1 ,x 2 ,y 2 ]Obtaining the ground area [2x ] by area position translation 2 -x 1 ,y 1 ,3x 2 -2x 1 ,y 2 ]Or [3x ] 1 -2x 2 ,y 1 ,2x 1 -x 2 ,y 2 ]Entering S3.5;
for the identified wire hardware fitting, according to the method for acquiring the position of the ground wire in the space position relationship, the position of the wire area is judged and acquired through the translation of the area position of the wire hardware fitting and the infrared image characteristic, namely the position [ x ] of the wire hardware fitting 1 ,y 1 ,x 2 ,y 2 ]Obtaining ground area [2x ] by area position translation 2 -x 1 ,y 1 ,3x 2 -2x 1 ,y 2 ]Or [3x 1 -2x 2 ,y 1 ,2x 1 -x 2 ,y 2 ]Proceed to S3.5.
Preferably, S3.5 is in particular:
and judging whether the obtained ground wire area is accurate or not, and judging and determining whether the ground wire area is the ground wire area or not according to the infrared image characteristics of the ground wire area.
And judging the ground wire area, namely making a matching template, generating a model and matching the model with a target image.
Wherein generating the model comprises the steps of:
(1) Acquiring a template image, carrying out canny edge extraction on the template image, and extracting boundary points of the template image;
(2) Respectively solving the gradient of each point of the template image in the x direction and the gradient of each point in the y direction by using a sobel operator;
(3) According to the x and y gradient combination and the position information of the boundary points, the gradient direction and the gradient magnitude of each boundary are obtained;
(4) Calculating the gravity centers (X, Y) of the edge points of the template;
matching the target image with the model includes the steps of:
step 1: extracting canny edges of the areas to be matched of the ground wires to obtain boundary point information of the images to be matched;
step 2: respectively solving the gradient of each point in the image to be matched in the x direction and the gradient of each point in the image to be matched in the y direction by using a sobel operator (a Sobel operator);
and 3, step 3: sliding window matching search, locating the template inCalculating matching scores from left to right on the image to be matched and from top to bottom in sequence, respectively calculating the cosine value a of the included angle between each point on the template boundary point and the direction vector of the corresponding image point to be matched on the corresponding matching area on the assumption that the total number of the edge points of the template image is N 1 ，a 2 ， a 3 ，…，a n The matching score can be recorded as
If p is larger than or equal to a preset threshold value, the obtained ground lead area is judged to be accurate, then the temperature of all points in the obtained component position area is automatically analyzed, the highest temperature is extracted, the highest temperature in the ground lead area near the component area is extracted at the same time, and the m-n pixel infrared image temperature matrix is analyzed
Middle corresponding ground wire fitting and highest temperature value (T) in ground wire area j ,T x ) Entering S3.6; if the p is smaller than the preset threshold value, judging that no ground wire area exists, recording the relevant information of the picture to a problem database, storing the picture in addition, and checking and verifying manually.
Preferably, S3.6 is in particular:
analyzing the highest temperature difference in the three areas for the composite insulator and the lightning arrester, and judging other defects if the temperature difference is between 0.5 and 1 ℃; if the temperature difference is between 1 and 3 ℃, judging as a common defect; if the temperature difference is between 3 and 5 ℃, judging the defect as a major defect; if the temperature difference is more than 5 ℃, judging as a major defect;
for a ground wire hardware fitting, calculating the difference value and the relative temperature difference between the highest temperature in the ground wire hardware fitting area and the highest temperature in the ground wire area, analyzing the difference value and the relative temperature difference between the highest temperature of the ground wire hardware fitting and the highest temperature in the ground wire area, and judging as a common defect if the temperature difference value is between 5 and 15 ℃ or the relative temperature difference is between 35 and 80 percent;
if the highest temperature of the ground wire hardware area reaches 90-130 ℃, or the difference value between the highest temperature of the ground wire hardware area and the highest temperature of the ground wire area is 15-40 ℃, or the relative temperature difference is 80-95%, judging as a major defect;
if the highest temperature of the ground wire hardware fitting region reaches more than 130 ℃, or the difference between the highest temperature of the ground wire hardware fitting region and the highest temperature of the ground wire region is larger than 40 ℃, or the relative temperature difference is larger than 95%, judging as an emergency defect;
for the wire hardware fitting, calculating the difference value and the relative temperature difference between the highest temperature in the wire hardware fitting area and the highest temperature in the wire area, analyzing the difference value and the relative temperature difference between the highest temperature of the wire hardware fitting and the highest temperature in the wire area, and judging as a common defect if the temperature difference value is between 5 and 15 ℃ or the relative temperature difference is between 35 and 80 percent;
if the highest temperature of the wire hardware area reaches 90-130 ℃, or the difference value between the highest temperature of the wire hardware area and the highest temperature of the wire area is 15-40 ℃, or the relative temperature difference is 80-95%, judging as a major defect;
if the highest temperature of the wire hardware area reaches more than 130 ℃, or the difference value of the highest temperature of the wire hardware area and the highest temperature of the ground wire area is more than 40 ℃, or the relative temperature difference is more than 95%, judging as an emergency defect;
if the picture has defects, marking the defect type and the defect grade, renaming the picture according to the format of voltage grade, line name, pole tower number, component, time stamp, defect type, defect grade and JPG, and entering S3.7.
Preferably, the specific formula of the relative temperature difference is as follows:
wherein, T j Maximum temperature of component region, T x The highest temperature of the adjacent wire/ground area.
Preferably, S5 is specifically:
s5.1: inputting a defect picture;
s5.2: extracting information of lines, towers, components, defect types, defect grades and time in the names of the defect pictures;
s5.3: comparing the defect library, searching and checking whether the historical defect library has related defect information after the picture time, if not, indicating that the defect is not recorded into the system, and entering S5.4; if the relevant defect information exists, the operation and maintenance personnel are indicated to 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;
s5.4; comparing the work ticket library, searching and checking whether the historical work tickets have related defect elimination information after the picture time, if not, indicating that the defects are not processed, and entering S5.5; 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;
s5.5: comparing the personnel equipment base, extracting the operation and maintenance team, personnel and team leader information of the corresponding line, and entering S5.6 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;
s5.6: comparing the defect representation library, extracting specific representations of corresponding defect types, and entering S5.7 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;
s5.7: and generating defect input information, further generating defect input information and finishing the generation of the defect information.
