CN113610789A - Composite insulator pulverization identification method, terminal equipment and readable storage medium - Google Patents
Composite insulator pulverization identification method, terminal equipment and readable storage medium Download PDFInfo
- Publication number
- CN113610789A CN113610789A CN202110859551.3A CN202110859551A CN113610789A CN 113610789 A CN113610789 A CN 113610789A CN 202110859551 A CN202110859551 A CN 202110859551A CN 113610789 A CN113610789 A CN 113610789A
- Authority
- CN
- China
- Prior art keywords
- composite insulator
- pulverization
- image
- umbrella skirt
- powdering
- 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
- 239000012212 insulator Substances 0.000 title claims abstract description 108
- 239000002131 composite material Substances 0.000 title claims abstract description 93
- 238000010298 pulverizing process Methods 0.000 title claims abstract description 67
- 238000000034 method Methods 0.000 title claims abstract description 65
- 238000000227 grinding Methods 0.000 claims abstract description 36
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 230000005540 biological transmission Effects 0.000 claims abstract description 12
- 230000011218 segmentation Effects 0.000 claims abstract description 10
- 238000007689 inspection Methods 0.000 claims abstract description 8
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000004590 computer program Methods 0.000 claims description 22
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000013135 deep learning Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 238000012549 training Methods 0.000 claims description 4
- 238000003708 edge detection Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 3
- 238000012423 maintenance Methods 0.000 abstract description 2
- 230000006378 damage Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000000007 visual effect Effects 0.000 description 5
- 238000009413 insulation Methods 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 229920002379 silicone rubber Polymers 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 230000015556 catabolic process Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000006731 degradation reaction Methods 0.000 description 2
- 238000010410 dusting Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000002250 progressing effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000037353 metabolic pathway Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G06T5/10—Image enhancement or restoration using non-spatial domain filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
- G06T2207/20061—Hough transform
-
- 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
- G06T2207/20081—Training; Learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Insulators (AREA)
Abstract
The application belongs to the technical field of power transmission line maintenance, and particularly relates to a composite insulator pulverization identification method, terminal equipment and a readable storage medium. At present, the detection method of the pulverization of the composite insulator in China mainly adopts a method of manually controlling an unmanned aerial vehicle to shoot visible light pictures and then judging the pictures by the naked eyes of inspection personnel. The method has large workload, and different personnel have deviation on the judgment results of pulverization and grade. The application provides a composite insulator pulverization identification method, which comprises the following steps: the method comprises the steps of obtaining a composite insulator image, identifying a composite insulator in the image, obtaining a composite insulator outline image, carrying out umbrella skirt segmentation on the outline image by adopting an ellipse detection method to obtain a single umbrella skirt, carrying out image processing on the single umbrella skirt based on color characteristics, distinguishing a pulverization region from a non-pulverization region, and identifying the pulverization region. The problems that the current composite insulator powdering defect of the power transmission line is large in work load and difficult to judge the powdering severity are solved.
Description
Technical Field
The application belongs to the technical field of power transmission line maintenance, and particularly relates to a composite insulator pulverization identification method, terminal equipment and a readable storage medium.
Background
The insulator is an important element in a power transmission line, and has both insulation and mechanical supporting functions, and the silicon rubber composite insulator is widely applied since the 90 s of the 20 th century because of light weight, high strength and strong pollution flashover resistance. In the long-term service operation process of the silicon rubber composite insulator, pulverization and aging can occur due to high temperature and high humidity and the like. White powder appears on the surface of the powdered insulator, meanwhile, the hardness of the umbrella skirt is increased, the insulation and mechanical properties of the composite insulator are damaged, the umbrella skirt can be further damaged and the core rod can be further broken under severe conditions, and the transmission safety of a power transmission line is threatened.
At present, the detection method of the pulverization of the composite insulator in China mainly adopts a method of manually controlling an unmanned aerial vehicle to shoot visible light pictures and then judging the pictures by the naked eyes of inspection personnel. The method has large workload, and different personnel have deviation on the judgment results of pulverization and grade. And because there may be filth cover in the external world of pulverization layer, the probability of erroneous judgement caused by filth layer under the condition of manual judgement is higher.
Disclosure of Invention
1. Technical problem to be solved
The detection method based on the domestic composite insulator pulverization mainly adopts a method that an unmanned aerial vehicle is manually controlled to shoot visible light pictures, and then the pictures are judged by inspection personnel with naked eyes. The method has large workload, and different personnel have deviation on the judgment results of pulverization and grade. And because there may be dirty coverage in the external world of the pulverization layer, the problem that the probability of erroneous judgment caused by the dirty layer is high under the condition of manual judgment is provided.
