CN116094159A - Smart power grid safe operation and maintenance system based on cloud computing and big data analysis - Google Patents
Smart power grid safe operation and maintenance system based on cloud computing and big data analysis Download PDFInfo
- Publication number
- CN116094159A CN116094159A CN202211736601.XA CN202211736601A CN116094159A CN 116094159 A CN116094159 A CN 116094159A CN 202211736601 A CN202211736601 A CN 202211736601A CN 116094159 A CN116094159 A CN 116094159A
- Authority
- CN
- China
- Prior art keywords
- power equipment
- cloud computing
- image
- unit
- monitoring data
- 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
- 238000012423 maintenance Methods 0.000 title claims abstract description 37
- 238000007405 data analysis Methods 0.000 title claims abstract description 19
- 238000003745 diagnosis Methods 0.000 claims abstract description 81
- 238000012544 monitoring process Methods 0.000 claims abstract description 57
- 238000012545 processing Methods 0.000 claims description 34
- 238000012549 training Methods 0.000 claims description 31
- 238000011176 pooling Methods 0.000 claims description 18
- 238000012360 testing method Methods 0.000 claims description 16
- 238000000605 extraction Methods 0.000 claims description 15
- 238000000034 method Methods 0.000 claims description 15
- 230000002159 abnormal effect Effects 0.000 claims description 14
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000007781 pre-processing Methods 0.000 claims description 14
- 241001465754 Metazoa Species 0.000 claims description 10
- 238000007689 inspection Methods 0.000 claims description 10
- 238000007664 blowing Methods 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 8
- 238000013527 convolutional neural network Methods 0.000 claims description 6
- 238000009432 framing Methods 0.000 claims description 6
- 230000004913 activation Effects 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 4
- 238000007726 management method Methods 0.000 description 9
- 101100168110 Hathewaya histolytica colH gene Proteins 0.000 description 5
- 230000000694 effects Effects 0.000 description 3
- 238000007667 floating Methods 0.000 description 3
- 238000005286 illumination Methods 0.000 description 3
- 208000034699 Vitreous floaters Diseases 0.000 description 2
- 238000004590 computer program Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000010223 real-time analysis Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00001—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by the display of information or by user interaction, e.g. supervisory control and data acquisition systems [SCADA] or graphical user interfaces [GUI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00002—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by monitoring
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00006—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network characterised by information or instructions transport means between the monitoring, controlling or managing units and monitored, controlled or operated power network element or electrical equipment
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Power Engineering (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Databases & Information Systems (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Human Computer Interaction (AREA)
- Entrepreneurship & Innovation (AREA)
- Remote Sensing (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a smart power grid safety operation and maintenance system based on cloud computing and big data analysis, which comprises a data acquisition terminal, a cloud computing server and a site execution terminal; the cloud computing server is respectively and wirelessly connected with the data acquisition terminal and the site execution terminal; the data acquisition terminal is used for acquiring real-time monitoring data of the power equipment and transmitting the acquired real-time monitoring data to the cloud computing server; wherein the real-time monitoring data comprises power equipment image monitoring data; the cloud computing server is used for carrying out power equipment safety diagnosis according to the acquired power equipment image monitoring data to obtain a power equipment safety diagnosis result, generating a corresponding execution instruction according to the obtained power equipment safety diagnosis result, and sending the execution instruction to the on-site execution terminal; the on-site execution terminal is used for executing the received execution instruction and completing on-site safety maintenance of the power equipment. The intelligent safe operation and maintenance system is beneficial to improving the instantaneity and pertinence of the intelligent safe operation and maintenance of the power equipment.
Description
Technical Field
The invention relates to the technical field of intelligent power grids, in particular to a cloud computing and big data analysis-based intelligent power grid safe operation and maintenance system.
Background
Compared with the traditional power grid mode, the intelligent power grid is built by combining information technology, sensor technology and the like, and all links in a power grid system are comprehensively subjected to data acquisition and analysis, so that intelligent and automatic control of the intelligent power grid is realized.
At present, aiming at the technical research direction of the smart power grid, the management, the safe operation and maintenance management and the like of the power equipment are mostly realized by collecting the internal operation state data (such as power supply, current, voltage and the like) of the power equipment and further analyzing according to the obtained operation state data. However, in the above technical research direction for the smart grid, the attention is focused on the level of the operation state of the device, but the attention is lack of attention for the physical condition of the power device (such as the external condition of the device, the defect of the shell of the device, etc.), so that the power device is easily affected by the external physical condition (such as corrosion caused by the existence of foreign matter covering or heat dissipation affected by the damage of the shell of the device caused by the biting of small animals), thereby affecting the normal operation of the power device, and causing the defect of the safety operation and maintenance management of the power device for the smart grid.
Disclosure of Invention
Aiming at the technical problems that the physical condition of the power equipment is lack of attention, so that the power equipment is easily influenced by external physical conditions, and the normal operation of the power equipment is influenced, and the safety operation and maintenance management work of the power equipment of the intelligent power grid is defective, the invention aims to provide the intelligent power grid safety operation and maintenance system based on cloud computing and big data analysis.