The input information comprises line names, tower numbers, components, operation and maintenance teams, operation and maintenance personnel, line team leaders, defect types, defect grades and defect specific representation information.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that: the invention automatically analyzes the infrared inspection photo, detects whether the related parts generate heat or not, and automatically records the defects into the system, thereby saving a large amount of manpower and material resources, reducing the workload of personnel, shortening the working time and improving the inspection efficiency. The pertinence and the accuracy of intelligent processing of the infrared inspection data of the power transmission line are improved through renaming, the image processing time is shortened, and the inspection efficiency is improved. The defects are identified and detected through AI component identification and defect generator unification, the accuracy of heating defect identification and the normalization of processing are guaranteed, compared with the traditional infrared inspection data method of the power transmission line, the method is more objective and comprehensive, the error rate and the leakage rate are lower than those of the existing infrared image intelligent diagnosis, the infrared pictures can be better guaranteed to be processed according to requirements, and the heating defects of the line can be timely and comprehensively discovered and recorded.
Drawings
Fig. 1 is a flowchart of an intelligent processing method for infrared inspection data of a power transmission line according to embodiment 1.
Fig. 2 is a diagram of a picture renaming flow.
FIG. 3 is a flow chart of component identification and zone temperature detection analysis.
Fig. 4 is a defect generation flow chart.
Fig. 5 is a graph of temperature lift analysis of a composite insulator region.
Fig. 6 is a temperature extraction analysis diagram of the ground wire fitting region.
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 present 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.
Example 1
The embodiment provides an intelligent processing method for infrared inspection data of a power transmission line, as shown in fig. 1, the method comprises the following steps:
s1: and inputting an original infrared picture.
Inputting an infrared inspection picture (namely an inspection photo) of the daily operation and maintenance power transmission line into a system;
s2: renaming pictures using a picture name.
And the picture naming device calculates the distance between the picture naming device and the relevant line, tower and part longitude, latitude and height information in the line ledger library according to the information of the longitude, the latitude, the height, the shooting time and the like of the picture, matches the distance according to the distance, and renames the picture according to a fixed format.
S3: and carrying out component identification and area temperature detection analysis on the renamed picture.
And according to the AI component identification and temperature detection working flow, sequentially carrying out component identification, region temperature detection, defect judgment and marking on the renamed picture, renaming the picture according to the identified defect type and grade, and finally outputting the defect picture.
S4: and (5) manually checking defects.
And manually checking and judging a defect identification result, inputting the picture into a defect generator if the identification is correct, recording picture related information into a problem database if the identification or the temperature detection is wrong, and storing the picture for manual analysis and identification of error reasons so as to continuously perfect the system.
S5: defect-related information is generated using a defect generator.
And the defect generator respectively judges whether the historical defects and the working tickets have related defect information after the photo time by combining the defect library and the working ticket library according to the information of the lines, the towers, the components, the defect types, the grades and the like in the pictures, if not, the responsible personnel information and the corresponding description representation information of the defect types of the related lines and towers are searched according to the personnel equipment library and the defect representation library, a defect message is generated and sent to the RPA robot for processing, if so, the defect message is not generated, the related information of the pictures is recorded in a problem database, the pictures are additionally stored, and the pictures are checked and audited manually.
S6: and (5) recording the defects by using the RPA robot and informing a team manager.
And operating the production system by the RPA machine to simulate a manual defect recording process, recording the defects into the production management system, simulating a manual message sending process, and sending the recorded defect information to related management personnel through an internal communication tool.
The production management system is an information system uniformly built for a power grid, and the system does not open any API operation interface for the consideration of ensuring the safe operation of the system, so that the work order can be input only by providing front-end page operation input through the system.
The RPA is a robot Process Automation, and can simulate manual system operation to replace manual work for repeated input and message sending.
As shown in fig. 2, S2 includes the following steps:
s2.1: extracting and inputting information such as longitude, latitude, height, shooting time and the like in an original infrared picture;
s2.2: and circularly extracting longitude, latitude and height information of components such as a line A phase, a line B phase, a line C phase, a ground wire, a foundation and the like in the line standing book library, calculating the spatial distance between the infrared picture and the extracted standing book component, and taking the minimum value in all the distances.
If the distance is less than 10 meters, the infrared picture shooting object is considered as the line component, and the infrared picture is matched with the account line component; and if the distance is within the range of 10-200 meters, the infrared picture is regarded as the whole picture of the line tower, and the infrared picture is matched with the ledger line tower.
If the distance is greater than 200 meters, the picture is not considered to belong to any account return line, a problem exists, relevant information of the picture is recorded into a problem database, the picture is additionally stored, and the picture is checked and examined manually.
S2.3: renaming the picture according to the matching result, if the infrared picture is matched with the line component in the standing book, renaming the infrared picture according to a voltage level _ line name _ pole tower number _ component _ timestamp in a JPG format, and if the infrared picture is matched with the line tower of the standing book, renaming the infrared picture according to a voltage level _ line name _ pole tower number _ full tower _ timestamp in a JPG format;
s2.4: and outputting the renaming infrared picture to finish the renaming work flow.
The AI component identification and temperature detection workflow.
The heating defects of the power transmission equipment are mainly concentrated on three types of parts, namely heating defects of insulator bodies such as a composite insulator or a lightning arrester; 2. the ground wire hardware such as a suspension clamp, a strain clamp and the like has heating defects; 3. and the hardware of the lead has the defects of heating, such as suspension clamps, strain clamps, splicing hardware and the like.
The heating defects of the first insulator type are mainly detected through three steps, and firstly, the insulator components in the infrared images are identified based on a deep learning technology. For component identification, considering that a natural background of an infrared picture is simple relative to a visible light image and a heating part of power transmission equipment is relatively fixed, a component identification model based on the infrared picture is trained, typical components which are easy to heat, such as a composite insulator, a lightning arrester, a ground wire hardware fitting and a wire hardware fitting, in the original infrared picture are identified, and the position of the composite insulator or the lightning arrester component area is obtained. 2. And carrying out temperature detection, calculating the temperature of the infrared image, and extracting the highest temperature of the designated area. Due to the fact that the temperature values in the images cannot be directly extracted from partial infrared images due to different technologies, a method for calculating the image temperature based on infrared image parameters is designed, parameter information of the infrared images is extracted, the temperature of each point in the images is calculated by using a formula, a temperature matrix is formed, then the composite insulator or the lightning arrester identified in the first step is averagely divided into three areas, the highest temperature in each area is further extracted, and the specific area division is shown in a composite insulator sub-area temperature extraction analysis diagram in fig. 5. 3. And judging the defects according to the defect grading standard. In order to accurately detect the defects, detailed comparison is carried out according to the specification in the defect grading standard, the highest temperature difference in the main three areas is judged as other defects if the temperature difference is between 0.5 and 1 ℃; if the temperature difference is between 1 and 3 ℃, judging as a common defect; if the temperature difference is between 3 and 5 ℃, judging the defect as a major defect; and if the temperature difference is more than 5 ℃, judging as a major defect.
