CN113808081A - Transmission line small-size gold utensil defect detecting system - Google Patents
Transmission line small-size gold utensil defect detecting system Download PDFInfo
- Publication number
- CN113808081A CN113808081A CN202110935558.9A CN202110935558A CN113808081A CN 113808081 A CN113808081 A CN 113808081A CN 202110935558 A CN202110935558 A CN 202110935558A CN 113808081 A CN113808081 A CN 113808081A
- Authority
- CN
- China
- Prior art keywords
- transmission line
- power transmission
- small
- image
- defect
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 116
- 230000005540 biological transmission Effects 0.000 title claims abstract description 115
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 title description 8
- 239000010931 gold Substances 0.000 title description 8
- 229910052737 gold Inorganic materials 0.000 title description 8
- 238000001514 detection method Methods 0.000 claims abstract description 74
- 238000004891 communication Methods 0.000 claims abstract description 32
- 238000003745 diagnosis Methods 0.000 claims abstract description 7
- 238000007781 pre-processing Methods 0.000 claims description 18
- 238000012549 training Methods 0.000 claims description 18
- 230000010354 integration Effects 0.000 claims description 13
- 238000012545 processing Methods 0.000 claims description 12
- 238000013508 migration Methods 0.000 claims description 11
- 230000005012 migration Effects 0.000 claims description 11
- 238000013135 deep learning Methods 0.000 claims description 10
- 238000005457 optimization Methods 0.000 claims description 8
- 238000002372 labelling Methods 0.000 claims description 6
- 238000001931 thermography Methods 0.000 claims description 6
- 238000013136 deep learning model Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 238000009877 rendering Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 238000013526 transfer learning Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 230000004927 fusion Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000013473 artificial intelligence Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000000034 method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000004643 material aging Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 230000000007 visual effect 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
- G06N3/04—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
- G06T5/50—Image enhancement or restoration by the use of more than one image, e.g. averaging, subtraction
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- 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
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
Abstract
The invention provides a small-size hardware defect detection system for a power transmission line, which comprises an unmanned aerial vehicle and a ground control center, wherein the unmanned aerial vehicle acquires image information of the power transmission line and then sends the image information to the ground control center; the ground control center includes: the ground communication unit is used for receiving the image information of the power transmission line sent by the data acquisition device; the defect identification device is provided with a defect detection model unit, a preset transmission line small-size hardware defect detection model is stored in the defect detection model unit, and the preset transmission line small-size hardware defect detection model is used for identifying the image information received by the ground communication unit; and the early warning device executes alarm when the identification result of the defect identification device indicates that the defect exists. The invention can improve the accuracy of the abnormity diagnosis and the defect identification of the small-size hardware fitting of the power transmission line while releasing manpower.
Description
Technical Field
The invention relates to the technical field of defect detection of power transmission lines of power grids, in particular to a small-size hardware defect detection system of a power transmission line.
Background
Transmission of electricity is an important component of a power grid, and because transmission lines have large span and are easily damaged by natural environment and human factors, detection of the transmission lines gradually becomes an important component of construction of the transmission links, and the method is also an important technical means for realizing maintenance and management of the operation state of the transmission lines and improving the lean management level of production operation.
In recent years, the detection modes of the power transmission line can be roughly divided into the following three types:
firstly, traditional artifical line detection mode of patrolling is by examining and repairing the workman and regularly patrolling the circuit, and whether there is the abnormal conditions in the discovery circuit through the visual observation.
Secondly, by means of the camera equipment, a camera is installed on the power transmission line tower, image information of the power transmission line is collected through the camera, the image information is transmitted back to a power transmission line monitoring management background of the power company in a wireless communication mode, and then the collected monitoring image information is observed by a maintenance worker to manually judge whether the power transmission line has an abnormal phenomenon.
Thirdly, an unmanned aerial vehicle is used for polling and shooting images of the power transmission line, meanwhile, an intelligent identification platform of the images of the power transmission line is built at the power company end, the images are exported after the unmanned aerial vehicle finishes the line patrol, and the defect identification of the power transmission line is carried out by using an image intelligent identification technology based on artificial intelligence.
