CN112542800A - Method and system for identifying transmission line fault - Google Patents
Method and system for identifying transmission line fault Download PDFInfo
- Publication number
- CN112542800A CN112542800A CN202011325240.0A CN202011325240A CN112542800A CN 112542800 A CN112542800 A CN 112542800A CN 202011325240 A CN202011325240 A CN 202011325240A CN 112542800 A CN112542800 A CN 112542800A
- Authority
- CN
- China
- Prior art keywords
- inspection
- insulator
- aerial vehicle
- unmanned aerial
- power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000005540 biological transmission Effects 0.000 title claims abstract description 28
- 239000012212 insulator Substances 0.000 claims abstract description 73
- 238000007689 inspection Methods 0.000 claims abstract description 68
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims description 19
- 238000000605 extraction Methods 0.000 claims description 13
- 230000010365 information processing Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 10
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 238000004088 simulation Methods 0.000 claims description 5
- 230000007547 defect Effects 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 230000009471 action Effects 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 7
- 238000003745 diagnosis Methods 0.000 description 6
- 230000004888 barrier function Effects 0.000 description 5
- 239000000463 material Substances 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 239000010828 animal waste Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013075 data extraction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/081—Locating faults in cables, transmission lines, or networks according to type of conductors
- G01R31/085—Locating faults in cables, transmission lines, or networks according to type of conductors in power transmission or distribution lines, e.g. overhead
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/08—Locating faults in cables, transmission lines, or networks
- G01R31/088—Aspects of digital computing
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20032—Median filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Electric Cable Installation (AREA)
Abstract
The application discloses a method and a system for identifying transmission line faults, wherein the method comprises the following steps: the unmanned aerial vehicle executes power inspection operation based on the automatic inspection operation script; in the process of power inspection operation, identifying power inspection equipment based on inspection sensing equipment on an unmanned aerial vehicle, and adjusting relevant parameters of the inspection sensing equipment based on the power inspection equipment; acquiring patrol data on the power patrol route based on the adjusted patrol sensing equipment; and acquiring insulator fault information in the inspection data based on the DCNN. According to the embodiment of the invention, the insulator fault information is analyzed by unmanned aerial vehicle inspection and an algorithm, so that the inspection efficiency is improved, and the insulator fault information can be analyzed and processed quickly and accurately.
Description
Technical Field
The application relates to the technical field of electric power, in particular to a method and a system for identifying faults of a power transmission line.
Background
The maintenance of the power grid is mainly completed in a line patrol mode by electric workers at first, the labor intensity is high, the line patrol maintenance efficiency is low, the terrain of most power transmission lines is complex, and the power transmission lines are difficult to patrol and dangerous due to severe climate factors. With the development of automation equipment and technology, transmission line operation and maintenance units realize that the maintenance of a power grid by adopting an automatic scientific and technological means is more economical and reliable, and begin to research a comprehensive monitoring system of the transmission line, try to monitor the operation of the power grid by using various sensors installed on towers and power equipment, and replace manual inspection. However, the high-voltage transmission line crosses mountains and mountains, the natural environment is severe, the temperature is changed drastically, animal wastes and electromagnetic interference are caused, the monitoring system has power supply problems, and the like, so that the system is difficult to operate and maintain effectively, and finally 70% of the conventional comprehensive monitoring systems of the transmission line stop operating.
Because the breadth of our country is broad, the climate difference between south and north is large, the types of insulators adopted in different environments and different voltage grades are different, and various insulators have different materials and shapes. The traditional means needs to design a diagnosis algorithm for the insulator state diagnosis method, the existing insulator state diagnosis method based on manual characteristics is poor in robustness, complex in calculation and single in type of processed insulator faults, and rapid and accurate analysis and processing of the insulator faults cannot be achieved.
Disclosure of Invention
The purpose of this application lies in solving the technical problem that exists among the prior art at least, provides transmission line fault identification's method and system, patrols and examines through unmanned aerial vehicle and adopts the algorithm to carry out the analysis of insulator fault information, has promoted and has patrolled and examined efficiency, also can be fast with accurate analysis processing insulator fault information.
