CN113988573A - Risk judgment method, system and medium for routing inspection unmanned aerial vehicle based on power system - Google Patents
Risk judgment method, system and medium for routing inspection unmanned aerial vehicle based on power system Download PDFInfo
- Publication number
- CN113988573A CN113988573A CN202111234265.4A CN202111234265A CN113988573A CN 113988573 A CN113988573 A CN 113988573A CN 202111234265 A CN202111234265 A CN 202111234265A CN 113988573 A CN113988573 A CN 113988573A
- Authority
- CN
- China
- Prior art keywords
- risk
- unmanned aerial
- aerial vehicle
- data
- power system
- 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
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000007689 inspection Methods 0.000 title claims abstract description 41
- 238000012360 testing method Methods 0.000 claims abstract description 52
- 238000003062 neural network model Methods 0.000 claims abstract description 47
- 230000007613 environmental effect Effects 0.000 claims description 56
- 238000012549 training Methods 0.000 claims description 29
- 238000001514 detection method Methods 0.000 claims description 18
- 238000004088 simulation Methods 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 14
- 238000003860 storage Methods 0.000 claims description 13
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000007405 data analysis Methods 0.000 abstract description 4
- 230000007547 defect Effects 0.000 description 88
- 238000012423 maintenance Methods 0.000 description 43
- 238000004891 communication Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 238000005265 energy consumption Methods 0.000 description 6
- 238000013508 migration Methods 0.000 description 4
- 230000005012 migration Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000010485 coping Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000011835 investigation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 239000004576 sand Substances 0.000 description 2
- 230000008961 swelling Effects 0.000 description 2
- 238000013024 troubleshooting Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
-
- 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
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Marketing (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a risk judgment method, a system and a medium for patrolling an unmanned aerial vehicle based on a power system, wherein the method comprises the following steps: acquiring image information and environment information of a target area as test values; inputting the test value into a trained recognition neural network model to obtain risk data; analyzing the risk data based on big data and calling a preset database to output a solution; and outputting a corresponding instruction based on the solution to call the remaining unmanned aerial vehicles in the hangar to operate. According to the unmanned aerial vehicle inspection system, the unmanned aerial vehicle can be used for replacing traditional manpower to inspect an electric power system, for example, an overhead line or electric power equipment, during the inspection, the neural network model can be used for identifying the risk of inspection, and a corresponding solution is obtained based on big data analysis.
Description
Technical Field
The invention relates to the technical field of power system inspection, in particular to a risk judgment method, a risk judgment system and a risk judgment medium for inspecting an unmanned aerial vehicle based on a power system.
Background
The electric power system is an electric energy production and consumption system composed of power plant, power transmission and transformation line, power supply and distribution station and power consumption, and has corresponding information and control system at each link and different levels to measure, regulate, control, protect, communicate and schedule the production process of electric energy to ensure users to obtain safe and high-quality electric energy
Along with the continuous upgrading of the electric power industry of China, more and more electric wire netting systems are built and put into use, and economic benefits has also brought the maintenance problem when promoting greatly, still relies on the manpower to inspect to the line of setting up in some areas, has very big risk to operation personnel's life and property safety, and simultaneously, some areas have adopted unmanned aerial vehicle to patrol and examine, but because the dispatch is unreasonable, often cause the problem that unmanned aerial vehicle wasting of resources increases the energy consumption.
Disclosure of Invention
In view of the above problems, the present invention aims to provide a risk judgment method, system and medium for patrolling an unmanned aerial vehicle based on an electric power system, which can utilize the unmanned aerial vehicle to replace the traditional manpower to patrol the electric power system, identify the risk location and obtain a corresponding solution based on big data analysis, and simultaneously, reasonably allocate the unmanned aerial vehicle, so that the unmanned aerial vehicle can cooperatively operate, improve the operation efficiency and reduce the energy consumption.
The invention provides a risk judgment method for patrolling an unmanned aerial vehicle based on a power system, which comprises the following steps:
acquiring image information and environment information of a target area as test values;
inputting the test value into a trained recognition neural network model to obtain risk data;
analyzing the risk data based on big data and calling a preset database to output a solution;
and outputting a corresponding instruction based on the solution to call the remaining unmanned aerial vehicles in the hangar to operate.