In the first and second detection modes, the manual participation degree is high, the efficiency is low, the workload of personnel is high, and the condition of missed detection is easy to occur in long-time work. With the development of science and technology, the defect identification of the power transmission line by using unmanned aerial vehicle inspection and an image intelligent identification technology based on artificial intelligence gradually replaces artificial inspection and artificial judgment, and becomes the main mode of the defect detection of the current power transmission line.
The small-size hardware fitting in the power transmission line mainly comprises a bolt, a nut and a pin. The bolt, the nut and the pin play a role in connecting key components in the power transmission line, and are exposed in an external environment for a long time and affected by factors such as human factors, severe weather, mechanical tension, material aging and the like, so that the defects of corrosion, looseness, loss, pin falling, improper pin installation and the like can be caused, and the defects can directly cause component deformation, instability and even power failure accidents.
At present, when utilizing current unmanned aerial vehicle to patrol and examine the mode and come the small-size gold utensil defect in the transmission line and discern, because the shared pixel of small-size gold utensil is less in the image of gathering, belong to small target object, and there are a large amount of small-size gold utensils on transmission line and the shaft tower, so hardly carry out the accurate discernment of small-size gold utensil defect under the background of so complicacy, the less gold utensil defect target detection effect of size can't satisfy actual application demand promptly, transmission line unmanned aerial vehicle's the mode of patrolling and examining at present stage has small-size gold utensil defect to detect the rate of accuracy low, miss report rate and the also higher drawback of false positive rate.
Disclosure of Invention
The invention aims to provide a system for detecting the defects of small-size hardware fittings of a power transmission line, which can solve the problems of low detection accuracy rate, high missing report rate and high false report rate of the small-size hardware fittings in the prior art.
The purpose of the invention is realized by the following technical scheme:
the invention provides a small-size hardware defect detection system for a power transmission line, which is characterized by comprising an unmanned aerial vehicle and a ground control center, wherein the unmanned aerial vehicle is provided with a data acquisition device, and the ground control center is provided with a data processing system; the data acquisition device acquires image information of the power transmission line and then sends the image information to the data processing system; the data processing system includes:
the ground communication unit is used for receiving the image information of the power transmission line sent by the data acquisition device;
the defect identification device is provided with a defect detection model unit, a preset transmission line small-size hardware defect detection model is stored in the defect detection model unit, and the preset transmission line small-size hardware defect detection model is used for identifying the image information received by the ground communication unit;
and the early warning device executes alarm when the identification result of the defect identification device indicates that the defect exists.
Furthermore, the data processing system also comprises an image preprocessing unit, wherein the image preprocessing unit is connected between the ground communication unit and the defect identification device, and is used for preprocessing the image information received by the ground communication unit and then sending the image information to the defect identification device for defect identification.
Further, the defect detection model unit includes a virtual-real integration subunit, a migration learning subunit, and a model training subunit, wherein:
the virtual-real integration subunit is used for constructing a virtual sample generation and labeling model of virtual-real integration and fusing virtual data and real data;
the migration learning subunit migrates the virtual sample generation and labeling model integrated with the virtual and the real to the actual data training, realizes the migration learning based on the deep learning framework, and performs the source task of the virtual data learning model and then performs the target task of the actual data learning optimization model to realize the model optimization based on the migration learning;
the model training subunit is used for training a deep learning model based on a target detection algorithm and carrying out abnormity diagnosis on the small-size hardware fitting of the power transmission line on the basis of target detection of deep learning.
Further, the acquisition device comprises a control unit, an image acquisition unit and a wireless communication unit; the control unit is used for controlling the image acquisition unit and the wireless communication unit to work; the image acquisition unit is used for acquiring image information of the power transmission line, and the wireless communication unit is in communication connection with the ground communication unit, so that communication connection and data transmission between the unmanned aerial vehicle and the ground control center are realized.
Further, the image acquisition unit comprises a double-optical camera, the double-optical camera comprises a visible light camera and an infrared light camera, the visible light camera is used for shooting a scene picture of the power transmission line, and the infrared light camera is used for acquiring an infrared thermal imaging image of the power transmission line.
Further, an image current pushing processor is arranged in the dual-optical camera and used for fusing, superposing and rendering the scene picture of the power transmission line and the infrared thermal imaging image to generate a rendered image so as to realize single-line transmission of the image.
Further, the preprocessing includes image enhancement, noise filtering and threshold segmentation.