The heating defects of the second and third types of ground wires and the conducting wire hardware are mainly detected through four steps, and firstly, the power transmission component which is easy to heat in the infrared image is identified based on the deep learning technology. And similarly, identifying typical components which are easy to heat, such as a composite insulator, a lightning arrester, a ground wire hardware fitting, a wire hardware fitting and the like in the original infrared picture based on the component identification model of the infrared picture to obtain the regional positions of the components, such as the ground wire hardware fitting, the wire hardware fitting and the like. 2. The position of the ground or conductor near the component is determined. In order to detect the heat generation defect more accurately, the temperature of the ground wire or the lead wire near the power transmission component must be acquired for analysis and comparison. However, the ground wire and the lead wire are too simple in characteristics to accurately detect a specific position directly by image recognition. The method comprises the steps of obtaining the position of a part area obtained in the first step in a translation mode towards one side direction of the part to obtain the area position of a lead wire or a ground wire, judging whether the part area is the lead wire area according to the image characteristics of the area, if so, determining the lead wire area, if not, in the translation mode towards the other direction to judge the lead wire area, and if not, recording related information of a picture into a question database, storing the picture additionally, and checking manually. The specific ground wire area determination is shown in the temperature extraction analysis chart of the ground wire hardware area in fig. 6. 3. And carrying out temperature detection, calculating the temperature of the infrared image, and extracting the highest temperature of the specified area. Like the second step method of the first kind of defects, the temperature of each point in the picture is calculated by using a formula through extracting parameter information of the infrared picture to form a temperature matrix, and then the highest temperature of the component area and the ground wire area can be extracted through analysis. 4. And judging the defects according to the defect grading standard. For the ground wire hardware, in order to accurately detect defects, detailed comparison is performed according to the regulations in the defect grading standard, and three items are mainly compared: (1) component area maximum temperature; (2) The difference value of the highest temperature of the component area and the highest temperature of the ground wire area is obtained; (3) The highest temperature of the component area is different from the highest temperature of the ground wire area. If one of the three items reaches the corresponding numerical value in the defect grading standard, judging that the defect is in the corresponding grade.
As shown in fig. 3, S3 includes the steps of:
s3.1: and inputting an infrared picture to be identified.
S3.2: and identifying components of the picture, 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, and mainly identifying four types of components, namely a composite insulator, a lightning arrester, a ground wire fitting and a wire fitting. The ground wire hardware fitting comprises a suspension wire clamp, a strain clamp splicing hardware fitting, a connecting hardware fitting and the like, and the wire hardware fitting comprises a suspension wire clamp, a strain clamp, a splicing hardware fitting, a connecting hardware fitting and the like.
For image recognition, an image recognition model based on a deep convolutional neural network technology is adopted, an original infrared picture is input, pixel points at the upper left corner of the picture are taken as coordinate origin points, the horizontal direction is taken as the right axis, the vertical direction is taken as the downward axis, through recognition, if the part exists, specific part types and position labels, namely a type label b and coordinates (X) at the upper left corner of a part labeling frame can be returned 1 ,y 1 ) And the coordinates of the lower right corner of the part (x) 2 ,y 2 ) If the recognition result is not present, the part tag b is marked as 0.
S3.3: judging the identification result, if the part label b is not equal to 0, identifying that the equipment part exists, and inputting the picture into S3.4; if the part tag b is equal to 0, identifying that no equipment part exists, recording the relevant picture information into a problem database, and storing the picture in addition for manual checking and checking.
S3.4: obtaining a position [ x ] of a device component in a picture 1 ,y 1 ,x 2 ,y 2 ]And extracting parameter information of the infrared picture, wherein the parameters comprise a ' 16-bit RAW original value ', ' radiation coefficient E ', ' camera distance OD ', ' atmospheric temperature AT ', ' reflector surface temperature RT ', ' refractor surface temperature IT ', ' refractive index IRT ', ' relative humidity RH ', ' Planck R1 constant PR1', ' Planck B constant PB ', ' Planck F constant PF ', ' Planck shift constant PO ', ' Planck R2 constant PR2', and the like, calculating the temperature of each pixel point in the picture according to the formulas (1) to (9), forming a temperature matrix, and if the infrared picture of m × n pixels is the infrared picture of m × n pixels, the temperature matrix is the PR2' and the like
Formula (1):
formula (2):
formula (3):
formula (4):
formula (5):
formula (6):
formula (7):
formula (8):
formula (9):
wherein raw: 16-bit RAW original value;
e: the emissivity coefficient;
OD: a camera distance;
AT: the temperature of the atmosphere;
RT: reflector surface temperature;
IT: the surface temperature of the refractile;
IRT: a refractive index;
RH: relative humidity;
PR1: planck R1 constant;
PB: planck B constant;
PF: planck F constant;
PO: planck's offset constant;
PR2: planck R2 constant.
The above are all infrared picture acquisition parameters.
ATA1: the atmospheric heat transfer constant alpha 1 is used for calculating the influence of humidity on transmission, and 0.006569 is taken;
ATA2: the atmospheric heat transfer constant alpha 2 is used for calculating the influence of humidity on transmission, and 0.012620 is taken;
ATB1: the atmospheric heat transfer constant beta 1 is used for calculating the influence of humidity on transmission, and is-0.002276;
ATB2: the atmospheric heat transfer constant beta 2 is used for calculating the influence of humidity on transmission, and is-0.006670;
ATX: the atmospheric heat transfer constant, X, used to calculate the effect of humidity on transfer, was taken as 1.900000.