The embodiment of the invention provides a method for identifying faults of a power transmission line, which comprises the following steps:
the unmanned aerial vehicle executes power inspection operation based on the automatic inspection operation script;
in the process of power inspection operation, identifying power inspection equipment based on inspection sensing equipment on an unmanned aerial vehicle, and adjusting relevant parameters of the inspection sensing equipment based on the power inspection equipment;
acquiring patrol data on the power patrol route based on the adjusted patrol sensing equipment;
and acquiring insulator fault information in the inspection data based on the DCNN.
Unmanned aerial vehicle patrols and examines the operation based on automatic operation script execution power and includes:
generating a simulation calculation result of the route planning into a kml file through a Matlab open source toolbox and a custom programming, and displaying point, line and surface element in the three-dimensional terrain of Google Earth through the kml file description;
and executing the power patrol operation based on the kml file.
Unmanned aerial vehicle still includes based on automatic operation script execution power inspection operation:
and avoiding the obstacle in the flight path based on the autonomous obstacle avoidance system.
The obstacle avoidance system based on the self-help obstacle avoidance system for avoiding the obstacle in the flight path comprises:
the unmanned aerial vehicle obtains a depth image of the obstacle, accurately senses the specific contour of the obstacle based on the depth image, and achieves independent bypassing of the obstacle; and/or
The unmanned aerial vehicle establishes a map model for planning reasonable routes for the flight area and automatically bypasses the obstacles based on the reasonable routes.
Patrol sensing equipment discernment electric power and patrol and examine equipment based on unmanned aerial vehicle to it includes to patrol and examine equipment relevant parameter including to patrol and examine based on electric power:
and rapidly identifying the tower and the wire object, automatically correcting the shooting angle and adjusting the camera parameters.
The acquiring of the insulator fault information in the inspection data based on the deep convolutional neural network DCNN comprises the following steps:
extracting image data or video data in the inspection data;
performing information processing on the image data or the video data;
image preprocessing is carried out on the image data or the video data after the information processing;
performing insulator foreground extraction on the preprocessed image data or video data;
extracting insulator characteristics of the image data or the video data after the extraction processing of the insulator foreground based on an insulator extraction algorithm;
and detecting the insulator defects to acquire insulator fault information.
The information processing of the image data or the video data includes:
performing color space conversion;
carrying out gray level image conversion;
acquiring pixel information;
histogram calculation is performed.
The image preprocessing of the image data or the video data after the information processing comprises:
carrying out histogram equalization;
carrying out gray level stretching treatment;
carrying out median filtering processing;
and performing morphological filtering processing.
The step of extracting the insulator foreground from the preprocessed image data or video data comprises the following steps:
processing data based on an edge detection algorithm;
and processing data based on an image segmentation algorithm.
The embodiment of the invention also provides a system for identifying the transmission line fault, and the system is used for executing the method.
Compared with the prior art, the unmanned aerial vehicle power inspection operation method and system can improve the efficiency of power inspection operation, save labor cost and reduce inspection risk of personnel. Through utilizing DCNN network as the feature extractor, patrolling and examining through unmanned aerial vehicle and adopting the algorithm to carry out the analysis of insulator fault information, promoted and patrolled and examined efficiency, also can be fast and accurate analysis and processing insulator fault information for the fault classification rate of accuracy of insulator fault information reaches more than 95%.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart of a method for thermal fault simulation accuracy correction in an embodiment of the invention;
fig. 2 is a block diagram of a typical thermal fault experimental simulation process of a switchgear in an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a method for identifying faults of a power transmission line, which is characterized in that an unmanned aerial vehicle executes power inspection operation based on an automatic inspection operation script; in the process of power inspection operation, identifying power inspection equipment based on inspection sensing equipment on an unmanned aerial vehicle, and adjusting relevant parameters of the inspection sensing equipment based on the power inspection equipment; acquiring patrol data on the power patrol route based on the adjusted patrol sensing equipment; and acquiring insulator fault information in the inspection data based on the DCNN.
Specifically, fig. 1 shows a flowchart of a method for identifying a power transmission line fault in the embodiment of the present invention, which specifically includes the following steps:
s101, the unmanned aerial vehicle executes power inspection operation based on the automatic inspection operation script;
specifically, unmanned aerial vehicle patrols and examines the operation based on automatic operation script execution power and includes: generating a simulation calculation result of the route planning into a kml file through a Matlab open source toolbox and a custom programming, and displaying point, line and surface element in the three-dimensional terrain of Google Earth through the kml file description; and executing the power patrol operation based on the kml file.