The aim of the invention is realized by adopting the following technical scheme:
the invention provides a smart power grid safety operation and maintenance system based on cloud computing and big data analysis, which is characterized by comprising a data acquisition terminal, a cloud computing server and a site execution terminal; the cloud computing server is respectively and wirelessly connected with the data acquisition terminal and the site execution terminal;
the data acquisition terminal is used for acquiring real-time monitoring data of the power equipment and transmitting the acquired real-time monitoring data to the cloud computing server; wherein the real-time monitoring data comprises power equipment image monitoring data;
the cloud computing server is used for carrying out power equipment safety diagnosis according to the acquired power equipment image monitoring data to obtain a power equipment safety diagnosis result, generating a corresponding execution instruction according to the obtained power equipment safety diagnosis result, and sending the execution instruction to the on-site execution terminal;
the on-site execution terminal is used for executing the received execution instruction and completing on-site safety maintenance of the power equipment.
Preferably, the power equipment comprises a transformer and a transformer box.
Preferably, the system further comprises a configuration management terminal;
the configuration management terminal is used for carrying out initialization setting on the data acquisition terminal information, the power equipment information and the site execution terminal information.
Preferably, the data acquisition terminal comprises a fixed shooting unit and an unmanned aerial vehicle shooting unit;
the fixed shooting unit is used for being arranged on the electric power equipment site, collecting electric power equipment image monitoring data in real time, and transmitting the collected electric power equipment image monitoring data to the cloud computing server;
the unmanned aerial vehicle shooting unit is used for reaching the electric power equipment site according to the specified flight route according to the inspection instruction, collecting electric power equipment image monitoring data in the inspection process, and transmitting the collected electric power equipment image monitoring data to the cloud computing server.
Preferably, the cloud computing server comprises a preprocessing unit, an image extraction unit, a security diagnosis unit and an instruction generation unit;
the preprocessing unit is used for preprocessing the acquired power equipment image monitoring data, including filtering, framing and other processing, so as to obtain a preprocessed power equipment image;
the image extraction unit is used for carrying out target extraction processing according to the preprocessed power equipment image to obtain a power equipment target image;
the safety diagnosis unit is used for inputting the obtained power equipment target image into a safety diagnosis model trained based on big data to obtain a power equipment safety diagnosis result;
the instruction generation unit is used for generating corresponding execution instructions when the safety diagnosis result of the power equipment is abnormal, and transmitting the execution instructions to the field execution terminals corresponding to the abnormal power equipment.
Preferably, the preprocessing unit preprocesses the acquired image monitoring data of the electric power equipment, specifically including:
carrying out framing treatment according to the acquired power equipment image monitoring data, and extracting each power equipment image frame picture;
and performing filtering processing according to the obtained image frames of the power equipment to obtain preprocessed power equipment images.
Preferably, the image extraction unit performs target extraction according to the preprocessed power equipment image, and specifically includes:
performing edge detection processing according to the preprocessed power equipment image, and dividing the preprocessed power equipment image into a foreground part and a background part according to the acquired edge information;
and carrying out image segmentation according to the partitioned foreground part to obtain a power equipment target image.
Preferably, the cloud computing server further comprises a model training unit;
the model training unit is used for extracting power equipment target images from the large database, carrying out security diagnosis identification according to the extracted power equipment target images, and forming a training set and a testing set from the power equipment target images with the security diagnosis identification;
training the safety diagnosis model by adopting a training set, testing the trained safety diagnosis model by adopting a testing set after the training is finished, and finishing the training of the safety diagnosis model when the testing accuracy exceeds a set standard level, and outputting a trained safety diagnosis model;
when the accuracy of the test does not exceed the set standard level, the model parameters are adjusted and a training set is further provided to train the model until the accuracy of the security diagnostic model exceeds the set standard level.
Preferably, in the security diagnosis unit, the security diagnosis model is built based on a CNN convolutional neural network structure, wherein the security diagnosis model comprises an input layer, a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer, a third convolutional layer, a full connection layer and an output layer which are sequentially connected; the input layer is used for inputting a power equipment target image; the first convolution layer contains 32 convolution kernels of size 3 x 3; the first pooling layer adopts maximum pooling treatment and comprises 32 convolution kernels, wherein the size of the convolution kernels is 2 multiplied by 2; the second convolution layer contains 64 convolution kernels, where the size of the convolution kernels is 1 x 1; the second pooling layer adopts maximum pooling treatment and comprises 64 convolution kernels, wherein the size of the convolution kernels is 2 multiplied by 2; the third convolution layer comprises 128 convolution kernels, wherein the size of the convolution kernels is 2 x 2; the full connection layer comprises 128 nodes, and a sigmoid activation function is adopted; the output layer normalizes the data of the upper layer by adopting a softmax function, converts the characteristic data into a numerical value in a 0-1 interval, and uses the obtained numerical value as a predicted value of different safety diagnosis results to realize safety diagnosis analysis of the power equipment.
