CN115753801A - Power transmission line defect detection method based on knowledge graph technology - Google Patents
Power transmission line defect detection method based on knowledge graph technology Download PDFInfo
- Publication number
- CN115753801A CN115753801A CN202211519989.8A CN202211519989A CN115753801A CN 115753801 A CN115753801 A CN 115753801A CN 202211519989 A CN202211519989 A CN 202211519989A CN 115753801 A CN115753801 A CN 115753801A
- Authority
- CN
- China
- Prior art keywords
- image
- abnormal
- pictures
- power transmission
- transmission line
- 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
Images
Landscapes
- Electric Cable Installation (AREA)
Abstract
The invention provides a power transmission line defect detection method based on a knowledge graph technology, which comprises the following steps of: s1: acquiring an image of the line, positioning and marking the image, and transmitting the image back to a background; s2: performing preliminary content analysis on the pictures transmitted back to the background, and classifying and naming the pictures according to the analysis result; s3: extracting power components in the image based on the intelligent map, analyzing and detecting the power components in the image, and judging whether the circuit in the image is abnormal or not; s4: reading the geographical position of the abnormal image, recording the abnormal condition of the line in the image, and transmitting the geographical position and the abnormal condition of the line to the mobile equipment; s5: and storing the pictures into a database according to the classification names of the abnormal images. The invention extracts the circuit components in the picture by using the knowledge graph, and then analyzes different abnormal conditions by using different image processing modes in a targeted manner, thereby improving the intelligent degree of the system and the accuracy of the abnormal analysis.
Description
Technical Field
The invention relates to the field of power transmission line inspection, in particular to a power transmission line defect detection method based on a knowledge graph technology.
Background
The safe operation of the transmission line is the basis of stable transmission of electric power energy. In recent years, with the change of climate and environment and the increase of line corridors, the operation state of the transmission tower itself has become the focus of line operation and maintenance work. The intelligent inspection system has the advantages that inspection benefits, efficiency and quality are comprehensively improved, operation and maintenance cost is greatly reduced, operation and inspection mode conversion and industry upgrading are promoted, intelligent operation and inspection is realized, and the intelligent inspection system is a necessary route for building and developing a smart power grid.
With the rapid development of advanced technologies such as big data, cloud computing, internet of things, mobile internet, artificial intelligence and the like, the national power grid company actively upgrades the operation and maintenance mode, develops from the traditional artificial operation and maintenance to the operation and maintenance of 'intellectualization + synergetic three-dimensional', and brings the unmanned aerial vehicle inspection operation into lean assessment indexes of the power transmission line. In recent years, unmanned aerial vehicle inspection becomes an important inspection means of power transmission lines, and inspection benefits and quality are remarkably improved compared with traditional manual inspection.
However, the existing power transmission line inspection mode still has several disadvantages and short boards in practical application. The processing of mass data generated by inspection consumes a large amount of manpower and has low efficiency, and mass unmanned aerial vehicle inspection data generated by production inspection does not have uniform acquisition and storage specifications; original handheld equipment is patrolled and examined and is patrolled and examined at image quality and collection angle mode etc. and there is not unified adaptation and management and control.
Disclosure of Invention
Aiming at the technical problems that the existing inspection method is low in efficiency and consumes a large amount of manpower, the invention provides the power transmission line defect detection method based on the knowledge graph technology, and the intelligent graph is used for analyzing the inspection line picture, so that the manpower cost is reduced, and the efficiency and the accuracy of line inspection are improved.
In order to achieve the purpose, the technical scheme of the invention is realized as follows: the power transmission line defect detection method based on the knowledge graph technology comprises the following steps:
s1: acquiring an image of the line, positioning and marking the image, and transmitting the image back to a background;
s2: performing preliminary content analysis on the pictures transmitted back to the background, and classifying and naming the pictures according to the analysis result;
s3: extracting power components in the image based on the intelligent map, analyzing and detecting the power components in the image, and judging whether the circuit in the image is abnormal or not;
s4: reading the geographic position of the abnormal image, recording the abnormal condition of the line in the image, and transmitting the geographic position and the abnormal condition of the line to the mobile equipment;
s5: and classifying and storing the pictures into the database according to the names of the abnormal pictures in S2.
The method for performing preliminary content analysis on the picture transmitted back to the background in the step S2 comprises the following steps: and comparing the pictures to be classified with the pictures in the database, and classifying the pictures with higher content similarity into a group and naming the group by utilizing clustering analysis.
In the step S2, the pictures are divided into five types, namely tower head, ground wire, upper, middle and lower three phases, insulator hanging points and linearity.