In this scheme, the obtaining of the image information and the environmental information of the target area as the test values specifically includes:
acquiring image information of the target area based on an image acquisition device arranged on the unmanned aerial vehicle;
acquiring environmental information of the target area based on a first sensor group arranged on the unmanned aerial vehicle and a second sensor group arranged in the target area;
and performing time matching combination on the image information and the environment information to obtain the test value.
In this scheme, the inputting the test value into the trained recognition neural network model to obtain the risk data specifically includes:
inputting the test value into a trained recognition neural network model to be tested to obtain a simulation output value;
judging a risk factor based on the simulation output value, wherein the risk factor comprises a risk point position, a risk level and a risk type;
and extracting the position of the risk point, the risk level and the risk type to obtain the risk data.
In this scheme, the training method for identifying the neural network model comprises the following steps:
acquiring image information, environmental information and risk results of historical detection data;
preprocessing image information, environmental information and risk results of the historical detection data to obtain a training sample set;
inputting the training sample set into the initialized recognition neural network model for training;
acquiring the accuracy of an output result;
and if the accuracy is greater than a preset accuracy threshold, stopping training to obtain the recognition neural network model.
In this scheme, analyzing the risk data based on big data and calling a preset database to output a solution specifically includes:
analyzing the position of the risk point, the risk level and the risk type based on big data to obtain an analysis result;
calling the preset database to perform matching based on the analysis result, wherein the risk type corresponds to first data, the position of the risk point corresponds to second data, and the risk level corresponds to third data;
deriving the solution based on the first data and the second data and the third data.
In this scheme, the output of the corresponding instruction based on the solution calls the surplus unmanned aerial vehicle in the hangar to perform the operation specifically includes:
generating the corresponding instruction based on the solution;
and calling the remaining unmanned aerial vehicles in the hangar and the unmanned aerial vehicles in the working state to carry out cooperative operation based on the instruction.
The second aspect of the present invention further provides a risk judgment system for patrolling an unmanned aerial vehicle based on an electric power system, including a memory and a processor, where the memory includes a risk judgment method program for patrolling the unmanned aerial vehicle based on the electric power system, and the risk judgment method program for patrolling the unmanned aerial vehicle based on the electric power system is executed by the processor to implement the following steps:
acquiring image information and environment information of a target area as test values;
inputting the test value into a trained recognition neural network model to obtain risk data;
analyzing the risk data based on big data and calling a preset database to output a solution;
and outputting a corresponding instruction based on the solution to call the remaining unmanned aerial vehicles in the hangar to operate.
In this scheme, the obtaining of the image information and the environmental information of the target area as the test values specifically includes:
acquiring image information of the target area based on an image acquisition device arranged on the unmanned aerial vehicle;
acquiring environmental information of the target area based on a first sensor group arranged on the unmanned aerial vehicle and a second sensor group arranged in the target area;
and performing time matching combination on the image information and the environment information to obtain the test value.
In this scheme, the inputting the test value into the trained recognition neural network model to obtain the risk data specifically includes:
inputting the test value into a trained recognition neural network model to be tested to obtain a simulation output value;
judging a risk factor based on the simulation output value, wherein the risk factor comprises a risk point position, a risk level and a risk type;
and extracting the position of the risk point, the risk level and the risk type to obtain the risk data.
In this scheme, the training method for identifying the neural network model comprises the following steps:
acquiring image information, environmental information and risk results of historical detection data;
preprocessing image information, environmental information and risk results of the historical detection data to obtain a training sample set;
inputting the training sample set into the initialized recognition neural network model for training;
acquiring the accuracy of an output result;
and if the accuracy is greater than a preset accuracy threshold, stopping training to obtain the recognition neural network model.