According to the system for detecting the defects of the small-size hardware fittings of the power transmission line, disclosed by the invention, the defect detection model of the small-size hardware fittings of the power transmission line based on the fusion of multiple images such as visible light, infrared and the like is established by carrying out deep learning distributed training on image samples and utilizing a transfer learning technology, so that the influence of large background and small target adverse factors of the small-size hardware fittings of the power transmission line patrolled by an unmanned aerial vehicle on patrolling the small-size hardware fittings can be overcome. Meanwhile, the accuracy of the abnormity diagnosis and the defect identification of the small-size hardware fitting of the power transmission line can be improved under the condition that the scale of the training data is insufficient.
The detection system acquires the image information of the power transmission line through the image acquisition unit, then detects and identifies the acquired image information of the power transmission line through the defect detection model of the small-size hardware fitting of the power transmission line preset in the defect identification device to obtain the defect identification result of the small-size hardware fitting of the power transmission line, and executes corresponding early warning through the early warning device under the condition that the defect identification result of the small-size hardware fitting shows that the defect characteristics exist, so that the detection and the defect identification of the small-size hardware fitting of the power transmission line are realized, manpower is liberated, and the detection efficiency and the quality of the defects of the small-size hardware fitting of the power transmission line are improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is an architecture diagram of the small-size hardware defect detection system for the power transmission line of the invention.
Detailed Description
The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
The embodiments of the present disclosure are described below with specific examples, and other advantages and effects of the present disclosure will be readily apparent to those skilled in the art from the disclosure in the specification. It is to be understood that the described embodiments are merely illustrative of some, and not restrictive, of the embodiments of the disclosure. The disclosure may be embodied or carried out in various other specific embodiments, and various modifications and changes may be made in the details within the description without departing from the spirit of the disclosure. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
The small-size hardware defect detection system for the power transmission line comprises an unmanned aerial vehicle and a ground control center, wherein the unmanned aerial vehicle is provided with a data acquisition device 1, and the ground control center is provided with a data processing system 2.
The data acquisition device 1 comprises a control unit 11, an image acquisition unit 12 and a wireless communication unit 13. The control unit 11 is used for controlling the image acquisition unit 12 and the wireless communication unit 13 to work; the image acquisition unit 12 is configured to acquire image information of the power transmission line, the image acquisition unit 12 includes a dual-optical camera, the dual-optical camera includes a visible light camera and an infrared camera, the visible light camera is configured to capture a scene picture of the power transmission line, and the infrared camera is configured to acquire an infrared thermal imaging image of the power transmission line (by sensing infrared radiation energy of the power transmission line); the wireless communication unit 13 is used for realizing communication connection and data transmission between the unmanned aerial vehicle and the ground control center, and comprises data transmission of the image acquisition unit 12, control instruction reception of the data processing system 2 and the like.
The image current pushing processor is arranged in the double-light camera and used for fusing, superposing and rendering the scene picture of the power transmission line and the infrared thermal imaging picture to generate a rendered image so as to realize single-line transmission of the image, thereby facilitating quick transmission and improving efficiency.
The data processing system 2 comprises a defect detection model unit 21, wherein the defect detection model unit 21 is used for constructing a defect detection model of the small-size hardware fitting of the power transmission line based on virtual and real sample integration and transfer learning according to image sample data of the small-size hardware fitting of the power transmission line so as to diagnose the abnormity of the small-size hardware fitting of the power transmission line.
The image sample data of the small-size hardware fittings of the power transmission line comprises sample data of visible light, infrared light and the like, the sample data comprises normal annotation images and annotation images with defects, the image sample data comprises multi-source images of all types of small-size hardware fittings, and the number of the image samples of each type of small-size hardware fittings can meet the requirement of deep learning network training.
The small-size hardware defect detection model of the power transmission line based on virtual and real sample integration and transfer learning can realize a learning mode that a source task of target recognition in a virtual scene is transferred to a target task of real scene recognition, can realize automatic sample marking and iterative incremental learning of small-size hardware, reduces the workload of manually marking a training data set, liberates manpower, and can improve overfitting caused by too little defect data.
The defect detection model unit 21 includes a virtual-real integration subunit 211, a migration learning subunit 212, and a model training subunit 213.
The virtual-real integration subunit 211 is configured to construct a virtual sample generation and labeling model for virtual-real integration, and is configured to integrate abundant surface feature information in virtual data and real image data, so as to implement effective fusion of the virtual data and the real data.