2. Technical scheme
In order to achieve the above object, the present application provides a composite insulator chalking identification method, including: the method comprises the steps of obtaining a composite insulator image, identifying a composite insulator in the image, obtaining a composite insulator outline image, carrying out umbrella skirt segmentation on the outline image by adopting an ellipse detection method to obtain a single umbrella skirt, carrying out image processing on the single umbrella skirt based on color characteristics, distinguishing a pulverization region from a non-pulverization region, and identifying the pulverization region.
Another embodiment provided by the present application is: the composite insulator image is a visible light image, and the visible light image is a visible light image of the power transmission line inspection acquired based on a visible light camera carried by an unmanned aerial vehicle.
Another embodiment provided by the present application is: and identifying the composite insulator in the image comprises the step of inputting the visible light image into a deep learning identification model to identify the composite insulator, wherein the deep learning identification model is based on an improved MaskRCNN algorithm.
Another embodiment provided by the present application is: the ellipse detection method comprises the steps of adopting ellipse fitting in random Hough transform and segmenting each umbrella skirt through edge detection.
Another embodiment provided by the present application is: acquiring the composite insulator outline image, wherein the acquiring comprises constructing an image database with the composite insulator, and establishing a composite insulator mask layer for each composite insulator image; in the training process, the proportion of the detection anchor frames is set to be 4: 1; and realizing the pixel-level segmentation of the composite insulator outline by adopting a mask method.
Another embodiment provided by the present application is: the method comprises the steps of obtaining the ratio S of the powdering area on the umbrella skirt to the whole area of the umbrella skirt, obtaining the ratio L of the maximum distance from the powdering area of the umbrella skirt to the edge of the umbrella skirt to the radius of the umbrella skirt, and grading the powdering according to the S and the L.
Another embodiment provided by the present application is: if the L is more than four fifths, the shed is judged to be severely pulverized, if the L is less than four fifths, but the S is more than one half, the shed is judged to be moderately pulverized; if the L is less than four fifths and the S is more than one half, judging the umbrella skirt to be slightly pulverized; if L is 0, the insulator is not pulverized.
Another embodiment provided by the present application is: and the pulverization grade of the umbrella skirt with the most severe pulverization in the umbrella skirt is the pulverization grade of the composite insulator.
The present application also provides a terminal device including a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: the processor implements the method when executing the computer program.
The present application also provides a computer-readable storage medium storing a computer program characterized in that: the computer program realizes the method when being executed by a processor.
3. Advantageous effects
Compared with the prior art, the composite insulator pulverization identification method, the terminal equipment and the readable storage medium have the advantages that:
the composite insulator powdering identification method solves the problems that the current composite insulator powdering defect of the power transmission line is large in inspection workload and difficult to judge the powdering severity.
According to the composite insulator powdering identification method, the depth learning method based on the MaskRCNN algorithm can improve the identification accuracy rate and the positioning accuracy degree of the composite insulator, meanwhile, pixel-level image segmentation is achieved, and subsequent image processing is facilitated.
According to the composite insulator pulverization identification method, pulverization grade classification bases and method problems based on visual images are used for classifying the severity of damage to insulation and mechanical properties of the composite insulator according to pulverization and are realized by using an image algorithm.
The composite insulator powdering identification method provided by the application considers factors such as shooting conditions, powdering classification methods and powdering shielding performance, provides a set of complete powdered insulator identification and classification law, and improves the efficiency of field powdered insulator inspection.
The composite insulator pulverization identification method provided by the application can be used for identifying and judging classification of composite insulator pulverization defects of the power transmission line.
Drawings
FIG. 1 is a schematic view of a camera shooting angle and a viewing angle according to the present application;
FIG. 2 is a schematic view of a 4-angle shot of the present application;
FIG. 3 is a schematic diagram of the results of 4 angle shots of the present application;
fig. 4 is a schematic view of a visible light image of an aerial photograph of the drone of the present application;
FIG. 5 is a schematic diagram of a Mask RCNN Mask-based segmented image according to the present application;
FIG. 6 is a schematic illustration of the composite insulator of the present application for mild powdering;
FIG. 7 is a schematic illustration of moderate dusting of the composite insulator of the present application;
FIG. 8 is a schematic diagram of heavy dusting of a composite insulator of the present application;
fig. 9 is a schematic diagram illustrating the definition of the composite insulator powdering decision parameter according to the present application;
fig. 10 is a schematic structural diagram of a terminal device of the present application.