In this scheme, analyzing the risk data based on big data and calling a preset database to output a solution specifically includes:
analyzing the position of the risk point, the risk level and the risk type based on big data to obtain an analysis result;
calling the preset database to perform matching based on the analysis result, wherein the risk type corresponds to first data, the position of the risk point corresponds to second data, and the risk level corresponds to third data;
deriving the solution based on the first data and the second data and the third data.
In this scheme, the output of the corresponding instruction based on the solution calls the surplus unmanned aerial vehicle in the hangar to perform the operation specifically includes:
generating the corresponding instruction based on the solution;
and calling the remaining unmanned aerial vehicles in the hangar and the unmanned aerial vehicles in the working state to carry out cooperative operation based on the instruction.
A third aspect of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a program of a risk determination method for a machine to patrol an unmanned aerial vehicle based on a power system, and when the program of the risk determination method for the unmanned aerial vehicle to patrol based on the power system is executed by a processor, the method implements the steps of the risk determination method for the unmanned aerial vehicle to patrol based on the power system.
According to the risk judgment method, system and medium for patrolling unmanned aerial vehicle based on the power system, the unmanned aerial vehicle can be used for replacing traditional manpower to patrol the power system, for example, overhead lines or power equipment are checked, the risk of patrolling can be identified by using a neural network model during the period, a corresponding solution is obtained based on big data analysis, and meanwhile, the unmanned aerial vehicle can be reasonably allocated based on different schemes, so that the unmanned aerial vehicle can cooperatively work, the working efficiency is improved, and the energy consumption is reduced.
Drawings
Fig. 1 shows a flow chart of a risk judgment method for patrolling an unmanned aerial vehicle based on a power system according to the invention;
fig. 2 shows a block diagram of a risk judgment system for patrolling an unmanned aerial vehicle based on a power system.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those specifically described herein, and therefore the scope of the present invention is not limited by the specific embodiments disclosed below.
Fig. 1 shows a flowchart of a risk judgment method for patrolling an unmanned aerial vehicle based on a power system according to the present application.
As shown in fig. 1, the application discloses a risk judgment method for patrolling unmanned aerial vehicle based on power system, including the following steps:
s102, acquiring image information and environment information of a target area as test values;
s104, inputting the test value into a trained recognition neural network model to obtain risk data;
s106, analyzing the risk data based on big data and calling a preset database to output a solution;
and S108, outputting a corresponding instruction based on the solution to call the remaining unmanned aerial vehicles in the hangar to operate.
It should be noted that, in the process of the unmanned aerial vehicle polling the power system, data of a polling field is obtained by identifying the image information and the environment information, that is, the test value is input into the trained recognition neural network model for testing, a simulation output value of the model is obtained to obtain the risk data, after the risk data is obtained, the database can be called according to the risk data for matching, different solutions are output for different risk problems, and then the solutions are obtained after summarizing, and in addition, after the solutions are obtained, corresponding commands can be output according to different solutions to the remaining unmanned aerial vehicles in the hangar for operation.
It is worth mentioning that the solution is used for being output to the user end and being identified by corresponding staff to take subsequent risk elimination measures.
According to the embodiment of the present invention, the obtaining of the image information and the environment information of the target area as the test values specifically includes:
acquiring image information of the target area based on an image acquisition device arranged on the unmanned aerial vehicle;
acquiring environmental information of the target area based on a first sensor group arranged on the unmanned aerial vehicle and a second sensor group arranged in the target area;
and performing time matching combination on the image information and the environment information to obtain the test value.
It should be noted that the image capturing device and the first sensor group are preset on the unmanned aerial vehicle, where the image capturing device may be a high-definition anti-shake camera, the first sensor group includes a leakage detection sensor, a bright light detection sensor, and the like, and the second sensor group is preset in the target area, where the second sensor group includes a temperature sensor, a humidity sensor, and the like.
Further, the image information of the target area is obtained through the image acquisition device, the environment information in the target area is obtained through the first sensor group and the second sensor group, and the image information and the environment information are matched to obtain the test value based on time division and the same time axis.
According to the embodiment of the present invention, the inputting the test value into the trained recognition neural network model to obtain the risk data specifically includes:
inputting the test value into a trained recognition neural network model to be tested to obtain a simulation output value;
judging a risk factor based on the simulation output value, wherein the risk factor comprises a risk point position, a risk level and a risk type;
and extracting the position of the risk point, the risk level and the risk type to obtain the risk data.