In the embodiment of the invention, the image information of the to-be-determined region is acquired based on the camera in the unmanned aerial vehicle, and the position information corresponding to the image information is extracted, the flight record information in the embodiment of the invention can select a set-bin file generated by flight control or a set-tlog file recorded on ground station software as an original material of flight record, but considering that the flight log based on the M300 RTK unmanned aerial vehicle is not in a common set-bin file format, the set-tlog file recorded on the ground station is adopted as a main material.
The's of tlog' file is all data frame raw data recorded by the ground station and sent to the ground station by the unmanned aerial vehicle flight control, and the data contains key information such as real-time GPS coordinates, height, unmanned aerial vehicle attitude, input channel value, output channel value, azimuth angle and pitch angle of the load pod, but the data in the file needs to be extracted and simplified. For example, it takes 60s for the unmanned aerial vehicle to fly from point a to point B, and it is set that the attitude data of the unmanned aerial vehicle is issued to the ground station at a frequency of 2Hz, then 120 frames of data are available in the ". tlog" file to describe the process from point a to point B, and the unmanned aerial vehicle only needs two instructions to fly from point a to point B, so that a log data analysis and extraction tool software needs to be designed to automatically extract "key waypoints" and "key actions" from a large amount of redundant data, where the "key actions" refer to pod attitude angles at the moment of photographing the loads.
Here unmanned aerial vehicle patrols and examines the operation based on automatic operation script execution power and includes: extracting key routing points and routing objects of power routing inspection operation in the automatic routing inspection operation script; and generating a corresponding key route and routing inspection action based on the key routing inspection point and the routing inspection object.
In the embodiment of the invention, a star-tlog file recorded by a ground station is used as a main material, the star-tlog file is original data of all data frames which are recorded by the ground station and sent to the ground station by unmanned aerial vehicle flight control, the data comprises key information such as real-time GPS coordinates, height, unmanned aerial vehicle attitude, input channel values, output channel values, azimuth angles and pitch angles of a load pod and the like of the unmanned aerial vehicle, and key navigation points and key actions are extracted from the information. The "key waypoints" include the unmanned aerial vehicle's GPS coordinates, altitude, unmanned aerial vehicle attitude, input channel values, output channel values, and the like. The "key action" refers to the nacelle attitude angle at the moment the load is photographed. The critical route relates to the setting of a critical navigation point, and the patrol action relates to the setting of a critical action.
Unmanned aerial vehicle still includes based on automatic operation script execution power inspection operation: and avoiding the obstacle in the flight path based on the autonomous obstacle avoidance system. The obstacle avoidance system based on the self-help obstacle avoidance system for avoiding the obstacle in the flight path comprises: the unmanned aerial vehicle obtains a depth image of the obstacle, accurately senses the specific contour of the obstacle based on the depth image, and achieves independent bypassing of the obstacle; and/or the unmanned aerial vehicle establishes a map model for the flight area to plan a reasonable route, and automatically bypasses the barrier based on the reasonable route.
The unmanned aerial vehicle autonomous obstacle avoidance system can avoid obstacles in a flight path in time, and the perfect autonomous obstacle avoidance system can reduce various losses caused by misoperation to a great extent. The unmanned plane obstacle avoidance technology can be divided into three stages, namely a stage of sensing obstacles; second, bypassing the obstacle; and thirdly, a scene modeling and path searching phase. The unmanned aerial vehicle finds the barrier, and can automatically bypass the barrier, and then reach the process of planning the path by oneself.
In the first phase, the drone can only simply sense the obstacle. When the unmanned aerial vehicle encounters an obstacle, the unmanned aerial vehicle can be quickly identified and hovered off, and the unmanned aerial vehicle waits for the next instruction of the driver of the unmanned aerial vehicle and is relatively dependent on the attention and operation of the flyer.
In the second stage, the unmanned aerial vehicle can acquire the depth image of the obstacle, accurately sense the specific contour of the obstacle and then automatically bypass the obstacle. The stage is a stage of getting rid of the operation of the flying hand, improving the intellectualization and realizing the autonomous driving of the unmanned aerial vehicle.