Detailed Description
Hereinafter, specific embodiments of the present application will be described in detail with reference to the accompanying drawings, and it will be apparent to those skilled in the art from this detailed description that the present application can be practiced. Features from different embodiments may be combined to yield new embodiments, or certain features may be substituted for certain embodiments to yield yet further preferred embodiments, without departing from the principles of the present application.
Firstly, the shooting angle and the height of the unmanned aerial vehicle carrying the visible light camera are regulated so as to fully acquire the disc surface information of the composite insulator string. Secondly, the problems of identification and accurate positioning of the composite insulator based on the visible light image shot by the unmanned aerial vehicle are solved, and the problems of low identification rate, inaccurate positioning frame and the like of the identification of the composite insulator in the deep learning method can directly influence the accuracy rate of pulverization identification. Then, the classification basis and method problem of the composite insulator pulverization grade is solved, no method for classifying the composite insulator pulverization grade completely based on visual image characteristics exists at present, and the classification basis is used for classifying the severity of the insulation and mechanical property damage of the composite insulator and realizing the classification by using an image algorithm. And then the problem that pulverization judgment is influenced by dirt shielding in the composite insulator pulverization visual identification process is solved.
Referring to fig. 1 to 10, the application provides a composite insulator chalking identification method, which includes: the method comprises the steps of obtaining a composite insulator image, identifying a composite insulator in the image, obtaining a composite insulator outline image, carrying out umbrella skirt segmentation on the outline image by adopting an ellipse detection method to obtain a single umbrella skirt, and distinguishing a pulverization region from a non-pulverization region by digital image processing technologies such as color gradient edge calculation and gray level processing on the single umbrella skirt based on color characteristics so as to identify pulverization.
Further, the composite insulator image is a visible light image, and the visible light image is a visible light image of the power transmission line inspection acquired based on a visible light camera carried by the unmanned aerial vehicle.
As shown in fig. 1 to 3, the shooting standard for setting the visible light camera carried by the unmanned aerial vehicle aims to acquire information of the umbrella skirt plate surface of the composite insulator as much as possible. The shooting distance is the safe distance corresponding to different power transmission line grades, the shooting height is equal to the height of the first umbrella skirt, and the shooting angle is properly overlooked, so that the first umbrella skirt is positioned at the upper edge of the picture. The composite insulator string is taken as an axis, the safety distance is taken as a radius, and the composite insulator string is taken once every 90 degrees, so that 4 pictures are obtained by the composite insulator string to completely reflect the pulverization information of the composite insulator.
Further, identifying the composite insulator in the image comprises inputting the visible light image into a deep learning identification model to identify the composite insulator, wherein the deep learning identification model is based on an improved MaskRCNN algorithm. The identification is performed using a modified MaskRCNN algorithm, the modifications including but not limited to anchor frame ratio setting to 4:1, optimizing functions in the position regression algorithm, etc. Compared with an unmodified algorithm, after the steps are improved, the accuracy of the method for insulator identification is improved.
Further, the ellipse detection method comprises the step of segmenting each umbrella skirt by edge detection by adopting ellipse fitting in random Hough (hough) transformation.
Further, acquiring the composite insulator outline image comprises constructing an image database with the composite insulator, and establishing the composite insulator mask layer for each composite insulator image; in the training process, the proportion of the detection anchor frames is set to be 4: 1; and realizing the pixel-level segmentation of the composite insulator outline. The whole MaskRCNN algorithm aims to realize the contour segmentation of the pixel-level insulator.
In order to realize the composite insulator recognition model based on deep learning with good detection effect, an image database with composite insulators is firstly constructed, and a mask layer of each image containing the composite insulators is established. The method is a necessary process of using a MaskRCNN method, and specifically, only when a mask layer is established when a database is established, a model can learn the mask characteristics of an insulator, and the mask segmentation effect can be achieved when the model is finally used. In the training process, the ratio of the detection anchor frame is set to be 4:1 so as to adapt to the slender shape of the composite insulator and improve the accuracy of the composite insulator. And (3) realizing the pixel-level segmentation of the composite insulator outline by adopting a mask method.
And further, obtaining the ratio S of the powdering area on the umbrella skirt to the whole area of the umbrella skirt, obtaining the ratio L of the maximum distance from the powdering area of the umbrella skirt to the edge of the umbrella skirt to the radius of the umbrella skirt, and grading the pulverization according to the S and the L.