It should be noted that after the test value is obtained, the test value needs to be tested, and the test value is input into the trained recognition neural network model to be tested to obtain the simulation output value, and the risk factor is determined based on the simulation output value, where the risk factor includes the position of the risk point, the risk level, and the risk type, and is extracted to obtain the risk data.
It is worth mentioning that, for example, when a line is erected for inspection, a risk point appears on the line, and at this time, the position "# group # segment # number" of the point is recorded, and the risk type, including line group falling, rubber ring swelling, and the like, is checked, and the risk level is correspondingly checked.
According to the embodiment of the invention, the training method for identifying the neural network model comprises the following steps:
acquiring image information, environmental information and risk results of historical detection data;
preprocessing image information, environmental information and risk results of the historical detection data to obtain a training sample set;
inputting the training sample set into the initialized recognition neural network model for training;
acquiring the accuracy of an output result;
and if the accuracy is greater than a preset accuracy threshold, stopping training to obtain the recognition neural network model.
It should be noted that the neural network model identification needs a large amount of historical data for training, the larger the data size is, the more accurate the result is, the neural network model identification in the present application can be trained by using the image information, the environmental information and the risk result of the historical detection data as inputs, of course, when the neural network model is trained, not only the image information, the environmental information and the risk result of the historical detection data need to be trained, but also the determined risk reason needs to be combined for training, the obtained result can be more accurate by comparing a large amount of test data with real data, and further, the output result of the neural network identification is more accurate. Preferably, the accuracy threshold is generally set to 90%.
According to the embodiment of the invention, the analyzing the risk data based on big data and calling a preset database to output a solution specifically comprises:
analyzing the position of the risk point, the risk level and the risk type based on big data to obtain an analysis result;
calling the preset database to perform matching based on the analysis result, wherein the risk type corresponds to first data, the position of the risk point corresponds to second data, and the risk level corresponds to third data;
deriving the solution based on the first data and the second data and the third data.
It should be noted that after the risk data is obtained, big data can be used for analysis, and the preset database is called to match the analysis result, where the risk type corresponds to first data, the position of the risk point corresponds to second data, the risk level corresponds to third data, and the solution is obtained according to these three data, and the priorities of the first data, the second data, and the third data are different.
According to the embodiment of the present invention, the outputting of the corresponding instruction based on the solution calls the remaining drones in the hangar to perform the operation, specifically:
generating the corresponding instruction based on the solution;
and calling the remaining unmanned aerial vehicles in the hangar and the unmanned aerial vehicles in the working state to carry out cooperative operation based on the instruction.
It should be noted that different solutions have different instructions, for example, when it is recognized that an electrical device is on fire, a surviving unmanned aerial vehicle in a hangar can be dispatched immediately to the site for rescue, and meanwhile, an alternative unmanned aerial vehicle in the hangar can be dispatched immediately to the site for monitoring, so as to return a video picture in real time.
It is worth mentioning, still include to be in operating condition unmanned aerial vehicle schedules, specifically is:
identifying and classifying the risk types in the risk factors, wherein the risk types are classified into a type I risk and a type II risk;
and when the current risk type is judged to be the type I, establishing communication connection with the unmanned aerial vehicle within the preset range of the position of the risk point, and outputting a scheduling instruction to enable the unmanned aerial vehicle to inspect the position of the risk point for multiple times.
It should be noted that the class I risks, such as thread group dropping and rubber ring expanding, and the class II risks, such as fire risk and leakage risk, are not so high as to the class I risk emergency degree, so that the inspection operation can be performed by other unmanned aerial vehicles in the inspection working state, so as to reduce the inspection energy consumption and reduce the operation cost of the hangar.
It is worth mentioning that the method further comprises the step of dividing the risk grade, specifically:
identifying the variation of the risk factors in adjacent preset time, wherein the migration quantity of the position of the risk point is delta S, and the variation of the risk type is delta C;
invoking a level calculation to obtain the risk level based on the amount of change in the risk factor.