The transfer learning subunit 212 is configured to construct a deep learning transfer learning model, and implement model optimization based on transfer learning. Specifically, after a virtual sample generation and labeling model of virtual-real integration is constructed, the model is migrated to actual data training, migration learning is realized based on a deep learning framework, a source task of the virtual data learning model is firstly performed, and then a target task of the actual data learning optimization model is performed, so that model optimization based on the migration learning is realized.
The model training subunit 213 is configured to train a deep learning model based on a target detection algorithm, and perform abnormality diagnosis on the small-size hardware fitting of the power transmission line based on the target detection of the deep learning. The target detection algorithm comprises TensorFlow, FasterR-CNN, SSD and other algorithms. The deep learning model comprises a defect target detection model, a multi-model integrated learning model and a fusion detection model which are respectively constructed according to visible light image sample data and infrared image sample data, model training and parameter adjustment optimization are completed, and finally a defect detection model of the small-size hardware fitting of the power transmission line is output, so that the abnormal diagnosis and the online intelligent defect identification of the small-size hardware fitting of the power transmission line are realized.
According to the system, the image samples are subjected to deep learning distributed training, a visible light, infrared and other multi-image fusion-based defect detection model of the small-size hardware fitting of the power transmission line is established by using a transfer learning technology, the accuracy of abnormity diagnosis and defect identification of the small-size hardware fitting of the power transmission line can be improved under the condition that the training data scale is insufficient, and the detection efficiency and quality of routing inspection work are also improved.
The data processing system 2 further comprises a ground communication unit 22 for connecting and communicating with the wireless communication unit 13, a defect identification device 23, and an early warning device 24.
The defect detection model unit 21 is in communication connection with the image acquisition unit 12 through a communication unit, and is configured to receive and detect image information of the power transmission line transmitted by the image acquisition unit 12, where the defect detection model unit 21 is configured in the defect identification device 23, that is, a preset defect detection model for small-sized hardware fittings of the power transmission line is configured in the defect identification device 23. The defect recognition device 23 obtains a defect recognition result of the small-size hardware fitting of the power transmission line based on the image information of the small-size hardware fitting of the power transmission line transmitted by the image acquisition unit 12 and a preset defect detection model of the small-size hardware fitting of the power transmission line. The defect recognition device 23 is used for performing online defect detection by using the trained and tested defect detection model, and recognizing and marking the defect hardware in the detected image.
But above-mentioned defect recognition device 23 automatic analysis transmission line's monitoring image to can avoid traditional artifical line and camera to shoot, the artifical intelligent degree not enough problem of judging the detection mode of manual work.
The early warning device 24 is connected to the defect identification device 23, and the early warning device 24 is configured to execute corresponding early warning when the defect identification result of the small-sized hardware fitting indicates that the defect feature exists. The early warning form is to generate an early warning list and send out an alarm.
After the image information of the power transmission line is obtained, the obtained image information can be preprocessed, so that the defect detection model can effectively detect and identify the image information. For this purpose, an image preprocessing unit may be provided in the defect recognition device 23 to perform the corresponding preprocessing operations. Namely, the defect identification device 23 is further provided with an image preprocessing unit 25, an input end of the image preprocessing unit 25 is connected with the image acquisition unit 12, an output end of the image preprocessing unit 25 is connected with the defect detection model unit 21, and the image preprocessing unit 25 is configured to preprocess image information of the power transmission line and send the preprocessed image information of the power transmission line to the defect detection model unit 21, so that the defect detection model can perform effective detection and identification. Specifically, the preprocessing operation includes image enhancement, noise filtering, threshold segmentation and other technical means.
The detection system collects the image information of the power transmission line through the image collection unit, then detects and identifies the collected image information of the power transmission line through the defect detection model of the small-size hardware fitting of the power transmission line preset in the defect identification device to obtain the defect identification result of the small-size hardware fitting of the power transmission line, and executes corresponding early warning through the early warning device under the condition that the defect identification result of the small-size hardware fitting shows that defect characteristics exist, so that the detection and defect identification of the small-size hardware fitting of the power transmission line are realized, manpower is liberated, and meanwhile, the detection efficiency of the defect of the small-size hardware fitting of the power transmission line and the accuracy of the defect identification are improved.