In the third stage, the unmanned aerial vehicle can establish a map model for a flight area and then plan a reasonable route, the map cannot be only a mechanical plane model, but also a three-dimensional map which can be updated in real time, and the map is the highest stage of the existing unmanned aerial vehicle obstacle avoidance technology.
The autonomous obstacle avoidance technology needs to be capable of sensing the surrounding environment in real time in the flight process of the unmanned aerial vehicle, and automatically avoiding collision according to the distance of environmental obstacles. To avoid the barrier, must detect the barrier at first, common unmanned aerial vehicle range finding sensor has ultrasonic wave, infrared ray, laser etc. on the market.
S102, in the process of power inspection operation, identifying power inspection equipment based on inspection sensing equipment on the unmanned aerial vehicle, and adjusting relevant parameters of the inspection sensing equipment based on the power inspection equipment;
here, survey sensing equipment discernment electric power and patrol the equipment based on unmanned aerial vehicle to adjust and patrol the relevant parameter of sensing equipment and include based on electric power and patrol the equipment: and rapidly identifying the tower and the wire object, automatically correcting the shooting angle and adjusting the camera parameters.
In the front-end operation process, objects such as towers, wire channels and the like need to be identified in real time. Under an ideal condition, the front end can accurately extract objects such as towers, wires and the like in real time, but in actual operation, the outside of the front end equipment needs to be influenced by factors such as light and shadow change, airflow disturbance, equipment vibration and the like, and the inside of the front end equipment is limited by the computing power of an onboard computer, so that the effect completely the same as that under the ideal condition is difficult to achieve. However, the recognition function of the front-end equipment is mainly used for rapidly recognizing objects such as towers and wires, automatically correcting the shooting angle and adjusting the camera parameters, so that the robustness of the system is improved, the fault recognition of the rear end is more accurate, and the information processing is smoother.
S103, acquiring routing inspection data on the power routing inspection route based on the adjusted routing inspection sensing equipment;
and S104, acquiring insulator fault information in the inspection data based on the deep convolutional neural network DCNN.
Specifically, fig. 2 shows a schematic diagram of a principle of an unmanned aerial vehicle transmission line fault detection method based on image recognition in the embodiment of the present invention, where obtaining insulator fault information in patrol data based on a deep convolutional neural network DCNN includes: extracting image data or video data in the inspection data; performing information processing on the image data or the video data; image preprocessing is carried out on the image data or the video data after the information processing; performing insulator foreground extraction on the preprocessed image data or video data; extracting insulator characteristics of the image data or the video data after the extraction processing of the insulator foreground based on an insulator extraction algorithm; and detecting the insulator defects to acquire insulator fault information.
Specifically, the information processing of the image data or the video data includes: performing color space conversion; carrying out gray level image conversion; acquiring pixel information; histogram calculation is performed.
Specifically, the image preprocessing of the image data or the video data after the information processing includes: carrying out histogram equalization; carrying out gray level stretching treatment; carrying out median filtering processing; and performing morphological filtering processing.
Specifically, the performing of the insulator foreground extraction on the preprocessed image data or video data includes: processing data based on an edge detection algorithm; and processing data based on an image segmentation algorithm.
The step of acquiring the insulator fault information based on the deep convolutional neural network DCNN comprises the following steps: and binarizing the positioned insulator image, scanning the insulator image in lines, counting the number of pixel points of each line of insulator image, and dividing the insulator image into a plurality of insulator umbrella disc images by taking the wave troughs of the number of the pixel points as dividing lines.
Because the breadth of our country is broad, the climate difference between the south and the north is large, the types of insulators adopted in different environments and different voltage grades are different, and various insulators have different materials and shapes, the prior art needs to design diagnosis algorithms for the insulators respectively, the prior insulator state diagnosis method based on manual characteristics has poor robustness, complex calculation and single type of insulator fault to be processed. In the embodiment of the invention, the DCNN is firstly applied to the fault diagnosis of the insulator of the power transmission line, and the corresponding expression of the insulator fault is discovered through a deep network.