Preferably, the field execution terminal comprises a buzzer unit and a blowing unit;
the buzzer unit is used for sending out a buzzing alarm when the safety diagnosis result of the power equipment is analyzed to be that personnel or animals stay in the power equipment, so as to drive the personnel or animals approaching the power equipment;
and the blowing unit is used for blowing out strong wind to the power equipment to blow out the covered foreign matters when the power equipment is covered by the foreign matters as a result of analysis on the safety diagnosis of the power equipment.
The beneficial effects of the invention are as follows: according to the intelligent safety operation and maintenance method, the image monitoring data of the power equipment are obtained as a basis, intelligent safety diagnosis analysis is further carried out on the image of the power equipment based on the cloud computing server, true full diagnosis analysis is carried out on the external condition of the power equipment, when the external safety abnormal condition of the power equipment is analyzed, corresponding execution instructions can be intelligently generated, the external safety abnormal condition is eliminated by the on-site execution terminal of the power equipment, the conditions of equipment damage, performance interference and the like caused by the influence of the external factors of the power equipment are avoided, and the instantaneity and pertinence of the intelligent safety operation and maintenance of the power equipment are improved.
Meanwhile, the intelligent analysis processing of the data is completed based on the cloud computing server, and the remote safe operation and maintenance requirements of the large-scale power equipment can be met based on the data processing performance of the cloud server. Compared with the traditional mode of checking the external abnormal condition of the power equipment through manual inspection, the method is beneficial to reducing the labor cost and improving the real-time level of safe operation and maintenance.
Drawings
The invention will be further described with reference to the accompanying drawings, in which embodiments do not constitute any limitation of the invention, and other drawings can be obtained by one of ordinary skill in the art without inventive effort from the following drawings.
FIG. 1 is a schematic diagram of an exemplary embodiment of a smart grid security operation and maintenance system based on cloud computing and big data analysis;
fig. 2 is a schematic diagram of an exemplary functional unit structure of a smart grid security operation and maintenance system based on cloud computing and big data analysis.
Detailed Description
The invention is further described in connection with the following application scenario.
Referring to the smart grid security operation and maintenance system based on cloud computing and big data analysis shown in the embodiment of fig. 1, the smart grid security operation and maintenance system comprises a data acquisition terminal, a cloud computing server and a site execution terminal; the cloud computing server is respectively and wirelessly connected with the data acquisition terminal and the site execution terminal;
the data acquisition terminal is used for acquiring real-time monitoring data of the power equipment and transmitting the acquired real-time monitoring data to the cloud computing server; wherein the real-time monitoring data comprises power equipment image monitoring data;
the cloud computing server is used for carrying out power equipment safety diagnosis according to the acquired power equipment image monitoring data to obtain a power equipment safety diagnosis result, generating a corresponding execution instruction according to the obtained power equipment safety diagnosis result, and sending the execution instruction to the on-site execution terminal;
the on-site execution terminal is used for executing the received execution instruction and completing on-site safety maintenance of the power equipment.
According to the embodiment of the invention, the image monitoring data of the power equipment is obtained as a basis, the intelligent security diagnosis analysis is further carried out on the image of the power equipment based on the cloud computing server, the true full diagnosis analysis is carried out on the external condition of the power equipment, when the external security abnormal condition of the power equipment is analyzed, the corresponding execution instruction can be intelligently generated, the external security abnormal condition is eliminated by the execution terminal of the power equipment site, the conditions of equipment damage, performance interference and the like caused by the influence of the external factors of the power equipment are avoided, and the instantaneity and pertinence of the intelligent security operation and maintenance of the power equipment are improved.
Meanwhile, the intelligent analysis processing of the data is completed based on the cloud computing server, and the remote safe operation and maintenance requirements of the large-scale power equipment can be met based on the data processing performance of the cloud server. Compared with the traditional mode of checking the external abnormal condition of the power equipment through manual inspection, the method is beneficial to reducing the labor cost and improving the real-time level of safe operation and maintenance.
Preferably, the power equipment includes a transformer, a transformer tank, and the like.
Preferably, referring to fig. 2, the system further includes a configuration management terminal;
the configuration management terminal is used for carrying out initialization setting on the data acquisition terminal information, the power equipment information and the site execution terminal information.
When the system is arranged, basic information of the power equipment is input through the configuration management terminal, the basic information of the data acquisition terminal and the field execution terminal is input into the system, and the power equipment is associated with the data acquisition terminal or the field execution terminal according to actual setting conditions.
Specifically, the power equipment image monitoring data acquired through the data acquisition terminal carries basic information of the power equipment, namely the acquired power equipment image monitoring data is associated with the power equipment, a safety diagnosis result obtained by analyzing the power equipment image monitoring data is also associated with the corresponding power equipment, and when the safety diagnosis analysis result is abnormal, the site execution terminal associated with the power equipment can be controlled so that the site execution terminal associated with the site execution terminal can relieve the abnormal condition of the power equipment.