The rank calculation formula is:
Ls＝L0+αΔS+βΔC+θ；
wherein L issCalculating the result for said risk level, L0As a basic level, α is a parameter value of a migration amount Δ S of the position of the risk point, β is a parameter value of a variation Δ C of the risk type, two of the parameter values are dynamic setting values, β is less than or equal to 1, θ is a response value of the sensor, for example, L is taken0First order, α is 0.5, β is 1, Δ S is "8 cm", Δ C is "+ 1", θ is "2", then LsAnd 8, namely the current risk level is a first level, wherein the calculation result of the risk level is positioned at [2, 10) as the first level, at [11, 20) as the second level and at [21, 30) as the third level.
According to the embodiment of the invention, the method further comprises the following steps:
analyzing and identifying the position, the risk level and the risk type of the risk point of the risk data based on the big data;
the risk point position identification comprises the parameter identification of equipment type, working condition parameters, temperature and humidity light and regional altitude;
the risk grades comprise a first grade, a second grade and a third grade, and the risk types comprise a class I and a class II;
comparing similarity between the parameters identified according to the position of the risk point and a preset database, and acquiring a plurality of database samples, which meet preset value requirements with the equipment type, working condition parameters, temperature and humidity light and region altitude similarity threshold of the position of the risk point in the preset database, as a plurality of initial database samples;
performing similarity comparison according to the risk grades and risk types of the plurality of initial database samples and the risk data to obtain a database sample in the plurality of initial database samples with the maximum similarity comparison as a target database sample;
and taking the solution corresponding to the target database sample as a target solution.
It should be noted that, when analyzing and identifying the risk point position, the risk level and the risk type of the risk data according to the big data, the big data performs preset database similarity comparison on the device type, the working condition parameters, the temperature and humidity light and the region altitude of the risk point position, obtains a plurality of database samples with similarity thresholds meeting preset values in the preset database as a plurality of initial database samples, then performs similarity comparison on the plurality of initial database samples and the risk level and the risk type, obtains a certain database sample in the plurality of initial database samples with the largest similarity comparison value as a target database sample, and obtains a solution corresponding to the target database sample as a target solution, where the similarity comparison may be an euclidean similarity comparison or a cosine similarity comparison, and the preset similarity threshold may be 70%.
According to the embodiment of the invention, the method further comprises the following steps:
generating a corresponding instruction according to the solution, and calling the maintenance unmanned aerial vehicle with the matched performance and the matched type to carry out risk investigation or risk maintenance operation;
the maintenance unmanned aerial vehicle and the inspection unmanned aerial vehicle are in channel matching and communication connection, and parameters such as equipment type, working condition parameters, temperature and humidity light, regional altitude and the like of a target risk point position identified by inspection of the inspection unmanned aerial vehicle are obtained;
the maintenance unmanned aerial vehicle obtains environmental parameters such as weather, season, terrain, altitude and the like of a target risk point position according to the equipment type, the working condition parameters, the temperature and humidity light, the region altitude and the like;
inquiring a plurality of historical risk defect samples of equipment of corresponding types under the environmental parameters in a preset database according to the environmental parameters;
taking the defect samples with the fault probability larger than a preset value in the plurality of historical risk defect samples as target defects;
and the maintenance unmanned aerial vehicle carries out risk maintenance according to the target defects and the instructions.
It should be noted that, when the solution generates a corresponding instruction to call the maintenance unmanned aerial vehicle with matching performance and category to perform risk troubleshooting or risk maintenance operation, in order to further improve the maintenance accuracy and maintenance efficiency of the maintenance unmanned aerial vehicle to the risk, the maintenance unmanned aerial vehicle and the inspection unmanned aerial vehicle perform channel matching and communication connection to obtain the device type, the operating condition parameters, the temperature and humidity light, the regional altitude and other parameters of the target risk point position identified by the inspection unmanned aerial vehicle, the maintenance unmanned aerial vehicle obtains the environmental parameters of the weather, the season, the terrain, the altitude and the like of the target risk point position according to the parameters, and then queries the defect state of the corresponding type device with higher risk failure rate under the same historical conditions in the preset database according to the environmental parameters to perform targeted maintenance, and takes the defect sample with failure probability larger than the preset value in the database as the target defect, and the targeted maintenance is carried out according to the instruction, so that the maintenance efficiency is improved.
