CN111831430A - Electrical equipment defect identification system based on edge calculation - Google Patents

Electrical equipment defect identification system based on edge calculation Download PDF

Info

Publication number
CN111831430A
CN111831430A CN202010542392.XA CN202010542392A CN111831430A CN 111831430 A CN111831430 A CN 111831430A CN 202010542392 A CN202010542392 A CN 202010542392A CN 111831430 A CN111831430 A CN 111831430A
Authority
CN
China
Prior art keywords
power equipment
defect identification
edge computing
image
communication module
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
Application number
CN202010542392.XA
Other languages
Chinese (zh)
Inventor
倪祺
江安烽
沈保国
颜楠楠
朱皇儒
黄浩
严炜
续涛
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
China Online Shanghai Energy Internet Research Institute Co ltd
State Grid Shanghai Electric Power Co Ltd
Electric Power Research Institute of State Grid Shanghai Electric Power Co Ltd
Original Assignee
China Online Shanghai Energy Internet Research Institute Co ltd
State Grid Shanghai Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by China Online Shanghai Energy Internet Research Institute Co ltd, State Grid Shanghai Electric Power Co Ltd filed Critical China Online Shanghai Energy Internet Research Institute Co ltd
Priority to CN202010542392.XA priority Critical patent/CN111831430A/en
Publication of CN111831430A publication Critical patent/CN111831430A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00—Arrangements for program control, e.g. control units
    • G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46—Multiprogramming arrangements
    • G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5061—Partitioning or combining of resources
    • G06F9/5072—Grid computing
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J5/0096—Radiation pyrometry, e.g. infrared or optical thermometry for measuring wires, electrical contacts or electronic systems
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N25/00—Investigating or analyzing materials by the use of thermal means
    • G01N25/72—Investigating presence of flaws
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/23—Clustering techniques
    • G06F18/232—Non-hierarchical techniques
    • G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/24—Classification techniques
    • G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
    • 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
    • G01—MEASURING; TESTING
    • G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
    • G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
    • G01J2005/0077—Imaging
    • 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
    • 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
    • G06T2207/10032—Satellite or aerial image; Remote sensing
    • 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]
    • 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
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30108—Industrial image inspection

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Data Mining & Analysis (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • General Engineering & Computer Science (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Software Systems (AREA)
  • Evolutionary Biology (AREA)
  • Evolutionary Computation (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Artificial Intelligence (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Quality & Reliability (AREA)
  • Mathematical Physics (AREA)
  • Probability & Statistics with Applications (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Health & Medical Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
  • Image Analysis (AREA)

Abstract

The invention relates to an electric power equipment defect identification system based on edge calculation, which comprises: the image sensor is used for acquiring an image of the power equipment on site; the edge computing equipment is provided with an image-based power equipment defect identification algorithm, and the defect identification is carried out on the power equipment image acquired by the image sensor through the algorithm; the cloud center is used for acquiring defect identification information of all the edge computing devices and displaying the defect information on a human-computer interface, and the edge computing devices are respectively communicated with the image sensor and the cloud center; the image-based power equipment defect identification algorithm is embedded in the edge computing equipment and used for processing and analyzing the image acquired by the image sensor to finally obtain a defect identification result. Compared with the prior art, the method has the advantages of faster defect feedback of the power equipment, more stable system, high identification accuracy, high processing speed and the like.