For the identified composite insulator and lightning arrester, the composite insulator and lightning arrester are averagely divided into three areas according to the obtained component positions, namely the positions [ x ] of the composite insulator and the lightning arrester 1 ,y 1 ,x 2 ,y 2 ]Judgment of x 2 -x 1 And y 2 -y 1 Size if y 2 -y 1 ≥x 2 -x 1 Then, the following three regions are divided
If y 2 -y 1 <x 2 -x 1 Then, the following three regions are divided
Analyzing the temperature of all pixel points in each region, and respectively extracting the highest temperature, namely analyzing the temperature matrix of the m x n pixel infrared picture
Highest temperature value (T) in the middle corresponding region max1 ,T max2 ,T max3 ) Entering S3.6; for the ground wire hardware obtained by identification, according to the method for acquiring the position of the ground wire in the spatial position relationship, the position of the ground wire area is judged and acquired through the translation of the area position of the ground wire hardware and the infrared image characteristic, namely the position [ x ] of the ground wire hardware is acquired 1 ,y 1 ,x 2 ,y 2 ]Obtaining a ground area [2x ] by area position translation 2 -x 1 ,y 1 ,3x 2 -2x 1 ,y 2 ]Or [3x 1 -2x 2 ,y 1 ,2x 1 -x 2 ,y 2 ]Entering S3.5; for the identified wire hardware fitting, according to the method for acquiring the position of the ground wire according to the spatial position relationship, the regional position of the wire is judged and acquired through regional position translation and infrared image characteristics of the wire hardware fitting, namely according to the position [ x ] of the wire hardware fitting 1 ,y 1 ,x 2 ,y 2 ]Obtaining ground area [2x ] by area position translation 2 -x 1 ,y 1 ,3x 2 -2x 1 ,y 2 ]Or [3x ] 1 -2x 2 ,y 1 ,2x 1 -x 2 ,y 2 ]Entering S3.5;
s3.5: and judging whether the obtained ground wire area is accurate or not, and judging and determining whether the ground wire area is the ground wire area or not according to the infrared image characteristics of the ground wire area.
For the judgment of the ground wire area, a matching model based on a shape matching algorithm is adopted, the whole process mainly comprises two parts, one part is used for manufacturing a matching template, and a model is generated; and secondly, matching the target image by adopting a model.
The model generation process mainly comprises the following steps: 1. acquiring a template image, and extracting canny edges of the template image to obtain boundary points of the template image; 2. respectively solving the gradient in the x direction and the gradient in the y direction of each point of the template image by using a sobel operator; 3. according to the x and y gradient combination and the position information of the boundary point, the gradient direction and the gradient size of each boundary are obtained; 4. the center of gravity (X, Y) of the template edge points is calculated.
The matching process mainly comprises the following steps: 1. extracting canny edges of the areas to be matched of the ground wires to obtain boundary point information of the images to be matched; 2. respectively solving the gradient in the x direction and the gradient in the y direction of each point in the image to be matched by using a sobel operator; 3. and (3) sliding window matching search, namely calculating matching scores of the template from left to right on the image to be matched sequentially from top to bottom, assuming that the total number of edge points of the template image is N, and respectively calculating an included angle cosine value a of each point on the boundary point of the template and the direction vector of the corresponding image point to be matched on the corresponding matching area 1 ，a 2 ，a 3 ，…，a n The matching score can be recorded as
If p is more than or equal to 0.8 of threshold value, the obtained ground lead area is judged to be accurate, then the temperature of all points in the obtained component position area is automatically analyzed, the highest temperature is extracted, and meanwhile, the highest temperature in the ground lead area near the component area is extracted, namely, the temperature matrix of the infrared picture of m x n pixels is analyzed
Highest temperature value (T) in middle corresponding ground wire hardware fitting and ground wire area j ,T x ) Entering S3.6; if the p is smaller than the threshold value of 0.8, judging that no ground wire area exists, recording the relevant information of the picture into a problem database, storing the picture additionally, and checking and examining the picture manually.
S3.6: analyzing the extracted temperature, and judging whether the defects exist or not and judging the defect grade according to the defect grading standard.
For composite insulators and arresters, the maximum temperature (T) in the three zones was analyzed max1 ,T max2 ,T max3 ) Difference value, if the temperature difference value is between 0.5 and 1 ℃, judgingOther defects are identified; if the temperature difference is between 1 and 3 ℃, judging as a common defect; if the temperature difference is between 3 and 5 ℃, judging the defect as a major defect; and if the temperature difference is more than 5 ℃, judging the defect as a major defect.
For the ground wire hardware fitting, calculating the highest temperature T in the ground wire hardware fitting area j Maximum temperature T of ground wire area x Analyzing the maximum temperature T of the ground wire hardware fitting by the difference value and the relative temperature difference delta T j The highest temperature difference T with the ground wire area j -T x And the relative temperature difference DeltaT if the temperature difference T j -T x Judging the defect as a common defect when the temperature is between 5 and 15 ℃ or the relative temperature difference delta T is between 35 and 80 percent; if the highest temperature T of the ground wire hardware fitting area j The highest temperature difference T between 90 and 130 ℃ or the highest temperature difference T of the ground wire area is achieved j -T x Judging the defect as major defect if the temperature is between 15 and 40 ℃ or the relative temperature difference delta T is between 80 and 95 percent; if the highest temperature T of the ground wire hardware fitting area j Reaching above 130 ℃ or the highest temperature difference T with the ground wire area j -T x If the temperature is higher than 40 ℃ and the relative temperature difference delta T is higher than 95%, the defect is judged to be an emergency defect.
For the wire hardware fitting, calculating the highest temperature T in the wire hardware fitting area j Difference value T of highest temperature of lead area x And the relative temperature difference delta T, analyzing the maximum temperature T of the wire hardware j The difference value T between the highest temperature of the wire hardware fitting and the highest temperature of the wire area j -T x And the relative temperature difference DeltaT if the temperature difference T j -T x Judging as a common defect if the temperature is between 5 and 15 ℃ or the relative temperature difference delta T is between 35 and 80 percent; if the highest temperature T of the wire hardware fitting area j Reaching 90-130 ℃, or reaching the highest temperature difference T with the lead area j -T x Judging the defect as major defect if the temperature is between 15 and 40 ℃ or the relative temperature difference delta T is between 80 and 95 percent; if the highest temperature T of the wire hardware fitting area j Reaching a maximum temperature difference T of above 130 ℃ or the ground wire area j -T x If the temperature is higher than 40 ℃ and the relative temperature difference delta T is higher than 95%, the emergency defect is judged.