Preferably, the data acquisition terminal comprises a fixed shooting unit and an unmanned aerial vehicle shooting unit;
the fixed shooting unit is used for being arranged on the electric power equipment site, collecting electric power equipment image monitoring data in real time, and transmitting the collected electric power equipment image monitoring data to the cloud computing server;
the unmanned aerial vehicle shooting unit is used for reaching the electric power equipment site according to the specified flight route according to the inspection instruction, collecting electric power equipment image monitoring data in the inspection process, and transmitting the collected electric power equipment image monitoring data to the cloud computing server.
Specifically, the data acquisition terminal can be set in a form of a fixed shooting unit or in a form of an unmanned aerial vehicle shooting unit, wherein the fixed shooting unit is fixedly arranged in a scene where the power equipment is located, and the fixed shooting unit and the power equipment are arranged one to one, namely, the power equipment image monitoring data acquired by the fixed shooting unit are associated with the appointed power equipment; the unmanned aerial vehicle shooting unit can be flexibly arranged according to requirements, before the unmanned aerial vehicle executes the inspection task, the power equipment information designed by the inspection task can be input first, and then the power equipment image monitoring data collected by the unmanned aerial vehicle shooting unit are associated with corresponding power equipment.
Preferably, the cloud computing server comprises a preprocessing unit, an image extraction unit, a security diagnosis unit and an instruction generation unit;
the preprocessing unit is used for preprocessing the acquired power equipment image monitoring data, including filtering, framing and other processing, so as to obtain a preprocessed power equipment image;
the image extraction unit is used for carrying out target extraction processing according to the preprocessed power equipment image to obtain a power equipment target image;
the safety diagnosis unit is used for inputting the obtained power equipment target image into a safety diagnosis model trained based on big data to obtain a power equipment safety diagnosis result;
the instruction generation unit is used for generating corresponding execution instructions when the safety diagnosis result of the power equipment is abnormal, and transmitting the execution instructions to the field execution terminals corresponding to the abnormal power equipment.
The cloud computing server is arranged to perform centralized processing on the collected power equipment image monitoring data, and the cloud computing server is based on the strong data computing capability, so that real-time analysis tasks of mass power equipment image monitoring data can be completed, and the effect of safety diagnosis of power equipment is ensured.
Meanwhile, the data processing unit built based on the cloud computing server can conduct intelligent processing on the image monitoring data of the power equipment according to a preset algorithm and a model, and the intelligent level of the system is improved.
Preferably, the preprocessing unit preprocesses the acquired image monitoring data of the electric power equipment, specifically including:
carrying out framing treatment according to the acquired power equipment image monitoring data, and extracting each power equipment image frame picture;
and performing filtering processing according to the obtained image frames of the power equipment to obtain preprocessed power equipment images.
The image monitoring data of the acquired power equipment is preprocessed firstly, and corresponding image frame pictures can be extracted according to the continuously acquired image monitoring data to further process, so that the effect of processing the image monitoring data is improved. And meanwhile, the lake surface is subjected to filtering treatment based on the acquired image frame, so that the quality of the power equipment image can be improved, and a foundation is laid for safety diagnosis according to the power equipment image.
Preferably, the preprocessing unit performs filtering processing according to the obtained image frames of each electrical device, and specifically includes:
aiming at the current power equipment image frame picture, respectively acquiring dynamic characteristic coefficients of all pixel points in the picture, wherein the adopted dynamic characteristic coefficient calculation function is as follows:
wherein D (x, y) represents a dynamic characteristic coefficient of a pixel point with coordinates (x, y); representing a dynamic coefficient of gray scale, wherein A t (x, y) represents color component values of pixel points with coordinates (x, y) in the current time frame under an RGB color model, wherein a=r, g, b respectively correspond to a red component value, a green component value and a blue component value of the RGB color model; a is that t-1 (x, y) represents the color component value of the pixel point with the coordinates of (x, y) in the picture at the previous moment under the RGB color model; />Representing i a for three color components a=r, g, b t (x,y)-A t-1 Maximum value obtained by (x, y) |, +.> Represents |a obtained for three color components of a=r, g, b t (x,y)-A t-1 Mean value of (x, y) |, thresH1 represents the set gray dynamic threshold, where when +.> When the gray dynamic coefficient is->/>The value of (2) is 2, otherwise-> The value of (2) is 0; f (F) L (|L t (x,y)-L t-1 (x, y) |, thresL 1) represents the luminance dynamic coefficient, where L t (x, y) represents the brightness component value, L, of the pixel point with coordinates (x, y) in the current moment picture under the Lab color model t-1 (x, y) represents the brightness component value of the pixel point with coordinates (x, y) in the previous moment picture under the Lab color model; thresL1 represents the dynamic luminance threshold value set, when |L t (x,y)-L t-1 (x,y)|>ThresL1, F L (|L t (x,y)-L t-1 (x, y) |, thresL 1) has a value of 1, otherwise F L (|L t (x,y)-L t-1 (x, y) |, thresL 1) has a value of 0;
classifying and dividing the pixel points according to the dynamic characteristic coefficients of the pixel points:
when the dynamic characteristic coefficient D (x, y) =2 or 3 of the pixel points, further counting the dynamic characteristic coefficients of other neighborhood pixel points (a, b) in the 3×3 range with the coordinates of (x, y), if the number N (D (a, b) > 2) >4 of the dynamic characteristic coefficients D (a, b) =2 or 3 of the pixel points in the other neighborhood pixel points, marking all the pixel points in the 3×3 range with the pixel points with the coordinates of (x, y) as the center as gray dynamic pixel points, and storing the gray dynamic pixel points into a gray dynamic pixel point set colH; otherwise, if the number N (D (a, b) of the pixel points with the dynamic characteristic coefficient D (a, b) being more than or equal to 2 or 3 in other neighborhood pixel points is less than or equal to 4, marking the pixel points with the coordinates of (x, y) as gray dynamic pixel points, and storing the gray dynamic pixel points into a gray dynamic pixel point set colH;
continuing to perform classification detection on other pixels except the gray dynamic pixel point set, when the dynamic characteristic D (x, y) of the pixel points is=1, marking all non-gray dynamic pixel points in a 3 x 3 range with the pixel points with coordinates (x, y) as brightness dynamic pixel points, and storing the brightness dynamic pixel points into a brightness dynamic pixel point set colL;
marking the rest non-gray dynamic pixel points and the non-brightness dynamic pixel points as general pixel points, and storing the general pixel points into a general pixel point set colN;
the dynamic adjustment processing is respectively carried out on the pixel points of each pixel point set, and the dynamic adjustment processing comprises the following steps:
carrying out K-time iterative gray scale dynamic adjustment processing on pixel points in the gray scale dynamic pixel point set colH:
in the kth iteration, k=1, 2, …, K, and for the pixel (x, y) e colH in the gray dynamic pixel set colH, gray dynamic adjustment is performed on the gray dynamic pixel, where the gray dynamic adjustment function is adopted as follows:
in the method, in the process of the invention,in the kth iteration for representing dynamic gray scale adjustment, the gray scale value of the pixel point with coordinates of (x, y), h t-1 (x, y) represents the previous timeGray values of pixel points with coordinates (x, y) in the plane; />Representing the gray value of the pixel point with coordinates (x+i, y+j) in the k-1 iteration, wherein +.>Gray values representing pixel points with coordinates of (x+i, y+j) in the current time frame;
and carrying out brightness dynamic adjustment processing on pixel points in the brightness dynamic pixel point set colL:
aiming at pixel points (x, y) E colL in the luminance dynamic pixel point set colL, luminance dynamic adjustment is carried out on the luminance dynamic pixel points, wherein the adopted luminance dynamic adjustment function is as follows:
in the method, in the process of the invention,representing brightness component values of pixel points with coordinates (x, y) under a Lab color model after brightness dynamic adjustment; l (L) t-1 (x, y) represents the brightness component value of the pixel point with coordinates (x, y) in the previous moment picture under the Lab color model; the mean represents the average brightness component value of each pixel point in the current time picture, and the stanl represents the set standard brightness component value; num (X) represents the number of pixels in the screen, and Num (colL) represents the number of pixels in the luminance dynamic pixel set;
and carrying out brightness dynamic adjustment processing on the pixel points in the general pixel point set colN:
for the pixel points (x, y) E colN in the general pixel point set colN, the luminance dynamic pixel points are generally regulated, wherein the adopted general regulating function is as follows:
representing brightness component values of pixel points with coordinates (x, y) under a Lab color model after brightness dynamic adjustment; l (L) t (x, y) represents the brightness component value of the pixel point with coordinates (x, y) in the current time picture under the Lab color model; the mean represents the average brightness component value of each pixel point in the current time picture, and the stanl represents the set standard brightness component value; num (X) represents the number of pixels in the screen, and Num (colN) represents the number of pixels in the general pixel set;
and after the dynamic adjustment processing is finished on all pixel points in the image, outputting the preprocessed power equipment image.
Specifically, K is more than or equal to 4 and more than or equal to 2;
considering that in the process of collecting the image monitoring data of the electric equipment, the electric equipment is influenced by illumination or floater factors and the like because the electric equipment is arranged outdoors, for example, sunlight irradiates the electric equipment after passing through the swinging leaves to form shaking illumination shadows on the electric equipment, or the situation that floating shielding objects appear on the image picture of the electric equipment because of falling leaves in the falling process is easy to cause the situation that misjudgment appears when foreign object shielding detection is carried out on the image of the electric equipment. Therefore, the invention particularly provides a technical scheme for preprocessing the obtained continuous power equipment image monitoring data, which can calculate dynamic characteristic coefficients according to the pixel points in the obtained video picture frame, accurately monitor sunlight shaking pixel points and floating object shielding pixel points appearing in the image through the dynamic characteristic coefficients, and classify the pixel points; according to the obtained gray dynamic pixel points, gray adjustment processing is carried out according to gray values of the pixel points, and self-adaptive blurring processing can be carried out on foreground floaters in the images; for the brightness dynamic pixel points, brightness adjustment processing is carried out according to brightness component values of the pixel points, and self-adaptive brightness uniform adjustment processing can be carried out for the light and shadow shaking pixel points in the image; the method can effectively remove the influence of illumination or floating object factors in the image, and improve the definition of the image. And meanwhile, the integral brightness adjustment processing is carried out on the common pixel points, so that the normalization adjustment of the information features of the pixel points in the image is facilitated, and the characterization level of the feature information in the image is ensured. By means of the method, the power equipment image monitoring data are preprocessed, so that the anti-interference performance of the power equipment target image is improved, the characteristic representation level in the power equipment target image is improved, and the reliability and the robustness of subsequent safety diagnosis according to the power equipment target image are improved.