Description

Electrical equipment defect identification system based on edge calculation
Technical Field
The invention relates to the technical field of power equipment defect identification, in particular to a power equipment defect identification system based on edge calculation.
Background
In recent years, with the development of social economy, the scale of the power grid is continuously enlarged, and the overhaul of power equipment becomes important for the operation and maintenance of the power grid. In recent years, the unmanned aerial vehicle inspection technology is continuously developed, images of the power equipment are collected on site through the unmanned aerial vehicle and then transmitted to the central monitoring platform, the images are processed by the central monitoring platform, and then the defect condition of the power equipment is judged.
Chinese patent CN110411580A discloses a system for diagnosing heating defects of electrical equipment, which includes an infrared sensor, an infrared charged detection device and a cloud platform connected in sequence. The cloud platform is used for constructing a heating defect diagnosis model, performing heating defect diagnosis on the electric power equipment in real time by using the heating defect diagnosis model, and transmitting a diagnosis result to the infrared live detection device. In the system, the algorithm is deployed at a server side of a cloud platform, when the system is used, an infrared sensor needs to transmit an infrared image to the cloud platform, all data calculation is completed in the cloud platform, feedback is delayed for a long time, timely feedback cannot be achieved, and safety accidents are possibly caused.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide the power equipment defect identification system based on edge calculation, which realizes faster power equipment defect feedback, more stable system, high identification accuracy and high processing speed.
The purpose of the invention can be realized by the following technical scheme:
an edge-calculation-based electrical equipment defect identification system, comprising:
the image sensor is used for acquiring an image of the power equipment on site;
the edge computing equipment is provided with an image-based power equipment defect identification algorithm, and the defect identification is carried out on the power equipment image acquired by the image sensor through the algorithm;
the cloud center is used for acquiring defect identification information of all edge computing devices and displaying the defect information on a human-computer interface;
the edge computing device is respectively communicated with the image sensor and the cloud center.
Preferably, the image sensor is a visible light camera, an infrared camera, an ultraviolet camera or a remote sensing satellite.
Preferably, the edge computing device comprises an edge computing chip, a memory, a first communication module, a second communication module and an edge computing device power supply; the memory, the first communication module, the second communication module and the edge computing device power supply are respectively connected with the edge computing chip; the edge computing device is communicated with the image sensor through the first communication module and is communicated with the cloud center through the second communication module.
More preferably, the edge computing chip is a CPU processor.
More preferably, the first communication module is a serial communication interface module or a wireless communication module; the second communication module is a wireless communication module.
More preferably, the edge computing device is provided with a GPU, and the chip is used for accelerating the running speed of the edge computing device; and the GPU is connected with the edge computing chip.
Preferably, the cloud center comprises a cloud center processor, a cloud center display and a cloud center power supply; and the cloud center display and the cloud center power supply are respectively connected with the cloud center processor.
Preferably, the image-based power equipment defect identification algorithm comprises the following steps:
step 1: processing an image acquired by an image sensor by using a convolution layer of an image-based power equipment defect identification model, extracting a feature block of the image, and then sending the image to an RPN network;
step 2: generating a candidate region by using an RPN network, and then sending the feature block and the candidate region into an ROI (region of interest) pooling layer of a power equipment defect identification model;
and step 3: processing the feature block and the candidate region by using the ROI pooling layer to obtain a target feature map, and sending the target feature map into the full-connection layer;
and 4, step 4: sending the target characteristic graph into a deep convolutional neural network through a full connection layer to obtain the type of the power equipment;
and 5: and 4, carrying out normalization classification processing on the target characteristic diagram through the type of the electric power equipment obtained in the step 4, then obtaining the accurate position of the detection frame through frame regression processing, and finally obtaining the defect identification result of the electric power equipment.
More preferably, the defect identification model is a VGG16 neural network model; the defect identification model comprises 13 convolutional layers, 5 pooling layers and 3 full-connection layers.
More preferably, the step 5 is specifically to obtain the target to be measured and the background by normalizing the classified anchor points and then obtain the accurate target by correcting the anchor points through frame regression; the classification anchor point and the correction anchor point are both obtained through a density peak value clustering algorithm.
Compared with the prior art, the invention has the following advantages:
firstly, realizing faster defect feedback of power equipment: in the defect identification system, the edge computing equipment is adopted to process the image of the electric power equipment to obtain the defect identification result of the electric power equipment, and then the identification result is transmitted to the cloud center, so that a worker can monitor the electric power equipment through the terminal arranged in the cloud center.