In step S3, the method for analyzing and detecting the power component in the image and determining whether the line in the image is abnormal includes:
s31: firstly, extracting power components in an image based on a knowledge graph, then carrying out color filtering on the image, judging whether a circuit has defects caused by chemical reasons or not, and detecting whether foreign matters exist around the circuit or not;
s32: then, carrying out gray level conversion and binarization on the picture, and judging the accurate position of the line part;
s33: detecting whether the line is damaged or not by using a shape invariant moment method;
s34: and judging whether parts are missing or not by using a particle filter algorithm.
The defect caused by the chemical cause in step S31 includes corrosion, rusting, or arc burn.
The method for judging the accurate position of the line part in the step S32 is as follows: and analyzing and positioning the position of the part in the picture by using a density-based clustering algorithm.
And step S34, the parts are parts with periodic and symmetrical distribution in the circuit.
The invention has the beneficial effects that: according to the method, firstly, the pictures collected in the line inspection are analyzed and classified by using cluster analysis, then, circuit components in the pictures are extracted by using the knowledge graph according to different possible abnormal conditions, and then different abnormal conditions are analyzed by using different image processing modes in a targeted manner, so that the intelligent degree of the system and the accuracy of the abnormal analysis are improved. Meanwhile, the method provided by the invention needs no manual intervention in other steps except for manually checking whether the abnormality exists when the last abnormal information is transmitted to the detector, so that the labor cost is greatly reduced, and the inspection analysis efficiency is improved.
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 embodiments or the prior art descriptions will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a schematic flow chart of the present invention.
FIG. 2 is a flowchart illustrating step S3 according to the present 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 obtained by a person skilled in the art without inventive effort based on the embodiments of the present invention, are within the scope of the present invention.
As shown in fig. 1, the method for detecting the defect of the power transmission line based on the knowledge-graph technology is characterized in that: the method comprises the following steps:
s1: the method comprises the steps of utilizing a camera or an unmanned aerial vehicle to collect images of a line needing to be patrolled and examined, collecting photographing places while photographing, carrying out positioning marking on the images, and transmitting the images and positioning information back to a background.
S2: and performing preliminary content analysis on the pictures transmitted back to the background, comparing the pictures to be classified with the pictures in the database, and classifying the pictures with higher content similarity into a group and naming the pictures by utilizing cluster analysis. Specifically, in the step S2, the picture is divided into five types, namely tower head, ground wire, upper, middle and lower three phases, insulator hanging point and linearity.
S3: and analyzing and detecting the content of the image, and judging whether the line in the image is abnormal or not. As shown in fig. 2, the method for analyzing and detecting the content of the image and determining whether the line in the image is abnormal includes:
s31: the method comprises the steps of extracting power components in a picture based on a knowledge graph, then carrying out color filtering on the picture, judging whether the circuit has defects caused by chemical reasons, such as circuit corrosion, corrosion or arc burn, and the like, and detecting whether foreign matters, such as advertisement banners, bird nests and the like, exist around the circuit, so that the circuit damage caused by the fact that the foreign matters scratch the circuit is prevented from causing fire.
S32: secondly, carrying out gray level conversion and binarization on the picture, analyzing the picture by using a density-based clustering algorithm, and searching an area close to the density distribution of the power component according to the density distribution of the graph in the image to judge the area as the accurate position of the line component;
s33: extracting the characteristics of the power component by using a shape invariant moment method, identifying the power component in the picture, and detecting whether the circuit is damaged;
s34: the particle filter algorithm is used for extracting high-weight particles from the image, accurately identifying the electric power component in the image, and comparing whether symmetrical and periodic parts such as insulators and damper on the line have defects.
S4: when the circuit shot in the sent image is analyzed to be abnormal, the background reads the geographical position written in the abnormal image memory, records the abnormal condition of the circuit in the image, transmits the geographical position and the abnormal condition of the circuit to the mobile equipment, and manually confirms whether the abnormal condition exists by a detection worker; if the system judges that the alarm is wrong, the detector receiving the message can manually eliminate the abnormal alarm.
S5: and after the abnormity warning is sent, the background stores the pictures into the database in a classified manner according to the names of the abnormal images in the S2.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (7)
1. The power transmission line defect detection method based on the knowledge graph technology is characterized by comprising the following steps: the method comprises the following steps:
s1: acquiring an image of the line, positioning and marking the image, and transmitting the image back to a background;
s2: performing preliminary content analysis on the pictures transmitted back to the background, and classifying and naming the pictures according to the analysis result;
s3: extracting power components in the image based on the intelligent map, analyzing and detecting the power components in the image, and judging whether the circuit in the image is abnormal or not;
s4: reading the geographical position of the abnormal image, recording the abnormal condition of the line in the image, and transmitting the geographical position and the abnormal condition of the line to the mobile equipment;
s5: and classifying and storing the pictures into the database according to the names of the abnormal pictures in S2.