Preferably, the image extraction unit performs target extraction according to the preprocessed power equipment image, and specifically includes:
performing edge detection processing according to the preprocessed power equipment image, and dividing the preprocessed power equipment image into a foreground part and a background part according to the acquired edge information;
and carrying out image segmentation according to the partitioned foreground part to obtain a power equipment target image.
Preferably, in the security diagnosis unit, the security diagnosis model is built based on a CNN convolutional neural network structure, wherein the security diagnosis model comprises an input layer, a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer, a third convolutional layer, a full connection layer and an output layer which are sequentially connected; the input layer is used for inputting a power equipment target image; the first convolution layer contains 32 convolution kernels of size 3 x 3; the first pooling layer adopts maximum pooling treatment and comprises 32 convolution kernels, wherein the size of the convolution kernels is 2 multiplied by 2; the second convolution layer contains 64 convolution kernels, where the size of the convolution kernels is 1 x 1; the second pooling layer adopts maximum pooling treatment and comprises 64 convolution kernels, wherein the size of the convolution kernels is 2 multiplied by 2; the third convolution layer comprises 128 convolution kernels, wherein the size of the convolution kernels is 2 x 2; the full connection layer comprises 128 nodes, and a sigmoid activation function is adopted; the output layer normalizes the data of the upper layer by adopting a softmax function, converts the characteristic data into a numerical value in a 0-1 interval, and uses the obtained numerical value as a predicted value of different safety diagnosis results to realize safety diagnosis analysis of the power equipment.
Specifically, according to the normalized value output by the output layer, when the output is within the interval [0,0.2 ], outputting the safety diagnosis result of the power equipment as that the foreign matter coverage exists; when the output is in the interval [0.2, 0.4), outputting the safety diagnosis result of the power equipment as that the small animal stays; when the output is in the interval [0.4,1 ], the output power equipment safety diagnosis result is normal.
Preferably, the cloud computing server further comprises a model training unit;
the model training unit is used for extracting power equipment target images from the large database, carrying out security diagnosis identification according to the extracted power equipment target images, and forming a training set and a testing set from the power equipment target images with the security diagnosis identification;
training the safety diagnosis model by adopting a training set, testing the trained safety diagnosis model by adopting a testing set after the training is finished, and finishing the training of the safety diagnosis model when the testing accuracy exceeds a set standard level, and outputting a trained safety diagnosis model;
when the accuracy of the test does not exceed the set standard level, the model parameters are adjusted and a training set is further provided to train the model until the accuracy of the security diagnostic model exceeds the set standard level.
The power equipment target image is automatically grabbed from the large database based on the model training unit, and after expert calibration is carried out on the obtained target image, a training set and a testing set for model training are formed, so that the safety aiming model can be trained based on massive data, and the training effect and reliability of the safety diagnosis model can be improved.
Specifically, the training set is composed of standard images aiming at different types of power equipment, and images when the power equipment is under different external conditions (such as covered by foreign matters, small animals on the power equipment, personnel on the power equipment and the like); the standard images under different conditions are marked to form a training set, so that the accuracy and the adaptability of the safety diagnosis model training can be improved.
Preferably, the field execution terminal comprises a buzzer unit and a blowing unit;
the buzzer unit is used for sending out a buzzing alarm when the safety diagnosis result of the power equipment is analyzed to be that personnel or animals stay in the power equipment, so as to drive the personnel or animals approaching the power equipment;
and the blowing unit is used for blowing out strong wind to the power equipment to blow out the covered foreign matters when the power equipment is covered by the foreign matters as a result of analysis on the safety diagnosis of the power equipment.
According to different safety diagnosis results, the small animals are driven or covered foreign matters are removed through the field execution terminal, so that potential safety hazards of noise of the power equipment due to external physical influence are reduced, and reliability and intelligent level of safety operation and maintenance of the power equipment of the smart power grid are improved.
It should be noted that, in each embodiment of the present invention, each functional unit/module may be integrated in one processing unit/module, or each unit/module may exist alone physically, or two or more units/modules may be integrated in one unit/module. The integrated units/modules described above may be implemented either in hardware or in software functional units/modules.
From the description of the embodiments above, it will be apparent to those skilled in the art that the embodiments described herein may be implemented in hardware, software, firmware, middleware, code, or any suitable combination thereof. For a hardware implementation, the processor may be implemented in one or more of the following units: an Application Specific Integrated Circuit (ASIC), a Digital Signal Processor (DSP), a Digital Signal Processing Device (DSPD), a Programmable Logic Device (PLD), a Field Programmable Gate Array (FPGA), a processor, a controller, a microcontroller, a microprocessor, other electronic units designed to perform the functions described herein, or a combination thereof. For a software implementation, some or all of the flow of an embodiment may be accomplished by a computer program to instruct the associated hardware. When implemented, the above-described programs may be stored in or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a computer. The computer readable media can include, but is not limited to, RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer.