The working process of the detection system is as follows:
firstly, a defect detection model unit 21 in the system constructs a defect detection model of the small-size hardware fitting of the power transmission line based on virtual and real sample integration and transfer learning according to image sample data of the small-size hardware fitting of the power transmission line, so that the efficiency and the accuracy of defect detection and identification of the small-size hardware fitting of the power transmission line are improved.
The detection system collects the image information of the power transmission line through the image collection unit on the unmanned aerial vehicle, after the image information data are transmitted to the ground control center, the image information data of the power transmission line are preprocessed through the image preprocessing unit, then the collected image information of the power transmission line after preprocessing is detected and recognized through the power transmission line small-size hardware defect detection model preset in the defect recognition device, so that the defect recognition result of the power transmission line small-size hardware is obtained, and under the condition that the defect recognition result of the small-size hardware shows that defect characteristics exist, corresponding early warning is executed through the early warning device, and therefore detection and defect recognition of the small-size hardware of the power transmission line are achieved.
In the description of the present invention, it is to be understood that the terms "intermediate", "length", "upper", "lower", "front", "rear", "vertical", "horizontal", "inner", "outer", "radial", "circumferential", and the like, indicate orientations and positional relationships that are based on the orientations and positional relationships shown in the drawings, are used for convenience in describing the present invention and for simplicity in description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and therefore, are not to be construed as limiting the present invention.
In the present invention, unless otherwise expressly stated or limited, the first feature may be "on" the second feature in direct contact with the second feature, or the first and second features may be in indirect contact via an intermediate. "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the present invention, unless otherwise expressly stated or limited, the terms "mounted," "connected," "secured," and the like are to be construed broadly and can, for example, be fixedly connected, detachably connected, or integrally formed; may be mechanically coupled, may be electrically coupled or may be in communication with each other; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The above description is for the purpose of illustrating embodiments of the invention and is not intended to limit the invention, and it will be apparent to those skilled in the art that any modification, equivalent replacement, or improvement made without departing from the spirit and principle of the invention shall fall within the protection scope of the invention.
Claims (7)
1. The invention provides a small-size hardware defect detection system for a power transmission line, which is characterized by comprising an unmanned aerial vehicle and a ground control center, wherein the unmanned aerial vehicle is provided with a data acquisition device, and the ground control center is provided with a data processing system; the data acquisition device acquires image information of the power transmission line and then sends the image information to the data processing system; the data processing system includes:
the ground communication unit is used for receiving the image information of the power transmission line sent by the data acquisition device;
the defect identification device is provided with a defect detection model unit, a preset transmission line small-size hardware defect detection model is stored in the defect detection model unit, and the preset transmission line small-size hardware defect detection model is used for identifying the image information received by the ground communication unit;
and the early warning device executes alarm when the identification result of the defect identification device indicates that the defect exists.
2. The system for detecting the defects of the small-size fittings of the power transmission line according to claim 1, wherein the data processing system further comprises an image preprocessing unit, the image preprocessing unit is connected between the ground communication unit and the defect identification device, and the image preprocessing unit is used for preprocessing image information received by the ground communication unit and then sending the image information to the defect identification device for defect identification.
3. The system for detecting the defects of the small-size hardware fittings of the power transmission line according to claim 1 or 2, wherein the defect detection model unit comprises a virtual-real integration subunit, a migration learning subunit and a model training subunit, wherein:
the virtual-real integration subunit is used for constructing a virtual sample generation and labeling model of virtual-real integration and fusing virtual data and real data;
the migration learning subunit migrates the virtual sample generation and labeling model integrated with the virtual and the real to the actual data training, realizes the migration learning based on the deep learning framework, and performs the source task of the virtual data learning model and then performs the target task of the actual data learning optimization model to realize the model optimization based on the migration learning;
the model training subunit is used for training a deep learning model based on a target detection algorithm and carrying out abnormity diagnosis on the small-size hardware fitting of the power transmission line on the basis of target detection of deep learning.
4. The system for detecting the defects of the small-size hardware fittings of the power transmission line according to claim 1 or 2, wherein the acquisition device comprises a control unit, an image acquisition unit and a wireless communication unit; the control unit is used for controlling the image acquisition unit and the wireless communication unit to work; the image acquisition unit is used for acquiring image information of the power transmission line, and the wireless communication unit is in communication connection with the ground communication unit, so that communication connection and data transmission between the unmanned aerial vehicle and the ground control center are realized.