Because the pulverization and aging are generated along with the increase of the hardness of the umbrella skirt, the harm caused by the pulverization progressing to the core rod is larger than the harm caused by the pulverization of the whole area, and the harm caused by the pulverization not progressing to the core rod is larger, so the judgment priority of the parameter L is higher than that of the parameter S during pulverization and classification.
Further, if L is more than four fifths, the shed is judged to be severely pulverized, if L is less than four fifths, and if S is more than one half, the shed is judged to be moderately pulverized; and if the L is less than four fifths of the total amount and the S is more than one half of the total amount, judging the umbrella skirt to be slightly pulverized. If L is 0 (and S is always 0), the insulator is not pulverized. Using S as a grading criterion: from the law of pulverization generation and development, pulverization firstly occurs at the edge of the umbrella skirt and the surface of the umbrella skirt, and when pulverization is further developed, the pulverization is developed from the edge of the umbrella skirt to the center of the umbrella skirt, and meanwhile, the pulverization is developed from the surface of the umbrella skirt to the depth of the thickness of the umbrella skirt. The above rules reflect the visual characteristics that the more severe the pulverization and the larger the pulverization area within the visual range of a circular umbrella skirt. The powdering occurs under conditions of high humidity, rainwater intrusion, etc., and rainwater, wind direction, etc. may cause uneven powdering of the umbrella skirt at 360 degrees in one turn. In extreme cases, the powdering is particularly severe in a direction that is more likely to develop towards the centre of the shed, i.e. the core rod sheath position. The degradation of the inner core rod can be accelerated by the pulverization and degradation of the silicon rubber on the surface of the sheath, so that the serious consequences of core rod fracture and insulator string drop are caused. Therefore, the pulverization is developed to the condition that the pulverization area of the core rod is small, the severity is larger than that of the pulverization area, but the pulverization progresses uniformly in different angles, and the pulverization is only limited to the condition of the umbrella skirt. Therefore, L is added as a ranking index, and the ranking priority of L is higher than that of S.
The parameter L is defined as shown in FIG. 9, and the maximum distance from the powdering area of the shed to the edge of the shed is L1Radius of the umbrella skirt is L0Maximum distance L between powdering area of umbrella skirt and edge of umbrella skirt1Is equal to the radius of the umbrella skirt0The ratio of L; the parameter S is defined as the ratio of the area of the whitish part in the picture to the area of the whole umbrella skirt.
Further, the pulverization grade of the umbrella skirt with the most severe pulverization in the umbrella skirts is the pulverization grade of the composite insulator.
The strategy for judging the powdering grade of the whole string of insulators is that the powdering layer is covered with a dirt layer, so that the powdering is concealed; however, for the whole string of insulators with the pollution layer, the pollution shielding degree of different umbrella skirts is not uniform, so that the piece with the most serious powdering degree in all the umbrella skirts of the whole string of insulators is used as the powdering grade of the whole string of insulators.
The present application further provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps in any of the method embodiments described above are implemented.
The terminal device of this embodiment includes: at least one processor (only one shown in fig. 10), a memory, and a computer program stored in the memory and executable on the at least one processor, the processor when executing the computer program implementing the steps in any of the various metabolic pathway prediction method embodiments described below.
The terminal device can be a desktop computer, a notebook, a palm computer, a cloud server and other computing devices. The terminal device may include, but is not limited to, a processor, a memory. Those skilled in the art will appreciate that the terminal device is merely an example, and does not constitute a limitation of the terminal device, and may include more or less components than those shown, or combine some components, or different components, such as input and output devices, network access devices, etc.
The Processor may be a Central Processing Unit (CPU), or other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The memory may in some embodiments be an internal storage unit of the terminal device, such as a hard disk or a memory of the terminal device. In other embodiments, the memory may also be an external storage device of the terminal device, such as a plug-in hard disk, a Smart Media Card (MC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the terminal device.
Further, the memory may also include both an internal storage unit and an external storage device of the terminal device. The memory is used for storing an operating system, application programs, a BootLoader (BootLoader), data, and other programs, such as program codes of the computer programs. The memory may also be used to temporarily store data that has been output or is to be output.
The embodiments of the present application further provide a computer-readable storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program implements the steps in the above-mentioned method embodiments.