Finally, it should be noted that the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the scope of the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solution of the present invention without departing from the spirit and scope of the technical solution of the present invention.
Claims (10)
1. The intelligent power grid safety operation and maintenance system based on cloud computing and big data analysis is characterized by comprising a data acquisition terminal, a cloud computing server and a site execution terminal; the cloud computing server is respectively and wirelessly connected with the data acquisition terminal and the site execution terminal;
the data acquisition terminal is used for acquiring real-time monitoring data of the power equipment and transmitting the acquired real-time monitoring data to the cloud computing server; wherein the real-time monitoring data comprises power equipment image monitoring data;
the cloud computing server is used for carrying out power equipment safety diagnosis according to the acquired power equipment image monitoring data to obtain a power equipment safety diagnosis result, generating a corresponding execution instruction according to the obtained power equipment safety diagnosis result, and sending the execution instruction to the on-site execution terminal;
the on-site execution terminal is used for executing the received execution instruction and completing on-site safety maintenance of the power equipment.
2. The intelligent power grid safety operation and maintenance system based on cloud computing and big data analysis according to claim 1, wherein the power equipment comprises a transformer and a transformer box.
3. The intelligent power grid security operation and maintenance system based on cloud computing and big data analysis according to claim 1, further comprising a configuration management terminal;
the configuration management terminal is used for carrying out initialization setting on the data acquisition terminal information, the power equipment information and the site execution terminal information.
4. The intelligent power grid safety operation and maintenance system based on cloud computing and big data analysis according to claim 1, wherein the data acquisition terminal comprises a fixed shooting unit and an unmanned aerial vehicle shooting unit;
the fixed shooting unit is used for being arranged on the electric power equipment site, collecting electric power equipment image monitoring data in real time, and transmitting the collected electric power equipment image monitoring data to the cloud computing server;
the unmanned aerial vehicle shooting unit is used for reaching the electric power equipment site according to the specified flight route according to the inspection instruction, collecting electric power equipment image monitoring data in the inspection process, and transmitting the collected electric power equipment image monitoring data to the cloud computing server.
5. The intelligent power grid security operation and maintenance system based on cloud computing and big data analysis according to claim 1, wherein the cloud computing server comprises a preprocessing unit, an image extraction unit, a security diagnosis unit and an instruction generation unit;
the preprocessing unit is used for preprocessing the acquired power equipment image monitoring data, including filtering, framing and other processing, so as to obtain a preprocessed power equipment image;
the image extraction unit is used for carrying out target extraction processing according to the preprocessed power equipment image to obtain a power equipment target image;
the safety diagnosis unit is used for inputting the obtained power equipment target image into a safety diagnosis model trained based on big data to obtain a power equipment safety diagnosis result;
the instruction generation unit is used for generating corresponding execution instructions when the safety diagnosis result of the power equipment is abnormal, and transmitting the execution instructions to the field execution terminals corresponding to the abnormal power equipment.
6. The intelligent power grid security operation and maintenance system based on cloud computing and big data analysis according to claim 5, wherein the preprocessing unit preprocesses the acquired power equipment image monitoring data, specifically comprising:
carrying out framing treatment according to the acquired power equipment image monitoring data, and extracting each power equipment image frame picture;
and performing filtering processing according to the obtained image frames of the power equipment to obtain preprocessed power equipment images.
7. The intelligent power grid security operation and maintenance system based on cloud computing and big data analysis according to claim 5, wherein the image extraction unit performs target extraction according to the preprocessed power equipment image, and specifically comprises:
performing edge detection processing according to the preprocessed power equipment image, and dividing the preprocessed power equipment image into a foreground part and a background part according to the acquired edge information;
and carrying out image segmentation according to the partitioned foreground part to obtain a power equipment target image.
8. The intelligent power grid security operation and maintenance system based on cloud computing and big data analysis according to claim 5, wherein the cloud computing server further comprises a model training unit;
the model training unit is used for extracting power equipment target images from the large database, carrying out security diagnosis identification according to the extracted power equipment target images, and forming a training set and a testing set from the power equipment target images with the security diagnosis identification;
training the safety diagnosis model by adopting a training set, testing the trained safety diagnosis model by adopting a testing set after the training is finished, and finishing the training of the safety diagnosis model when the testing accuracy exceeds a set standard level, and outputting a trained safety diagnosis model;
when the accuracy of the test does not exceed the set standard level, the model parameters are adjusted and a training set is further provided to train the model until the accuracy of the security diagnostic model exceeds the set standard level.