Secondly, the system is more stable: all the calculations of the defect identification system are completed at the edge equipment, and only the defect identification result is uploaded to the cloud center without occupying a large amount of computing resources, so that the system is less influenced by network fluctuation and has higher stability.
Thirdly, the defect identification result is more accurate: the defect recognition system of the invention adopts a fast RCNN model to process and analyze the images of the electric power equipment, the image recognition speed can reach 0.17 second/piece, and a VGG16 model is adopted, so that the processing capacity and the processing speed of the algorithm are further improved.
Fourthly, the processing speed is faster: the defect identification system is provided with the GPU for accelerating the image processing speed, so that the system processing speed is higher, and workers can also obtain the defect identification result of the power equipment more quickly, thereby avoiding the occurrence of safety accidents.
Drawings
FIG. 1 is a schematic diagram of a defect identification system according to the present invention;
FIG. 2 is a schematic flow chart of a defect identification algorithm for power equipment according to the present invention.
The reference numbers in the figures indicate:
1. image sensor, 2, edge computing device, 3, cloud center, 21, edge computing chip, 22, memory, 23, first communication module, 24, second communication module, 25, edge computing device power supply, 26, GPU, 31, cloud center processor, 32, cloud center display, 33, cloud center power supply.
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 some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
An electric power equipment defect identification system based on edge calculation is structurally shown in fig. 1 and comprises:
the image sensor 1: the system comprises a camera, a display and a display, wherein the camera is used for acquiring relevant images of the power equipment on site;
the edge computing device 2: the embedded image-based power equipment defect identification algorithm is used for identifying the defects of the power equipment image acquired by the image sensor 1;
the cloud center 3: and acquiring defect identification information of all the edge computing devices 2, and displaying the defect information on a human-computer interface, wherein a user can check the defect identification condition of all the edge computing devices 2 on the power equipment on the human-computer interface.
Each module is described in detail below:
an image sensor 1
The image sensor 1 in this embodiment selects a visible light camera, an infrared camera, an ultraviolet camera, or a remote sensing satellite to collect image information of the power equipment on site.
Second, edge computing device 2
The edge computing device 2 comprises an edge computing chip 21, a memory 22, a first communication module 23, a second communication module 24 and an edge computing device power supply 25, wherein the memory 22, the first communication module 23, the second communication module 24 and the edge computing device power supply 25 are respectively connected with the edge computing chip 21, the edge computing device 2 is communicated with the image sensor 1 through the first communication module 23, and is communicated with the cloud center 3 through the second communication module 24.
The edge computing chip 21 in this embodiment is specifically a CPU processor, and an intel to strong D-2100 processor is selected, which can meet the requirements of low power consumption and high density edge computing.
In this embodiment, the first communication module 23 is a serial communication interface module or a wireless communication module, and the selection of the first communication module 23 is performed according to the type of the image sensor 1.
The second communication module 24 in this embodiment is a wireless communication module, that is, all the edge computing devices 2 communicate with the cloud center 3 through a wireless network.
The edge computing device 2 in this embodiment is further provided with a GPU26 for accelerating the operation speed of the edge computing device 2, and the GPU26 is connected to the edge computing chip 21.
The edge computing chip 21 in this embodiment is embedded with an image-based power equipment defect identification algorithm for processing and analyzing the power equipment image acquired by the image sensor 1, and the defect identification algorithm specifically includes:
step 1: processing the image acquired by the image sensor 1 by using a convolution layer of an image-based power equipment defect identification model, extracting a feature block of the image, and then sending the image to an RPN network;
step 2: generating a candidate region by using an RPN network, and then sending the feature block and the candidate region into an ROI (region of interest) pooling layer of a power equipment defect identification model;
and step 3: processing the feature block and the candidate region by using the ROI pooling layer to obtain a target feature map, and sending the target feature map into the full-connection layer;
and 4, step 4: sending the target characteristic graph into a deep convolutional neural network through a full connection layer to obtain the type of the power equipment;
and 5: and 4, carrying out normalization classification processing on the target characteristic diagram through the type of the electric power equipment obtained in the step 4, then obtaining the accurate position of the detection frame through frame regression processing, and finally obtaining the defect identification result of the electric power equipment.
In the embodiment, the VGG16 neural network model is selected as the defect identification model; the defect identification model comprises 13 convolutional layers, 5 pooling layers and 3 full-connection layers.
Step 5, obtaining a target to be detected and a background through the normalized classified anchor points, and then obtaining an accurate target through frame regression correction anchor points; the classification anchor point and the correction anchor point are both obtained through a density peak value clustering algorithm.
The density peak value clustering algorithm specifically comprises the following steps:
(1) calculating phase distances
dc＝D(t*m)
Wherein d iscIs stage distance, t is stage distance parameter, t belongs to (0,1), D is data set, m is intermediate parameter, D is calculated by
Figure BDA0002539438370000051