Relative temperature difference toolThe body formula is:
T j : the highest temperature of the component area is reached,
T x : the highest temperature of the adjacent wire/ground area.
If the picture has defects, marking the defect type and the defect grade, renaming the picture according to the ' voltage grade _ line name _ pole tower number _ component _ timestamp _ defect type _ defect grade ' JPG ' format, and entering S3.7;
s3.7: and outputting a defect picture to finish a defect identification working process.
As shown in fig. 4, S5 includes the steps of:
s5.1: inputting a defect picture;
s5.2: and extracting information such as lines, towers, parts, defect types, defect grades, time and the like in the picture names.
S5.3: 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 S5.4; if the relevant defect information exists, it indicates that the operation and maintenance personnel may record the defect into the generation management system, so the picture relevant information is recorded into the problem database, and the picture is additionally stored and is checked and examined manually.
S5.4; 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 S5.5; if the relevant defects are processed, the operation and maintenance personnel are indicated to possibly process the relevant defects, so the picture relevant information is recorded into a problem database, and the picture is additionally stored and is checked and examined manually.
S5.5: comparing the personnel equipment base, extracting the operation and maintenance team, personnel and team leader information of the corresponding line, and entering S5.6 if the operation and maintenance information of the line section exists; if not, recording the relevant information of the picture to a problem database, storing the picture additionally, and checking and examining manually.
S5.6: comparing the defect representation library, extracting specific representations of corresponding defect types, and entering S5.7 if the defect representations exist; if not, recording the relevant information of the picture to a problem database, storing the picture additionally, and checking and examining manually.
S5.7: and generating defect entry information, generating related information which needs to be entered into the production management system, such as a line name, a pole tower number, components, an operation and maintenance team, operation and maintenance personnel, a line team leader, defect types, defect grades, specific defect representations and the like according to the steps, further generating defect entry information, and finishing a defect information generation working process.
The method can perform analysis and processing on the infrared inspection photo of the power transmission line, automatically detect the heating defect, automatically record the related heating defect into a system, and completely replace manual work to carry out the work. The average processing time of each photo is 2 seconds, the defect entry time is 2 minutes, 10 ten thousand photos are calculated every year, 1200 working hours can be saved all year by applying the method disclosed by the embodiment, and the work of 15 team personnel can be replaced. Compared with the prior art, the embodiment has the following beneficial effects:
(1) The system automatically analyzes the infrared inspection photo, detects whether the related parts generate heat or not, and automatically records the defects into the system, so that 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 infrared inspection photos, detect the temperature of the key component, judge the heating 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. The intelligent processing method provided by the invention has the advantages that the program is automatically processed, the temperature analysis software which is complicated in operation by personnel is not needed, the mutual communication and exchange verification processes of manual statistics are omitted, the intelligent processing method can continuously work for 24 hours, a large amount of time can be saved, the timely discovery and processing of heating defects of the power transmission line are ensured, and the safe and stable operation of the line is ensured.
(3) The infrared photo analysis is more accurate and reliable, and heating defects are not easy to make mistakes and omit in processing. According to the intelligent processing method provided by the invention, the machine uniformly identifies and detects the defects, the defects are judged according to a standard scientific defect judgment method, the accuracy of heating defect identification and the processing normalization are ensured, compared with the traditional manual processing, the method is more objective and comprehensive, the error rate and the leakage rate are lower than those of the existing infrared image intelligent diagnosis, the infrared picture can be better ensured to be processed according to requirements, and the timely and comprehensive discovery and recording of the heating defects of the line are ensured.
(4) The analysis method has universality. The infrared image temperature extraction method provided by the invention is suitable for all infrared temperature measurement images, ensures that the method is generally suitable for all infrared images, and is more reliable and effective.
The terms describing positional relationships in the drawings are for illustrative purposes only and are not to be construed as limiting the 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. It will be apparent to those skilled in the art that other variations and modifications can be made on the basis of the above description. This need not be, nor should it be 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. An intelligent processing method for infrared inspection data of a power transmission line is characterized by comprising the following steps:
s1: inputting the infrared inspection picture of the daily operation and maintenance power transmission line into the system;
s2: renaming the input picture by using a picture naming device;
s3: carrying out component identification and area temperature detection analysis on the renamed picture: according to the AI component identification and temperature detection working flow, sequentially carrying out component identification, region temperature detection, defect judgment and marking on the renamed picture, renaming the picture according to the identified defect type and grade, and finally outputting a defect picture;
s4: and (3) manually checking defects: manually checking and judging a defect identification result, inputting the picture into a defect generator if the identification is correct, recording related information of the picture into a problem database if the identification is wrong or the temperature detection is wrong, and storing the picture for manually analyzing and identifying the error reason so as to continuously perfect the system;
s5: generating defect information using a defect generator: the defect generator respectively judges whether the historical defect and the working ticket have defect information after the picture time according to the line, the tower, the part and the defect type in the picture and by combining a defect library and a working ticket library, if the historical defect and the working ticket do not have the defect information, according to a personnel equipment library and a defect representation library, the responsible personnel information and the corresponding description representation information of the defect type of the relevant line tower are searched, a defect message is generated and sent to an RPA robot for processing, if the responsible personnel information and the defect representation library do not exist, the defect message is not generated, the picture information is recorded to a problem database, the picture is additionally stored, and the picture is checked and audited manually;
s6: and (5) recording the defects by using the RPA robot and informing a team manager.
2. The intelligent processing method for the infrared inspection data of the power transmission line according to claim 1, wherein S2 comprises the following steps:
s2.1: extracting longitude, latitude, height and shooting time information in the picture;
s2.2: 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 ledger library;
calculating the space distance between the infrared picture and the machine account extracting component, and taking the minimum value in all the distances; if the distance is less than 10 meters, the infrared picture shooting object is considered as the line component, and the infrared picture is matched with the account line component; if the distance is within the range of 10-200 m, the infrared picture is considered as the whole picture of the line tower, and the infrared picture is matched with the account line tower; if the distance is more than 200 meters, the picture is not considered to belong to any return account line, a problem exists, picture related information is recorded into a problem database, the picture is additionally stored, and the picture is checked and examined manually;
s2.3: renaming the picture according to the matching result;
s2.4: and outputting the renaming infrared picture to finish the renaming work flow.