And binarizing the positioned insulator image, scanning the insulator image in lines, counting the number of pixel points of each line of insulator image, and dividing the insulator image into a plurality of insulator umbrella disc images by taking the wave troughs of the number of the pixel points as dividing lines. And establishing an aerial photography insulator umbrella disk image library by using various insulator umbrella disk images such as normal, damaged, cracked and dirty images. The method comprises the steps of positioning a target, then carrying out depth feature extraction, compared with the method of directly carrying out forward calculation by using one picture, randomly generating 10 patches on an original image, carrying out forward calculation on each patch, and carrying out averaging operation on obtained features. For the resulting multi-patch features, an SVM classifier is trained. Only the DCNN is used as a feature extractor, the test result far exceeds the manual features of BoF and the like, and the fault classification accuracy is over 95 percent.
The embodiment of the invention is based on a Deep Convolutional Neural Network (DCNN), can effectively extract the high-level semantic features of data through a hierarchical structure, and has been successfully applied to a plurality of computer vision fields. The DCNN is constructed by adopting new model structural elements such as a modified Linear Unit (ReLU), a Packed Convolutional Layer (PCL) and a Local Response Normalization (LRN) and is applied to the problem of insulator fault location. The embodiment of the invention adopts a simple, convenient and effective multi-model averaging method based on the same data enhancement program. And training each DCNN by adopting a direct regression mode. And combining a plurality of DCNNs in a multilayer cascade connection mode to improve the positioning precision of the insulator fault. The method solves the problem that the existing DCNN cascade algorithm is time-consuming in training, and improves the training speed by five times compared with a method of the same scale on the premise of not reducing the prediction precision. In the embodiment of the invention, an algorithm frame for migrating DCNN characteristics is adopted, DCNN trained on an insulator recognition task is migrated to the problem of insulator fault recognition and positioning, and DCNN is used as a characteristic extractor to be embedded into a local regularized cascade regression frame, so that the problem that DCNN cannot be directly trained due to insulator faults is solved. By solving the problems of complex structure and high computation complexity of a cascaded DCNN frame, the DCNN is constructed by Batch Normalization (BN) to inhibit the change of numerical value ranges input by each layer of the DCNN during training, so that the network is trained more quickly; and a multi-task learning mode is adopted, and the characteristics with stronger learning expression capability are learned under the constraint of multi-task supervision signals. And then migrating the DCNN to the insulator fault location problem. Finally, a single network can be adopted to directly position the insulator fault reference point, so that an algorithm frame is greatly simplified, a higher prediction speed is obtained, positioning accuracy similar to that of a cascaded DCNN method is obtained, and the extraction process of insulator fault information in inspection data is greatly improved.
The embodiment of the invention also provides a system for identifying the transmission line fault, and the system is used for executing the method shown in the figure 1.
The method and the system for the unmanned aerial vehicle power inspection operation can improve the efficiency of the power inspection operation, save labor cost and reduce the inspection risk of personnel. Through utilizing DCNN network as the feature extractor, patrolling and examining through unmanned aerial vehicle and adopting the algorithm to carry out the analysis of insulator fault information, promoted and patrolled and examined efficiency, also can be fast and accurate analysis and processing insulator fault information for the fault classification rate of accuracy of insulator fault information reaches more than 95%.
The above embodiments of the present invention are described in detail, and the principle and the implementation manner of the present invention should be described herein by using specific embodiments, and the above description of the embodiments is only used to help understanding the method of the present invention and the core idea thereof; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method for identifying a fault of a transmission line, the method comprising:
the unmanned aerial vehicle executes power inspection operation based on the automatic inspection operation script;
in the process of power inspection operation, identifying power inspection equipment based on inspection sensing equipment on an unmanned aerial vehicle, and adjusting relevant parameters of the inspection sensing equipment based on the power inspection equipment;
acquiring patrol data on the power patrol route based on the adjusted patrol sensing equipment;
and acquiring insulator fault information in the inspection data based on the DCNN.
2. The method of transmission line fault identification of claim 1, wherein the unmanned aerial vehicle performing power patrol operations based on the automatic patrol operation script comprises:
generating a simulation calculation result of the route planning into a kml file through a Matlab open source toolbox and a custom programming, and displaying point, line and surface element in the three-dimensional terrain of Google Earth through the kml file description;
and executing the power patrol operation based on the kml file.