According to the embodiment of the invention, the method further comprises the following steps:
establishing an equipment defect risk database;
the equipment defect risk database comprises historical defect risk data corresponding to risk points generated by various types of equipment under different working condition environments, statistics of defect risk point type frequency is carried out on the various types of equipment, and the historical defect risk data corresponding to the high-frequency defect risk points of the various types of equipment are obtained;
according to the historical defect risk data of each type of equipment, counting the environmental characteristics of each type of equipment when the high-frequency defect risk point is generated;
the environmental characteristics comprise a plurality of environmental parameters such as solar terms, climate, temperature and humidity, terrain, elevation and the like;
the method comprises the steps that an inspection unmanned aerial vehicle carries out similarity comparison in an equipment defect risk database according to environmental characteristics acquired when inspection equipment is inspected, and historical defect risk data corresponding to the equipment environmental characteristics of the inspection equipment meeting the requirement of a preset similarity value in the equipment defect risk database are acquired;
sending a calling instruction to the maintenance unmanned aerial vehicle according to the defect position corresponding to the historical defect risk data;
and the maintenance unmanned aerial vehicle overhauls the defect position according to the instruction.
It should be noted that, for the maintenance accuracy rate of promotion equipment defect risk, to defect risk data such as defect risk point and position of different grade type equipment under different environmental conditions establish equipment defect risk database, can accurately find defect point and defect position according to historical defect risk data under this type equipment corresponds environmental characteristics in the database, give again the instruction and give maintenance unmanned aerial vehicle and have a needle to overhaul, effectively promote equipment defect risk and patrol and examine and repair efficiency, specifically do: establishing an equipment defect risk database which comprises historical defect risk data corresponding to risk points generated by various types of equipment under different working condition environments, carrying out statistics on defect risk point type frequency of various types of equipment to obtain historical defect risk data of various types of equipment corresponding to high-frequency defect risk points, carrying out statistics on environmental characteristics including multiple environmental parameters such as solar terms, climate, temperature and humidity, terrain, altitude and the like when the high-frequency defect risk points of various types of equipment are generated according to the historical defect risk data of various types of equipment, carrying out similarity comparison on the environmental characteristics acquired when the unmanned inspection machine inspects the equipment in the equipment defect risk database to obtain historical defect risk data corresponding to the equipment environmental characteristics of the unmanned inspection machine which meet the requirement of a preset similarity value in the equipment defect risk database, and sending a calling instruction to the unmanned inspection machine according to defect positions corresponding to the historical defect risk data to overhaul defect positions, the inspection and maintenance efficiency of coping with the equipment defect risks in different environments can be greatly improved, and the equipment safety is improved.
Fig. 2 shows a block diagram of a risk judgment system for patrolling an unmanned aerial vehicle based on a power system.
As shown in fig. 2, the present invention discloses a risk judgment system for patrolling an unmanned aerial vehicle based on a power system, which includes a memory and a processor, wherein the memory includes a risk judgment method program for patrolling the unmanned aerial vehicle based on the power system, and when executed by the processor, the risk judgment method program for patrolling the unmanned aerial vehicle based on the power system implements the following steps:
acquiring image information and environment information of a target area as test values;
inputting the test value into a trained recognition neural network model to obtain risk data;
analyzing the risk data based on big data and calling a preset database to output a solution;
and outputting a corresponding instruction based on the solution to call the remaining unmanned aerial vehicles in the hangar to operate.
It should be noted that, in the process of the unmanned aerial vehicle polling the power system, data of a polling field is obtained by identifying the image information and the environment information, that is, the test value is input into the trained recognition neural network model for testing, a simulation output value of the model is obtained to obtain the risk data, after the risk data is obtained, the database can be called according to the risk data for matching, different solutions are output for different risk problems, and then the solutions are obtained after summarizing, and in addition, after the solutions are obtained, corresponding commands can be output according to different solutions to the remaining unmanned aerial vehicles in the hangar for operation.