The embodiments of the present application provide a computer program product, which when running on a terminal device, enables the terminal device to implement the steps in the above method embodiments when executed. The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium and can implement the steps of the embodiments of the methods described above when the computer program is executed by a processor. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include at least: any entity or device capable of carrying computer program code to a photographing apparatus/terminal apparatus, a recording medium, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), an electrical carrier signal, a telecommunications signal, and a software distribution medium. Such as a usb-disk, a removable hard disk, a magnetic or optical disk, etc. In certain jurisdictions, computer-readable media may not be an electrical carrier signal or a telecommunications signal in accordance with legislative and patent practice.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus/network device and method may be implemented in other ways. For example, the above-described apparatus/network device embodiments are merely illustrative, and for example, the division of the modules or units is only one logical division, and there may be other divisions when actually implementing, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not implemented. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application. In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art would appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
Claims (10)
1. A composite insulator pulverization identification method is characterized by comprising the following steps: the method comprises the following steps: the method comprises the steps of obtaining a composite insulator image, identifying a composite insulator in the image, obtaining a composite insulator outline image, carrying out umbrella skirt segmentation on the outline image by adopting an ellipse detection method to obtain a single umbrella skirt, carrying out image processing on the single umbrella skirt based on color characteristics, distinguishing a pulverization region from a non-pulverization region, and identifying the pulverization region.
2. The composite insulator powdering identification method according to claim 1, characterized in that: the composite insulator image is a visible light image, and the visible light image is a visible light image of the power transmission line inspection acquired based on a visible light camera carried by an unmanned aerial vehicle.
3. The composite insulator powdering identification method according to claim 2, characterized in that: and identifying the composite insulator in the image comprises the step of inputting the visible light image into a deep learning identification model to identify the composite insulator, wherein the deep learning identification model is based on an improved MaskRCNN algorithm.
4. The composite insulator powdering identification method according to claim 1, characterized in that: the ellipse detection method comprises the steps of adopting ellipse fitting in random Hough transform and segmenting each umbrella skirt through edge detection.
5. The composite insulator powdering identification method according to claim 3, characterized in that: acquiring the composite insulator outline image, wherein the acquiring comprises constructing an image database with the composite insulator, and establishing a composite insulator mask layer for each composite insulator image; in the training process, the proportion of the detection anchor frames is set to be 4: 1; and realizing the pixel-level segmentation of the composite insulator outline by adopting a mask method.
6. The composite insulator powdering identification method according to any one of claims 1 to 5, characterized by: the method comprises the steps of obtaining the ratio S of the powdering area on the umbrella skirt to the whole area of the umbrella skirt, obtaining the ratio L of the maximum distance from the powdering area of the umbrella skirt to the edge of the umbrella skirt to the radius of the umbrella skirt, and grading the powdering according to the S and the L.
7. The composite insulator powdering identification method according to claim 6, wherein: if the L is more than four fifths, the shed is judged to be severely pulverized, if the L is less than four fifths, but the S is more than one half, the shed is judged to be moderately pulverized; if the L is less than four fifths and the S is more than one half, judging the umbrella skirt to be slightly pulverized; if L is 0, the insulator is not pulverized.
8. The composite insulator powdering identification method according to claim 7, wherein: and the pulverization grade of the umbrella skirt with the most severe pulverization in the umbrella skirt is the pulverization grade of the composite insulator.
9. A terminal device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: the processor, when executing the computer program, implements the method of any of claims 1 to 8.