9. The intelligent power grid safety operation and maintenance system based on cloud computing and big data analysis according to claim 5, wherein in the safety diagnosis unit, a safety diagnosis model is built based on a CNN convolutional neural network structure, wherein the safety diagnosis model comprises an input layer, a first convolution layer, a first pooling layer, a second convolution layer, a second pooling layer, a third convolution layer, a full connection layer and an output layer which are sequentially connected; the input layer is used for inputting a power equipment target image; the first convolution layer contains 32 convolution kernels of size 3 x 3; the first pooling layer adopts maximum pooling treatment and comprises 32 convolution kernels, wherein the size of the convolution kernels is 2 multiplied by 2; the second convolution layer contains 64 convolution kernels, where the size of the convolution kernels is 1 x 1; the second pooling layer adopts maximum pooling treatment and comprises 64 convolution kernels, wherein the size of the convolution kernels is 2 multiplied by 2; the third convolution layer comprises 128 convolution kernels, wherein the size of the convolution kernels is 2 x 2; the full connection layer comprises 128 nodes, and a sigmoid activation function is adopted; the output layer normalizes the data of the upper layer by adopting a softmax function, converts the characteristic data into a numerical value in a 0-1 interval, and uses the obtained numerical value as a predicted value of different safety diagnosis results to realize safety diagnosis analysis of the power equipment.
10. The intelligent power grid safety operation and maintenance system based on cloud computing and big data analysis according to claim 1, wherein the on-site execution terminal comprises a buzzing unit and a blowing unit;
the buzzer unit is used for sending out a buzzing alarm when the safety diagnosis result of the power equipment is analyzed to be that personnel or animals stay in the power equipment, so as to drive the personnel or animals approaching the power equipment;
and the blowing unit is used for blowing out strong wind to the power equipment to blow out the covered foreign matters when the power equipment is covered by the foreign matters as a result of analysis on the safety diagnosis of the power equipment.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211736601.XA CN116094159A (en) | 2022-12-30 | 2022-12-30 | Smart power grid safe operation and maintenance system based on cloud computing and big data analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211736601.XA CN116094159A (en) | 2022-12-30 | 2022-12-30 | Smart power grid safe operation and maintenance system based on cloud computing and big data analysis |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116094159A true CN116094159A (en) | 2023-05-09 |
Family
ID=86213241
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211736601.XA Pending CN116094159A (en) | 2022-12-30 | 2022-12-30 | Smart power grid safe operation and maintenance system based on cloud computing and big data analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116094159A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116824444A (en) * | 2023-06-13 | 2023-09-29 | 南方电网数字平台科技(广东)有限公司 | Power transmission detection system based on AI video analysis |
-
2022
- 2022-12-30 CN CN202211736601.XA patent/CN116094159A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116824444A (en) * | 2023-06-13 | 2023-09-29 | 南方电网数字平台科技(广东)有限公司 | Power transmission detection system based on AI video analysis |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108898077B (en) | Power equipment infrared chart identification method and power equipment infrared identification system | |
CN108537154B (en) | Power transmission line bird nest identification method based on HOG characteristics and machine learning | |
WO2020199538A1 (en) | Bridge key component disease early-warning system and method based on image monitoring data | |
CN110084165B (en) | Intelligent identification and early warning method for abnormal events in open scene of power field based on edge calculation | |
CN108875821A (en) | The training method and device of disaggregated model, mobile terminal, readable storage medium storing program for executing | |
CN111784633B (en) | Insulator defect automatic detection algorithm for electric power inspection video | |
CN108109385B (en) | System and method for identifying and judging dangerous behaviors of power transmission line anti-external damage vehicle | |
CN110567964B (en) | Method and device for detecting defects of power transformation equipment and storage medium | |
CN112200011B (en) | Aeration tank state detection method, system, electronic equipment and storage medium | |
CN109297978B (en) | Binocular imaging-based power line unmanned aerial vehicle inspection and defect intelligent diagnosis system | |
CN116094159A (en) | Smart power grid safe operation and maintenance system based on cloud computing and big data analysis | |
CN115131325A (en) | Breaker fault operation and maintenance monitoring method and system based on image recognition and analysis | |
CN109389322A (en) | The disconnected broken lot recognition methods of grounded-line based on target detection and long memory models in short-term | |
CN115936672A (en) | Smart power grid online safety operation and maintenance management method and system | |
CN114387558B (en) | Transformer substation monitoring method and system based on multi-dimensional video | |
CN115082813A (en) | Detection method, unmanned aerial vehicle, detection system and medium | |
CN113055657A (en) | Image acquisition method and system based on power grid line inspection | |
CN107977959B (en) | Respirator state identification method suitable for electric power robot | |
CN115912183B (en) | Ecological measure inspection method and system for high-voltage transmission line and readable storage medium | |
CN110956086B (en) | Machine room equipment online identification method based on image identification technology | |
CN111985472A (en) | Trough hay temperature image processing method based on artificial intelligence and active ball machine | |
CN116310274A (en) | State evaluation method for power transmission and transformation equipment | |
CN113284103B (en) | Substation equipment defect online detection method based on space transformation fast R-CNN model | |
CN114841932A (en) | Foreign matter detection method, system, equipment and medium for photovoltaic panel of photovoltaic power station | |
CN113989509A (en) | Crop insect pest detection method, crop insect pest detection system and crop insect pest detection equipment based on image recognition |
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 |