3. The method of transmission line fault identification of claim 2, wherein the unmanned aerial vehicle performing power patrol operations based on the automatic patrol operation script further comprises:
and avoiding the obstacle in the flight path based on the autonomous obstacle avoidance system.
4. The method of transmission line fault identification of claim 3, wherein the avoiding obstacles in the flight path based on the autonomous obstacle avoidance system comprises:
the unmanned aerial vehicle obtains a depth image of the obstacle, accurately senses the specific contour of the obstacle based on the depth image, and achieves independent bypassing of the obstacle; and/or
The unmanned aerial vehicle establishes a map model for planning reasonable routes for the flight area and automatically bypasses the obstacles based on the reasonable routes.
5. The method of power transmission line fault identification according to claim 4, wherein identifying the power inspection equipment based on the inspection sensing equipment on the unmanned aerial vehicle and adjusting the relevant parameters of the inspection sensing equipment based on the power inspection equipment comprises:
and rapidly identifying the tower and the wire object, automatically correcting the shooting angle and adjusting the camera parameters.
6. The method for identifying faults of transmission lines according to claim 5, wherein the obtaining of the insulator fault information in the patrol data based on the deep convolutional neural network DCNN comprises:
extracting image data or video data in the inspection data;
performing information processing on the image data or the video data;
image preprocessing is carried out on the image data or the video data after the information processing;
performing insulator foreground extraction on the preprocessed image data or video data;
extracting insulator characteristics of the image data or the video data after the extraction processing of the insulator foreground based on an insulator extraction algorithm;
and detecting the insulator defects to acquire insulator fault information.
7. The method of transmission line fault identification according to claim 6, wherein said performing information processing on said image data or video data comprises:
performing color space conversion;
carrying out gray level image conversion;
acquiring pixel information;
histogram calculation is performed.
8. The method for identifying transmission line faults according to claim 7, wherein the image preprocessing of the image data or the video data after the information processing comprises:
carrying out histogram equalization;
carrying out gray level stretching treatment;
carrying out median filtering processing;
and performing morphological filtering processing.
9. The method for identifying transmission line faults according to claim 8, wherein the performing of the insulator foreground extraction on the preprocessed image data or video data comprises:
processing data based on an edge detection algorithm;
and processing data based on an image segmentation algorithm.
10. A system for transmission line fault identification, characterized in that the system is adapted to perform the method of any of claims 1 to 9.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011325240.0A CN112542800A (en) | 2020-11-24 | 2020-11-24 | Method and system for identifying transmission line fault |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011325240.0A CN112542800A (en) | 2020-11-24 | 2020-11-24 | Method and system for identifying transmission line fault |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112542800A true CN112542800A (en) | 2021-03-23 |
Family
ID=75014660
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011325240.0A Pending CN112542800A (en) | 2020-11-24 | 2020-11-24 | Method and system for identifying transmission line fault |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112542800A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113838056A (en) * | 2021-11-29 | 2021-12-24 | 中国电力科学研究院有限公司 | Power equipment joint detection and identification method, system, equipment and storage medium |
CN114123021A (en) * | 2021-11-05 | 2022-03-01 | 国网辽宁省电力有限公司铁岭供电公司 | Mountain area electric power facility flight inspection monitoring system and device based on power line |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105843253A (en) * | 2016-04-08 | 2016-08-10 | 北京博瑞空间科技发展有限公司 | Design method and system for unmanned aerial vehicle's travel path |
CN106780444A (en) * | 2016-12-01 | 2017-05-31 | 广东容祺智能科技有限公司 | A kind of insulator automatic identification analysis system |