Wherein i and j are respectively any two points x in the data set DiAnd xj，dijIs xiAnd xjThe distance between the points is N, the number of the points to be clustered is N, and m is 0.5N (N-1);
(2) calculating point x by phase distanceiLocal density value of
ρi＝∑χ(dij-dc)
Where ρ isiIs xiLocal density value of dc> 0, χ (x) is a known function, specifically:
Figure BDA0002539438370000052
(3) calculating point xiRatio p to local density valueiLarge data point xjThe calculation method of the minimum distance between the two elements is as follows:
Figure BDA0002539438370000053
(4) according to local density value
Figure BDA0002539438370000054
And minimum distance
Figure BDA0002539438370000055
Drawing a decision graph, and selecting a clustering center point;
(5) and classifying the data of the non-clustering central point.
Three, cloud center 3
The cloud center 3 comprises a cloud center processor 31, a cloud center display 32 and a cloud center power supply 33, the cloud center display 32 and the cloud center power supply 33 are respectively connected with the cloud center processor 31, a user can directly check the defect identification condition of all the edge computing devices 2 on the cloud center display 32, the defect identification condition is timely processed when a defect occurs, and a large accident is avoided.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. An edge-computing-based electrical equipment defect identification system, comprising:
the image sensor (1) is used for acquiring an image of the power equipment on site;
the edge computing equipment (2) is provided with an image-based power equipment defect identification algorithm, and the defect identification is carried out on the power equipment image acquired by the image sensor (1) through the algorithm;
the cloud center (3) is used for acquiring defect identification information of all the edge computing devices (2) and displaying the defect information on a human-computer interface;
the edge computing device (2) is respectively communicated with the image sensor (1) and the cloud center (3).
2. An edge calculation-based power equipment defect identification system as claimed in claim 1, characterized in that the image sensor (1) is a visible light camera, an infrared camera, an ultraviolet camera or a remote sensing satellite.
3. An edge computing based power equipment defect identification system according to claim 1, characterized in that the edge computing equipment (2) comprises an edge computing chip (21), a memory (22), a first communication module (23), a second communication module (24) and an edge computing equipment power supply (25); the memory (22), the first communication module (23), the second communication module (24) and the edge computing device power supply (25) are respectively connected with the edge computing chip (21); the edge computing device (2) is communicated with the image sensor (1) through a first communication module (23) and is communicated with the cloud center (3) through a second communication module (24).
4. An edge-computing-based power equipment defect identification system as claimed in claim 3, characterized in that said edge computing chip (21) is a CPU processor.
5. An edge-computing-based power equipment defect identification system as claimed in claim 3, characterized in that said first communication module (23) is a serial communication interface module or a wireless communication module; the second communication module (23) is a wireless communication module.
6. An edge computing-based power equipment defect identification system as claimed in claim 3, characterized in that, the edge computing equipment (2) is provided with a GPU (26) which is used for accelerating the running speed of the edge computing equipment (2); the GPU (26) is connected with the edge computing chip (21).
7. An edge computing-based power equipment defect identification system as claimed in claim 1, wherein the cloud center (3) comprises a cloud center processor (31), a cloud center display (32) and a cloud center power supply (33); the cloud center display (32) and the cloud center power supply (33) are respectively connected with the cloud center processor (31).
8. An edge-computing-based power equipment defect identification system according to claim 1, wherein the image-based power equipment defect identification algorithm comprises the steps of:
step 1: processing an image collected by an image sensor (1) by using a convolution layer of an image-based power equipment defect identification model, extracting a feature block of the image, and then sending the image to an RPN network;
step 2: generating a candidate region by using an RPN network, and then sending the feature block and the candidate region into an ROI (region of interest) pooling layer of a power equipment defect identification model;
and step 3: processing the feature block and the candidate region by using the ROI pooling layer to obtain a target feature map, and sending the target feature map into the full-connection layer;
and 4, step 4: sending the target characteristic graph into a deep convolutional neural network through a full connection layer to obtain the type of the power equipment;
and 5: and 4, carrying out normalization classification processing on the target characteristic diagram through the type of the electric power equipment obtained in the step 4, then obtaining the accurate position of the detection frame through frame regression processing, and finally obtaining the defect identification result of the electric power equipment.
9. The system of claim 8, wherein the defect identification model is a VGG16 neural network model; the defect identification model comprises 13 convolutional layers, 5 pooling layers and 3 full-connection layers.
10. The system for recognizing the defect of the power equipment based on the edge calculation as claimed in claim 8, wherein the step 5 is to obtain the target to be detected and the background by normalizing the classified anchor points and then obtain the accurate target by correcting the anchor points by frame regression; the classification anchor point and the correction anchor point are both obtained through a density peak value clustering algorithm.
CN202010542392.XA 2020-06-15 2020-06-15 Electrical equipment defect identification system based on edge calculation Pending CN111831430A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010542392.XA CN111831430A (en) 2020-06-15 2020-06-15 Electrical equipment defect identification system based on edge calculation