10. A computer-readable storage medium storing a computer program, characterized in that: the computer program when executed by a processor implements the method of any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110859551.3A CN113610789A (en) | 2021-07-28 | 2021-07-28 | Composite insulator pulverization identification method, terminal equipment and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110859551.3A CN113610789A (en) | 2021-07-28 | 2021-07-28 | Composite insulator pulverization identification method, terminal equipment and readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113610789A true CN113610789A (en) | 2021-11-05 |
Family
ID=78305831
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110859551.3A Pending CN113610789A (en) | 2021-07-28 | 2021-07-28 | Composite insulator pulverization identification method, terminal equipment and readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113610789A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109635A (en) * | 2023-04-12 | 2023-05-12 | 中江立江电子有限公司 | Method, device, equipment and medium for detecting surface quality of composite suspension insulator |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109781614A (en) * | 2019-03-29 | 2019-05-21 | 云南电网有限责任公司电力科学研究院 | A kind of method for comprehensive detection of composite insulator degree of aging |
| CN109900699A (en) * | 2019-03-27 | 2019-06-18 | 国网湖南省电力有限公司 | Method is determined based on the degree of aging of composite insulator powdering grading |
| CN110008901A (en) * | 2019-04-04 | 2019-07-12 | 天津工业大学 | A kind of insulator breakdown identification and localization method based on Mask R-CNN |
| CN110658193A (en) * | 2019-09-30 | 2020-01-07 | 国网湖南省电力有限公司 | Composite insulator umbrella skirt image acquisition device and method and pulverization grade detection method |
-
2021
- 2021-07-28 CN CN202110859551.3A patent/CN113610789A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109900699A (en) * | 2019-03-27 | 2019-06-18 | 国网湖南省电力有限公司 | Method is determined based on the degree of aging of composite insulator powdering grading |
| CN109781614A (en) * | 2019-03-29 | 2019-05-21 | 云南电网有限责任公司电力科学研究院 | A kind of method for comprehensive detection of composite insulator degree of aging |
| CN110008901A (en) * | 2019-04-04 | 2019-07-12 | 天津工业大学 | A kind of insulator breakdown identification and localization method based on Mask R-CNN |
| CN110658193A (en) * | 2019-09-30 | 2020-01-07 | 国网湖南省电力有限公司 | Composite insulator umbrella skirt image acquisition device and method and pulverization grade detection method |
Non-Patent Citations (3)
| Title |
|---|
| 刘建友;李宝树;仝卫国;: "航拍绝缘子图像的提取和识别", 传感器世界, no. 12, pages 1 - 3 * |
| 刘社民;叶强;黄桥林;盛从兵;冯盼增;李俊防;吴嘉敏;徐征;: "弧形核磁共振传感器设计及其在复合绝缘子老化状态检测中的应用", 波谱学杂志, no. 02 * |
| 郝永;李巍;: "现场复合绝缘子老化特征的研究", 黑龙江电力, no. 06 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116109635A (en) * | 2023-04-12 | 2023-05-12 | 中江立江电子有限公司 | Method, device, equipment and medium for detecting surface quality of composite suspension insulator |
| CN116109635B (en) * | 2023-04-12 | 2023-06-16 | 中江立江电子有限公司 | Method, device, equipment and medium for detecting surface quality of composite suspension insulator |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111428748B (en) | HOG feature and SVM-based infrared image insulator identification detection method | |
| CN104483326B (en) | High-voltage line defects of insulator detection method and system based on depth belief network | |
| US11361423B2 (en) | Artificial intelligence-based process and system for visual inspection of infrastructure | |
| CN111008961B (en) | Transmission line equipment defect detection method and system, equipment and medium thereof | |
| CN111381579A (en) | Cloud deck fault detection method and device, computer equipment and storage medium | |
| CN112367400B (en) | Intelligent inspection method and system for power internet of things with edge cloud coordination | |
| CN111292321A (en) | Method for identifying defect image of insulator of power transmission line | |
| CN113313107B (en) | Intelligent detection and identification method for multiple types of diseases on cable surface of cable-stayed bridge | |
| WO2020232710A1 (en) | Haze image quality evaluation method and system, storage medium, and electronic device | |
| CN110057828A (en) | A kind of surface inspecting method and system based on machine vision | |
| Zhang et al. | Automatic diagnosis system of transmission line abnormalities and defects based on UAV | |
| Jha et al. | l2‐norm‐based prior for haze‐removal from single image | |
| CN113888462A (en) | Crack identification method, system, readable medium and storage medium | |
| CN113610789A (en) | Composite insulator pulverization identification method, terminal equipment and readable storage medium | |
| CN112396016B (en) | Face recognition system based on big data technology | |
| CN116958035A (en) | Product part defect detection method, device, medium and electronic equipment | |
| CN111597900A (en) | Illegal dog walking identification method | |
| CN113643234B (en) | Composite insulator damage detection method, terminal equipment and readable storage medium | |
| CN112396572B (en) | Composite insulator double-light fusion method based on feature enhancement and Gaussian pyramid | |
| CN115272262A (en) | Outdoor insulator surface defect identification method and device and electronic equipment | |
| CN114998889A (en) | Intelligent identification method and system for immersive three-dimensional image | |
| CN110322431B (en) | Haze image quality evaluation method and system, storage medium and electronic equipment | |
| CN112733610A (en) | Power transmission line image recognition detection method based on unmanned aerial vehicle | |
| CN112435329A (en) | Power transmission equipment programmed modeling method and device based on laser point cloud data | |
| CN113361968A (en) | Power grid infrastructure worker safety risk assessment method based on artificial intelligence and big data |
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 |