3. The intelligent processing method for the infrared inspection data of the power transmission line according to claim 2, wherein the renaming rule in S2.3 is as follows: and if the infrared picture is matched with the line component in the standing book, renaming the infrared picture according to the voltage level _ line name _ pole tower number _ component _ timestamp in the JPG format, and if the infrared picture is matched with the line tower of the standing book, renaming the infrared picture according to the voltage level _ line name _ pole tower number _ full tower _ timestamp in the JPG format.
4. The intelligent processing method for the infrared inspection data of the power transmission line according to any one of claims 1 to 3, wherein S3 comprises the following steps:
s3.1: inputting an infrared picture to be identified;
s3.2: carrying out component identification on the picture: constructing and training a power transmission equipment component identification model of the fast R-CNN, and identifying the power transmission equipment component in the picture by using the power transmission equipment component identification model of the fast R-CNN;
wherein the power transmission equipment component comprises: the composite insulator, the lightning arrester, the ground wire hardware fitting and the wire hardware fitting;
the ground wire hardware comprises a suspension clamp, a strain clamp splicing hardware and a connecting hardware, and the wire hardware comprises a suspension clamp, a strain clamp, a splicing hardware and a connecting hardware;
s3.3: judging the recognition result, and if the equipment part exists, inputting the picture into S3.4; if the device component does not exist, recording the relevant picture information into a problem database, storing the picture in addition, and checking manually;
s3.4: acquiring the position of a device component in a picture, extracting parameter information of the infrared picture, and calculating the temperature of each point in the picture to form a temperature matrix;
for the composite insulator and the lightning arrester obtained through identification, evenly dividing the composite insulator and the lightning arrester into three regions according to the obtained positions of the components, analyzing the temperature of all pixel points in each region, respectively extracting the highest temperature, and entering S3.6;
for the ground wire hardware obtained through identification, according to a method for obtaining the position of the ground wire in the spatial position relationship, judging and obtaining the position of the ground wire area through the translation of the position of the ground wire hardware area and the infrared image characteristics, and entering S3.5;
for the identified wire hardware, according to a method for acquiring the position of the ground wire according to the spatial position relationship, judging and acquiring the position of the wire area through the translation of the position of the wire hardware area and the infrared image characteristics, and entering S3.5;
s3.5: judging whether the obtained ground wire area is accurate or not, judging and determining whether the ground wire area is the ground wire area or not according to the infrared image characteristics of the ground wire area, if the obtained ground wire area is accurate, automatically analyzing the temperature of all points in the obtained component position area, extracting the highest temperature, simultaneously extracting the highest temperature in the ground wire area near the component area, and entering S3.6; if the situation that the ground wire area does not exist is judged, recording the relevant information of the picture into a problem database, and storing the picture in addition and checking the picture manually;
s3.6: analyzing the extracted temperature, and judging whether the defect exists or not and the defect grade according to the defect grading standard;
s3.7: and outputting a defect picture to finish defect identification.
5. The intelligent processing method for the infrared inspection data of the power transmission line according to claim 4, wherein S3.2 specifically comprises:
adopting an Faster R-CNN power transmission equipment part identification model, inputting an original infrared picture, taking a pixel point at the upper left corner of the picture as an origin of coordinates, taking the pixel point horizontally rightwards as an X axis and taking the pixel point vertically downwards as a Y axis, marking the type of a part and a part label if a power transmission equipment part exists through identification, and marking the coordinate (X) at the upper left corner of a part marking frame 1 ,y 1 ) And the coordinates (x) of the lower right corner of the part label box 2 ,y 2 ) If the recognition result is not present, the part tag is written as 0.
6. The intelligent processing method for the infrared inspection data of the power transmission line according to claim 5, wherein S3.4 specifically comprises:
obtaining a position [ x ] of a device component in a picture 1 ,y 1 ,x 2 ,y 2 ]And extracting parameter information of the infrared picture, wherein the parameters comprise: 16-bit RAW original value, radiation coefficient E, camera distance OD, atmospheric temperature AT, reflector surface temperature RT, refractor surface temperature IT, refractive index IRT, relative humidity RH, planck R1 constant PR1, planck B constant PB, planck F constant PF, planck shift constant PO, planck R2 constant PR2; calculating the temperature of each pixel point in the picture according to the formulas (1) to (9) to form a temperature matrix,
if the pixel of the infrared picture is m x n, the temperature matrix is
Formula (1):
formula (2):
formula (3):
formula (4):
formula (5):
formula (6):
formula (7):
formula (8):
formula (9):
wherein RAW is the original value of 16 bits RAW;
ATA1 is an atmospheric heat transfer constant used for calculating the influence of humidity on transmission;
ATA2 is an atmospheric heat transfer constant which is used for calculating the influence of humidity on transmission;
ATB1 is an atmospheric heat transfer constant and is used for calculating the influence of humidity on transmission;
ATB2 is an atmospheric heat transfer constant used for calculating the influence of humidity on transmission;
ATX is an atmospheric heat transfer constant used for calculating the influence of humidity on transmission;
for the identified composite insulator and arrester, the composite insulator and arrester are divided into three regions according to the acquired component positions, namely, the positions [ x ] of the composite insulator and arrester 1 ,y 1 ,x 2 ,y 2 ]Judgment of x 2 -x 1 And y 2 -y 1 Size, if y 2 -y 1 ≥x 2 -x 1 Then, the following three regions are divided
If y 2 -y 1 <x 2 -x 1 Then, the following three regions are divided
Analyzing the temperature of all pixel points in each region, respectively extracting the highest temperature, namely analyzing an m x n pixel infrared picture temperature matrix
Highest temperature value (T) in the middle corresponding region max 1 ,T max 2 ,T max 3 ) Entering S3.6;
for the ground wire hardware obtained by identification, according to the method for acquiring the position of the ground wire in the spatial position relationship, the position of the ground wire area is judged and acquired through the translation of the area position of the ground wire hardware and the infrared image characteristic, namely the position [ x ] of the ground wire hardware is acquired 1 ,y 1 ,x 2 ,y 2 ]Obtaining ground area [2x ] by area position translation 2 -x 1 ,y 1 ,3x 2 -2x 1 ,y 2 ]Or [3x 1 -2x 2 ,y 1 ,2x 1 -x 2 ,y 2 ]Entering S3.5;
for the identified wire hardware fitting, according to the method for acquiring the position of the ground wire in the space position relationship, the position of the wire area is judged and acquired through the translation of the area position of the wire hardware fitting and the infrared image characteristic, namely the position [ x ] of the wire hardware fitting 1 ,y 1 ,x 2 ,y 2 ]Obtaining ground area [2x ] by area position translation 2 -x 1 ,y 1 ,3x 2 -2x 1 ,y 2 ]Or [3x 1 -2x 2 ,y 1 ,2x 1 -x 2 ,y 2 ]Proceed to S3.5.