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010542392.XA CN111831430A (en) 2020-06-15 2020-06-15 Electrical equipment defect identification system based on edge calculation

Publications (1)

Publication Number Publication Date
CN111831430A true CN111831430A (en) 2020-10-27

Family

ID=72898786

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010542392.XA Pending CN111831430A (en) 2020-06-15 2020-06-15 Electrical equipment defect identification system based on edge calculation

Country Status (1)

Country Link
CN (1) CN111831430A (en)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112434740A (en) * 2020-11-26 2021-03-02 西北大学 Depth learning-based Qin tomb warriors fragment classification method
CN113033355A (en) * 2021-03-11 2021-06-25 中北大学 Abnormal target identification method and device based on intensive power transmission channel
CN113065508A (en) * 2021-04-20 2021-07-02 上海环能新科节能科技股份有限公司 Edge calculation method for discovering and identifying hidden danger of extra-high voltage transmission line channel
CN113362316A (en) * 2021-06-23 2021-09-07 合肥朗云物联科技股份有限公司 Method for accurately identifying image edge object
CN114199381A (en) * 2021-12-13 2022-03-18 国网陕西省电力公司延安供电公司 Electrical equipment fault detection method for improving infrared detection model
CN115138598A (en) * 2022-05-16 2022-10-04 格力电器（武汉）有限公司 PCB welding production line intelligence letter sorting system
CN116633025A (en) * 2023-07-24 2023-08-22 国网湖北省电力有限公司武汉市东湖新技术开发区供电公司 Visual wisdom limit platform of electric power operation monitoring
CN118429840A (en) * 2024-07-04 2024-08-02 国网上海市电力公司 Unmanned aerial vehicle aerial image splicing and hidden danger detection method and system based on end side

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150180730A1 (en) * 2013-12-19 2015-06-25 Amdocs Software Systems Limited System, method, and computer program for inter-module communication in a network based on network function virtualization (nfv)
CN107607207A (en) * 2017-08-22 2018-01-19 中国科学院深圳先进技术研究院 A kind of power equipment thermal fault detection method, system and electronic equipment
CN108828409A (en) * 2018-08-03 2018-11-16 南方电网科学研究院有限责任公司 Fault detection system based on edge calculation
CN110069975A (en) * 2018-12-25 2019-07-30 国网河北省电力有限公司电力科学研究院 A kind of conducting wire neural network based opens burst recognition methods and system
CN110097053A (en) * 2019-04-24 2019-08-06 上海电力学院 A kind of power equipment appearance defect inspection method based on improvement Faster-RCNN
CN110221558A (en) * 2019-06-05 2019-09-10 镇江四联机电科技有限公司 A kind of electrohydraulic servo valve on-line fault diagnosis gateway based on edge calculations technology
CN110222648A (en) * 2019-06-10 2019-09-10 国网上海市电力公司 A kind of aerial cable fault recognition method and device
CN110994798A (en) * 2019-12-16 2020-04-10 深圳供电局有限公司 Substation equipment monitoring system