2. The power transmission line defect detection method based on the knowledge-graph technology according to claim 1, characterized in that: the method for performing the preliminary content analysis on the picture transmitted back to the background in the step S2 comprises the following steps: and comparing the pictures to be classified with the pictures in the database, and dividing the pictures with higher content similarity into a group by utilizing clustering analysis and naming the group.
3. The power transmission line defect detection method based on the knowledge graph technology according to claim 2, characterized in that: in the step S2, the pictures are divided into five types, namely tower head, ground wire, upper, middle and lower three phases, insulator hanging points and linearity.
4. The power transmission line defect detection method based on the knowledge-graph technology according to claim 1 or 3, characterized in that: in step S3, the method for analyzing and detecting the power component in the image and determining whether the line in the image is abnormal includes:
s31: firstly, extracting power components in an image based on a knowledge graph, then carrying out color filtering on the image, judging whether a circuit has defects caused by chemical reasons, and detecting whether foreign matters exist around the circuit;
s32: then, carrying out gray level conversion and binarization on the picture, and judging the accurate position of the line part;
s33: detecting whether the line is damaged or not by using a shape invariant moment method;
s34: and judging whether parts are missing or not by using a particle filter algorithm.
5. The power transmission line defect detection method based on the knowledge graph technology according to claim 4, characterized in that: the defect caused by the chemical cause in step S31 includes corrosion, rusting, or arc burn.
6. The power transmission line defect detection method based on the knowledge-graph technology according to claim 5, characterized in that: the method for judging the accurate position of the line part in the step S32 includes: and analyzing and positioning the position of the part in the picture by using a density-based clustering algorithm.
7. The power transmission line defect detection method based on the knowledge-graph technology according to claim 5 or 6, characterized in that: and step S34, the parts are parts with periodic and symmetrical distribution in the circuit.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211519989.8A CN115753801A (en) | 2022-11-30 | 2022-11-30 | Power transmission line defect detection method based on knowledge graph technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211519989.8A CN115753801A (en) | 2022-11-30 | 2022-11-30 | Power transmission line defect detection method based on knowledge graph technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115753801A true CN115753801A (en) | 2023-03-07 |
Family
ID=85341537
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211519989.8A Pending CN115753801A (en) | 2022-11-30 | 2022-11-30 | Power transmission line defect detection method based on knowledge graph technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115753801A (en) |
-
2022
- 2022-11-30 CN CN202211519989.8A patent/CN115753801A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108037133B (en) | Intelligent electric power equipment defect identification method and system based on unmanned aerial vehicle inspection image | |
| CN111949809B (en) | Intelligent processing method for infrared inspection data of power transmission line | |
| US11361423B2 (en) | Artificial intelligence-based process and system for visual inspection of infrastructure | |
| CN109344753A (en) | A kind of tiny fitting recognition methods of Aerial Images transmission line of electricity based on deep learning | |
| CN108872781B (en) | Analysis method and device based on intelligent inspection of electric power facilities | |
| CN111709361B (en) | Method for processing inspection data of unmanned aerial vehicle of power transmission line | |
| CN110567964B (en) | Method and device for detecting defects of power transformation equipment and storage medium | |
| CN108680833B (en) | Composite insulator defect detection system based on unmanned aerial vehicle | |
| CN111080691A (en) | Infrared hot spot detection method and device for photovoltaic module | |
| CN115395646B (en) | Intelligent operation and maintenance system of digital twin traction substation | |
| CN113610749A (en) | Fan blade defect detection method based on neural network | |
| CN113255590A (en) | Defect detection model training method, defect detection method, device and system | |
| CN112697798A (en) | Infrared image-oriented diagnosis method and device for current-induced thermal defects of power transformation equipment | |
| CN112683916A (en) | Method and device for identifying missing or mounting error of small hardware fittings of current collecting line tower | |
| CN112184903A (en) | Method, device, equipment and medium for detecting high-voltage line tree obstacle risk points | |
| CN115753801A (en) | Power transmission line defect detection method based on knowledge graph technology | |
| CN111862023A (en) | Pantograph structure abnormity detection method based on computer vision | |
| CN115187880A (en) | Communication optical cable defect detection method and system based on image recognition and storage medium | |
| CN113362630B (en) | Traffic signal equipment fault analysis processing method, system and computer storage medium | |
| CN115494871A (en) | Unmanned aerial vehicle inspection method, device and system for power transmission line abnormity | |
| CN110826473A (en) | Neural network-based automatic insulator image identification method | |
| CN113034021A (en) | Power transmission line defect analysis method and system based on machine patrol data | |
| CN113744179A (en) | Hardware defect detection method on power transmission and distribution line | |
| CN117612047B (en) | Unmanned aerial vehicle inspection image recognition method for power grid based on AI large model | |
| CN113573169B (en) | Unmanned aerial vehicle distribution box data reading and detecting method and system |
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 |