7. The intelligent processing method for the infrared inspection data of the power transmission line according to claim 6, wherein S3.5 specifically comprises:
judging whether the obtained ground wire area is accurate or not, and judging and determining whether the ground wire area is the ground wire area or not according to the infrared image characteristics of the ground wire area;
judging the ground wire area, including making a matching template, generating a model and matching a target image by using the model;
wherein generating the model comprises the steps of:
(1) Acquiring a template image, carrying out canny edge extraction on the template image, and extracting boundary points of the template image;
(2) Respectively solving the gradient of each point of the template image in the x direction and the gradient of each point in the y direction by using a sobel operator;
(3) According to the x and y gradient combination and the position information of the boundary point, the gradient direction and the gradient size of each boundary are obtained;
(4) Calculating the gravity centers (X, Y) of the edge points of the template;
matching the target image with the model includes the steps of:
step 1: extracting canny edges of the areas to be matched of the conductive wires and the ground wires to obtain boundary point information of the images to be matched;
step 2: respectively solving the gradient in the x direction and the gradient in the y direction of each point in the image to be matched by using a sobel operator;
and step 3: and (3) sliding window matching search, namely calculating matching scores of the template from left to right on the image to be matched sequentially from top to bottom, assuming that the total number of edge points of the template image is N, and respectively calculating the cosine value a of the included angle between each point on the boundary point of the template and the direction vector of the corresponding image point to be matched on the corresponding matching area 1 ，a 2 ，a 3 ，…，a n The matching score can be recorded as
If p is larger than or equal to a preset threshold value, judging that the obtained ground wire area is accurate, automatically analyzing the temperature of all points in the obtained component position area, extracting the highest temperature, and simultaneously extractingTaking the highest temperature in the ground wire area near the component area, namely analyzing the temperature matrix of the infrared picture of m x n pixels
Middle corresponding ground wire hardware and highest temperature value (T) in ground wire area j ,T x ) Entering S3.6; if the p is smaller than the preset threshold value, judging that no ground wire area exists, recording the relevant information of the picture to a problem database, storing the picture in addition, and checking and verifying manually.
8. The intelligent processing method for the infrared inspection data of the power transmission line according to any one of claims 5 to 7, wherein S3.6 specifically comprises:
analyzing the highest temperature difference in the three areas for the composite insulator and the lightning arrester, and judging other defects if the temperature difference is between 0.5 and 1 ℃; if the temperature difference is between 1 and 3 ℃, judging as a common defect; if the temperature difference is between 3 and 5 ℃, judging the defect as a major defect; if the temperature difference is more than 5 ℃, judging as a major defect;
for the ground wire hardware fitting, calculating the difference value and the relative temperature difference between the highest temperature of the ground wire hardware fitting region and the highest temperature of the ground wire region, analyzing the highest temperature of the ground wire hardware fitting, the difference value and the relative temperature difference between the highest temperature of the ground wire hardware fitting and the highest temperature of the ground wire region, and judging as a common defect if the temperature difference value is between 5 and 15 ℃ or the relative temperature difference is between 35 and 80 percent;
if the highest temperature of the ground wire hardware area reaches 90-130 ℃, or the difference value between the highest temperature of the ground wire hardware area and the highest temperature of the ground wire area is 15-40 ℃, or the relative temperature difference is 80-95%, judging as a major defect;
if the highest temperature of the ground wire hardware area reaches more than 130 ℃, or the difference value of the highest temperature of the ground wire hardware area and the highest temperature of the ground wire area is more than 40 ℃, or the relative temperature difference is more than 95%, judging as an emergency defect;
for the wire hardware fitting, calculating the difference value and the relative temperature difference between the highest temperature in the wire hardware fitting area and the highest temperature in the wire area, analyzing the difference value and the relative temperature difference between the highest temperature of the wire hardware fitting and the highest temperature in the wire area, and judging as a common defect if the temperature difference value is between 5 and 15 ℃ or the relative temperature difference is between 35 and 80 percent;
if the highest temperature of the wire hardware area reaches 90-130 ℃, or the difference value between the highest temperature of the wire hardware area and the highest temperature of the wire area is 15-40 ℃, or the relative temperature difference is 80-95%, judging as a major defect;
if the highest temperature of the wire hardware fitting region reaches above 130 ℃, or the difference value of the highest temperature of the wire hardware fitting region and the highest temperature of the ground wire region is larger than 40 ℃, or the relative temperature difference is larger than 95%, judging as an emergency defect;
if the picture has defects, marking the defect type and the defect grade, renaming the picture according to the format of 'voltage grade _ line name _ pole tower number _ component _ timestamp _ defect type _ defect grade and JPG', and entering S3.7.
9. The intelligent processing method for the infrared inspection data of the power transmission line according to claim 8, wherein the specific formula of the relative temperature difference is as follows:
wherein, T j Maximum temperature of component region, T x The highest temperature of the adjacent wire/ground area.