CN107656545A (en) * | 2017-09-12 | 2018-02-02 | 武汉大学 | A kind of automatic obstacle avoiding searched and rescued towards unmanned plane field and air navigation aid |
CN108335294A (en) * | 2018-02-05 | 2018-07-27 | 贵州电网有限责任公司 | The power distribution room abnormality image-recognizing method of complex condition |
CN108614907A (en) * | 2016-12-12 | 2018-10-02 | 中国航空工业集团公司成都飞机设计研究所 | A kind of unmanned plane during flying course line and landform collision detection method |
CN110703800A (en) * | 2019-10-29 | 2020-01-17 | 国网江苏省电力有限公司泰州供电分公司 | Unmanned aerial vehicle-based intelligent identification method and system for electric power facilities |
-
2020
- 2020-11-24 CN CN202011325240.0A patent/CN112542800A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105843253A (en) * | 2016-04-08 | 2016-08-10 | 北京博瑞空间科技发展有限公司 | Design method and system for unmanned aerial vehicle's travel path |
CN106780444A (en) * | 2016-12-01 | 2017-05-31 | 广东容祺智能科技有限公司 | A kind of insulator automatic identification analysis system |
CN108614907A (en) * | 2016-12-12 | 2018-10-02 | 中国航空工业集团公司成都飞机设计研究所 | A kind of unmanned plane during flying course line and landform collision detection method |
CN107656545A (en) * | 2017-09-12 | 2018-02-02 | 武汉大学 | A kind of automatic obstacle avoiding searched and rescued towards unmanned plane field and air navigation aid |
CN108335294A (en) * | 2018-02-05 | 2018-07-27 | 贵州电网有限责任公司 | The power distribution room abnormality image-recognizing method of complex condition |
CN110703800A (en) * | 2019-10-29 | 2020-01-17 | 国网江苏省电力有限公司泰州供电分公司 | Unmanned aerial vehicle-based intelligent identification method and system for electric power facilities |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114123021A (en) * | 2021-11-05 | 2022-03-01 | 国网辽宁省电力有限公司铁岭供电公司 | Mountain area electric power facility flight inspection monitoring system and device based on power line |
CN113838056A (en) * | 2021-11-29 | 2021-12-24 | 中国电力科学研究院有限公司 | Power equipment joint detection and identification method, system, equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Liu et al. | High precision detection algorithm based on improved RetinaNet for defect recognition of transmission lines | |
Khan et al. | Unmanned aerial vehicle–based traffic analysis: Methodological framework for automated multivehicle trajectory extraction | |
WO2020103110A1 (en) | Image boundary acquisition method and device based on point cloud map and aircraft | |
CN113791641A (en) | Aircraft-based facility detection method and control equipment | |
CN112668696A (en) | Unmanned aerial vehicle power grid inspection method and system based on embedded deep learning | |
WO2021226900A1 (en) | Cotton crop row detection method and apparatus based on computer vision, and storage medium | |
Savva et al. | ICARUS: Automatic autonomous power infrastructure inspection with UAVs | |
CN112542800A (en) | Method and system for identifying transmission line fault | |
Xi et al. | A vision-based inspection strategy for large-scale photovoltaic farms using an autonomous UAV | |
CN115240089A (en) | Vehicle detection method of aerial remote sensing image | |
CN112327930A (en) | Routing inspection path determining method and device | |
CN112346481A (en) | Method and system for unmanned aerial vehicle power inspection operation | |
CN116843691B (en) | Photovoltaic panel hot spot detection method, storage medium and electronic equipment | |
CN117406789A (en) | Automatic planning method for multi-unmanned aerial vehicle bridge support inspection route based on image analysis | |
CN111339953A (en) | Clustering analysis-based mikania micrantha monitoring method | |
Majidi et al. | Real time aerial natural image interpretation for autonomous ranger drone navigation | |
CN112069997B (en) | Unmanned aerial vehicle autonomous landing target extraction method and device based on DenseHR-Net | |
Wang et al. | Online drone-based moving target detection system in dense-obstructer environment | |
Zou et al. | Research progresses and trends of power line extraction based on machine learning | |
CN115482277A (en) | Social distance risk early warning method and device | |
CN114842332A (en) | Stock position detection method and system | |
CN114217641A (en) | Unmanned aerial vehicle power transmission and transformation equipment inspection method and system in non-structural environment | |
CN117389311B (en) | Unmanned aerial vehicle autonomous obstacle surmounting method and device, electronic equipment and storage medium | |
Majidi et al. | Land Cover Boundary Extraction in Rural Aerial Videos. | |
Qu et al. | Research on UAV Image Detection Method in Urban Low-altitude Complex Background |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210323 |
|
RJ01 | Rejection of invention patent application after publication |