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150180730A1 (en) * 2013-12-19 2015-06-25 Amdocs Software Systems Limited System, method, and computer program for inter-module communication in a network based on network function virtualization (nfv)
CN107607207A (en) * 2017-08-22 2018-01-19 中国科学院深圳先进技术研究院 A kind of power equipment thermal fault detection method, system and electronic equipment
CN108828409A (en) * 2018-08-03 2018-11-16 南方电网科学研究院有限责任公司 Fault detection system based on edge calculation
CN110069975A (en) * 2018-12-25 2019-07-30 国网河北省电力有限公司电力科学研究院 A kind of conducting wire neural network based opens burst recognition methods and system
CN110097053A (en) * 2019-04-24 2019-08-06 上海电力学院 A kind of power equipment appearance defect inspection method based on improvement Faster-RCNN
CN110221558A (en) * 2019-06-05 2019-09-10 镇江四联机电科技有限公司 A kind of electrohydraulic servo valve on-line fault diagnosis gateway based on edge calculations technology
CN110222648A (en) * 2019-06-10 2019-09-10 国网上海市电力公司 A kind of aerial cable fault recognition method and device
CN110994798A (en) * 2019-12-16 2020-04-10 深圳供电局有限公司 Substation equipment monitoring system

Cited By (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112434740A (en) * 2020-11-26 2021-03-02 西北大学 Depth learning-based Qin tomb warriors fragment classification method
CN113033355A (en) * 2021-03-11 2021-06-25 中北大学 Abnormal target identification method and device based on intensive power transmission channel
CN113065508A (en) * 2021-04-20 2021-07-02 上海环能新科节能科技股份有限公司 Edge calculation method for discovering and identifying hidden danger of extra-high voltage transmission line channel
CN113362316A (en) * 2021-06-23 2021-09-07 合肥朗云物联科技股份有限公司 Method for accurately identifying image edge object
CN114199381A (en) * 2021-12-13 2022-03-18 国网陕西省电力公司延安供电公司 Electrical equipment fault detection method for improving infrared detection model
CN115138598A (en) * 2022-05-16 2022-10-04 格力电器（武汉）有限公司 PCB welding production line intelligence letter sorting system
CN116633025A (en) * 2023-07-24 2023-08-22 国网湖北省电力有限公司武汉市东湖新技术开发区供电公司 Visual wisdom limit platform of electric power operation monitoring
CN116633025B (en) * 2023-07-24 2023-09-26 国网湖北省电力有限公司武汉市东湖新技术开发区供电公司 Visual wisdom limit platform of electric power operation monitoring
CN118429840A (en) * 2024-07-04 2024-08-02 国网上海市电力公司 Unmanned aerial vehicle aerial image splicing and hidden danger detection method and system based on end side

Similar Documents

Publication Publication Date Title
CN111831430A (en) Electrical equipment defect identification system based on edge calculation
CN109935080B (en) Monitoring system and method for real-time calculation of traffic flow on traffic line
CN109214280B (en) Shop identification method and device based on street view, electronic equipment and storage medium
Bo et al. Particle pollution estimation from images using convolutional neural network and weather features
CN108537154A (en) Transmission line of electricity Bird's Nest recognition methods based on HOG features and machine learning
CN109886396A (en) A kind of transmission line galloping on-line prediction system and method
CN111179262B (en) Electric power inspection image hardware fitting detection method combining shape attribute
CN109872317A (en) A kind of defect identification method based on power equipments defect identification learning model
CN111091080A (en) Face recognition method and system
CN110796360A (en) Fixed traffic detection source multi-scale data fusion method
CN112949510A (en) Human detection method based on fast R-CNN thermal infrared image
CN116612098A (en) Insulator RTV spraying quality evaluation method and device based on image processing
CN116503354A (en) Method and device for detecting and evaluating hot spots of photovoltaic cells based on multi-mode fusion
CN112132157A (en) Raspberry pie-based gait face fusion recognition method
CN111339927A (en) Intelligent work state identification system for personnel in electric power business hall
CN107687994A (en) air detection system and method
CN114694130A (en) Method and device for detecting telegraph poles and pole numbers along railway based on deep learning
WO2024119983A1 (en) Anomality detection method and apparatus for cable terminal of rail vehicle
CN112419243B (en) Power distribution room equipment fault identification method based on infrared image analysis
CN110136097A (en) Insulator fault identification method and device based on characteristic pyramid
CN117636129A (en) Identification method of power construction supervision image
CN116959099B (en) Abnormal behavior identification method based on space-time diagram convolutional neural network
CN110765900A (en) DSSD-based automatic illegal building detection method and system
CN115932661A (en) Method for analyzing and judging noise compliance of transformer
CN115294048A (en) Foreign matter detection method, device, equipment and storage medium

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