5. The system for detecting the small-size hardware fitting defects of the power transmission line according to claim 4, wherein the image acquisition unit comprises a double-optical camera, the double-optical camera comprises a visible light camera and an infrared light camera, the visible light camera is used for shooting scene pictures of the power transmission line, and the infrared light camera is used for acquiring infrared thermal imaging pictures of the power transmission line.
6. The system for detecting the small-size hardware fitting defects of the power transmission line according to claim 5, wherein an image current pushing processor is arranged in the dual-optical camera and used for fusing, superposing and rendering a scene picture of the power transmission line and an infrared thermal imaging image to generate a rendered image so as to realize single line transmission of the image.
7. The system of claim 2, wherein the preprocessing comprises image enhancement, noise filtering and threshold segmentation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110935558.9A CN113808081A (en) | 2021-08-16 | 2021-08-16 | Transmission line small-size gold utensil defect detecting system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110935558.9A CN113808081A (en) | 2021-08-16 | 2021-08-16 | Transmission line small-size gold utensil defect detecting system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113808081A true CN113808081A (en) | 2021-12-17 |
Family
ID=78943094
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110935558.9A Pending CN113808081A (en) | 2021-08-16 | 2021-08-16 | Transmission line small-size gold utensil defect detecting system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113808081A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115829952A (en) * | 2022-11-21 | 2023-03-21 | 国网湖北省电力有限公司超高压公司 | Hardware fitting high-precision image analysis and full-life-cycle health state risk assessment based software system |
-
2021
- 2021-08-16 CN CN202110935558.9A patent/CN113808081A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115829952A (en) * | 2022-11-21 | 2023-03-21 | 国网湖北省电力有限公司超高压公司 | Hardware fitting high-precision image analysis and full-life-cycle health state risk assessment based software system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110031477B (en) | Bridge key component disease early warning system and method based on image monitoring data | |
| CN113223035B (en) | Intelligent inspection system for cage chickens | |
| CN110567964B (en) | Method and device for detecting defects of power transformation equipment and storage medium | |
| CN109142904B (en) | Image recognition-based fault monitoring method and device for direct-current transmission converter valve | |
| CN110807460B (en) | Transformer substation intelligent patrol system based on image recognition and application method thereof | |
| CN115184726B (en) | Smart power grid fault real-time monitoring and positioning system and method | |
| CN111604916B (en) | Machine room IT equipment fault cabinet U-position positioning system and method | |
| CN115133874A (en) | Unmanned aerial vehicle linkage inspection photovoltaic power station fault detection method and system | |
| CN111899211A (en) | Transformer oil leakage fault detection system and method based on images and smell | |
| CN113205039B (en) | Power equipment fault image recognition disaster investigation system and method based on multiple DCNN networks | |
| CN113485432A (en) | Photovoltaic power station electroluminescence intelligent diagnosis system and method based on unmanned aerial vehicle | |
| CN113589837A (en) | Electric power real-time inspection method based on edge cloud | |
| CN110149002B (en) | Unmanned operation and maintenance method, device and system for photovoltaic power station | |
| CN113808081A (en) | Transmission line small-size gold utensil defect detecting system | |
| KR20220055082A (en) | System and method for defect detection based on deep learning through machine-learning of solar module data of thermal image | |
| CN115186850A (en) | Dynamic monitoring method and system for submarine cable operating environment | |
| CN214314723U (en) | Intelligent power distribution station monitoring system based on 5G cloud control platform | |
| CN112455676A (en) | Intelligent monitoring and analyzing system and method for health state of photovoltaic panel | |
| CN114882682B (en) | High-voltage cable state monitoring platform and monitoring method | |
| CN217331227U (en) | Strain insulator string wind-induced vibration on-line monitoring system | |
| CN116365705A (en) | Method and system for monitoring faults of photovoltaic module in real time | |
| TWI732682B (en) | An analyzed system and method for failures of solar power module | |
| CN213152220U (en) | All-weather monitoring system for slot type optical thermal power station | |
| CN113809985A (en) | Robot-based marine photovoltaic bracket corrosion condition diagnosis system and method | |
| CN210745397U (en) | Unmanned aerial vehicle patrols and examines image acquisition processing 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 |