10. The intelligent processing method for the infrared inspection data of the power transmission line according to claim 1 or 9, wherein S5 specifically comprises:
s5.1: inputting a defect picture;
s5.2: extracting information of lines, towers, components, defect types, defect grades and time in the names of the defect pictures;
s5.3: comparing the defect library, searching and checking whether the historical defect library has related defect information after the picture time, if not, indicating that the defect is not recorded into the system, and entering S5.4; if the relevant defect information exists, the operation and maintenance personnel are indicated to 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;
s5.4; comparing the work ticket library, searching and checking whether the historical work tickets have related defect elimination information after the picture time, if not, indicating that the defects are not processed, and entering S5.5; 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;
s5.5: comparing the personnel equipment base, extracting the operation and maintenance team, personnel and team leader information of the corresponding line, and entering S5.6 if the operation and maintenance information of the line section exists; if the picture does not exist, recording the picture related information into a problem database, and storing the picture in addition and checking the picture manually;
s5.6: comparing the defect representation library, extracting specific representations of corresponding defect types, and entering S5.7 if the defect representations exist; if the picture does not exist, recording the picture related information into a problem database, and storing the picture in addition and checking the picture manually;
s5.7: generating defect input information, further generating defect input information and finishing the generation of the defect information;
the input information comprises line names, tower numbers, components, operation and maintenance teams, operation and maintenance personnel, line team leaders, defect types, defect grades and defect specific representation information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010684426.9A CN111949809B (en) | 2020-07-16 | 2020-07-16 | Intelligent processing method for infrared inspection data of power transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010684426.9A CN111949809B (en) | 2020-07-16 | 2020-07-16 | Intelligent processing method for infrared inspection data of power transmission line |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111949809A CN111949809A (en) | 2020-11-17 |
| CN111949809B true CN111949809B (en) | 2023-01-20 |
Family
ID=73340595
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010684426.9A Active CN111949809B (en) | 2020-07-16 | 2020-07-16 | Intelligent processing method for infrared inspection data of power transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111949809B (en) |
Families Citing this family (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112529859A (en) * | 2020-12-04 | 2021-03-19 | 广东电网有限责任公司佛山供电局 | Power distribution equipment defect detection method and system |
| CN112651454B (en) * | 2020-12-31 | 2022-11-29 | 国网湖北省电力有限公司技术培训中心 | Infrared data acquisition system and spiral data processing method for power equipment |
| CN112819183A (en) * | 2021-01-29 | 2021-05-18 | 广州中科智巡科技有限公司 | Algorithm and system for intelligently distinguishing heating defects of power transmission and distribution line |
| CN113129284B (en) * | 2021-02-26 | 2023-04-07 | 山东大学 | Appearance detection method based on 5G cloud edge cooperation and implementation system |
| CN113112487A (en) * | 2021-04-20 | 2021-07-13 | 广东电网有限责任公司 | Method, device, equipment and storage medium for identifying thermal defects |
| CN113269744A (en) * | 2021-05-20 | 2021-08-17 | 国网天津市电力公司 | Infrared intelligent identification method and system applied to defects of power transmission line equipment |
| CN113420686A (en) * | 2021-06-29 | 2021-09-21 | 广东电网有限责任公司 | Power transmission line inspection method, device and system |
| CN113838046A (en) * | 2021-10-08 | 2021-12-24 | 南方电网数字电网研究院有限公司 | Drainage plate overheating identification method and device, computer equipment and storage medium |
| 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 |
| CN114964510A (en) * | 2022-07-27 | 2022-08-30 | 北京智芯半导体科技有限公司 | Overhead line hardware temperature anomaly monitoring method and system and intelligent power terminal |
| CN115661468A (en) * | 2022-12-29 | 2023-01-31 | 广东信通通信有限公司 | Power transmission and transformation equipment fault image segmentation method based on color space |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037133A (en) * | 2017-12-27 | 2018-05-15 | 武汉市智勤创亿信息技术股份有限公司 | A kind of power equipments defect intelligent identification Method and its system based on unmanned plane inspection image |
| CN110197176A (en) * | 2018-10-31 | 2019-09-03 | 国网宁夏电力有限公司检修公司 | Inspection intelligent data analysis system and analysis method based on image recognition technology |
-
2020
- 2020-07-16 CN CN202010684426.9A patent/CN111949809B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108037133A (en) * | 2017-12-27 | 2018-05-15 | 武汉市智勤创亿信息技术股份有限公司 | A kind of power equipments defect intelligent identification Method and its system based on unmanned plane inspection image |
| CN110197176A (en) * | 2018-10-31 | 2019-09-03 | 国网宁夏电力有限公司检修公司 | Inspection intelligent data analysis system and analysis method based on image recognition technology |
Non-Patent Citations (1)
| Title |
|---|
| 基于无人机图像识别技术的输电线路缺陷检测;李宁等;《电子设计工程》;20190520(第10期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111949809A (en) | 2020-11-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111949809B (en) | Intelligent processing method for infrared inspection data of power transmission line | |
| CN108037133B (en) | Intelligent electric power equipment defect identification method and system based on unmanned aerial vehicle inspection image | |
| CN108537154B (en) | Power transmission line bird nest identification method based on HOG characteristics and machine learning | |
| CN111242123B (en) | Power equipment fault diagnosis method based on infrared image | |
| CN111709361B (en) | Method for processing inspection data of unmanned aerial vehicle of power transmission line | |
| CN103901072B (en) | Method for diagnosing equipment overheating defects by utilizing infrared spectrum analysis | |
| CN108680833B (en) | Composite insulator defect detection system based on unmanned aerial vehicle | |
| CN113962659A (en) | Cloud computing-based smart power grid big data information management system and method | |
| CN109872317A (en) | A kind of defect identification method based on power equipments defect identification learning model | |
| CN112906694A (en) | Reading correction system and method for inclined pointer instrument image of transformer substation | |
| CN108846331B (en) | Video identification method for judging whether screw fastener of motor train unit chassis falls off or not | |
| CN111402224B (en) | Target identification method for power equipment | |
| CN110427943A (en) | A kind of intelligent electric meter technique for partitioning based on R-CNN | |
| CN112102296A (en) | Power equipment target identification method based on human concept | |
| CN112115770A (en) | Method and system for identifying autonomous inspection defects of unmanned aerial vehicle of overhead line | |
| CN116258980A (en) | Unmanned aerial vehicle distributed photovoltaic power station inspection method based on vision | |
| CN115019294A (en) | Pointer instrument reading identification method and system | |
| CN108510487A (en) | A kind of photovoltaic module remote monitoring device | |
| CN111027565A (en) | Power transmission and transformation equipment report content generation method based on optical vision semantic extraction | |
| CN117498225B (en) | Unmanned aerial vehicle intelligent power line inspection system | |
| CN117252840B (en) | Photovoltaic array defect elimination evaluation method and device and computer equipment | |
| CN117114420A (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN109360289B (en) | Power meter detection method fusing inspection robot positioning information | |
| CN112732773A (en) | Uniqueness checking method and system for relay protection defect data | |
| CN113780224B (en) | Unmanned inspection method and system for transformer substation |
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 |