It is worth mentioning that the solution is used for being output to the user end and being identified by corresponding staff to take subsequent risk elimination measures.
According to the embodiment of the present invention, the obtaining of the image information and the environment information of the target area as the test values specifically includes:
acquiring image information of the target area based on an image acquisition device arranged on the unmanned aerial vehicle;
acquiring environmental information of the target area based on a first sensor group arranged on the unmanned aerial vehicle and a second sensor group arranged in the target area;
and performing time matching combination on the image information and the environment information to obtain the test value.
It should be noted that the image capturing device and the first sensor group are preset on the unmanned aerial vehicle, where the image capturing device may be a high-definition anti-shake camera, the first sensor group includes a leakage detection sensor, a bright light detection sensor, and the like, and the second sensor group is preset in the target area, where the second sensor group includes a temperature sensor, a humidity sensor, and the like.
Further, the image information of the target area is obtained through the image acquisition device, the environment information in the target area is obtained through the first sensor group and the second sensor group, and the image information and the environment information are matched to obtain the test value based on time division and the same time axis.
According to the embodiment of the present invention, the inputting the test value into the trained recognition neural network model to obtain the risk data specifically includes:
inputting the test value into a trained recognition neural network model to be tested to obtain a simulation output value;
judging a risk factor based on the simulation output value, wherein the risk factor comprises a risk point position, a risk level and a risk type;
and extracting the position of the risk point, the risk level and the risk type to obtain the risk data.
It should be noted that after the test value is obtained, the test value needs to be tested, and the test value is input into the trained recognition neural network model to be tested to obtain the simulation output value, and the risk factor is determined based on the simulation output value, where the risk factor includes the position of the risk point, the risk level, and the risk type, and is extracted to obtain the risk data.
It is worth mentioning that, for example, when a line is erected for inspection, a risk point appears on the line, and at this time, the position "# group # segment # number" of the point is recorded, and the risk type, including line group falling, rubber ring swelling, and the like, is checked, and the risk level is correspondingly checked.
According to the embodiment of the invention, the training method for identifying the neural network model comprises the following steps:
acquiring image information, environmental information and risk results of historical detection data;
preprocessing image information, environmental information and risk results of the historical detection data to obtain a training sample set;
inputting the training sample set into the initialized recognition neural network model for training;
acquiring the accuracy of an output result;
and if the accuracy is greater than a preset accuracy threshold, stopping training to obtain the recognition neural network model.
It should be noted that the neural network model identification needs a large amount of historical data for training, the larger the data size is, the more accurate the result is, the neural network model identification in the present application can be trained by using the image information, the environmental information and the risk result of the historical detection data as inputs, of course, when the neural network model is trained, not only the image information, the environmental information and the risk result of the historical detection data need to be trained, but also the determined risk reason needs to be combined for training, the obtained result can be more accurate by comparing a large amount of test data with real data, and further, the output result of the neural network identification is more accurate. Preferably, the accuracy threshold is generally set to 90%.
According to the embodiment of the invention, the analyzing the risk data based on big data and calling a preset database to output a solution specifically comprises:
analyzing the position of the risk point, the risk level and the risk type based on big data to obtain an analysis result;
calling the preset database to perform matching based on the analysis result, wherein the risk type corresponds to first data, the position of the risk point corresponds to second data, and the risk level corresponds to third data;
deriving the solution based on the first data and the second data and the third data.
It should be noted that after the risk data is obtained, big data can be used for analysis, and the preset database is called to match the analysis result, where the risk type corresponds to first data, the position of the risk point corresponds to second data, the risk level corresponds to third data, and the solution is obtained according to these three data, and the priorities of the first data, the second data, and the third data are different.
According to the embodiment of the present invention, the outputting of the corresponding instruction based on the solution calls the remaining drones in the hangar to perform the operation, specifically:
generating the corresponding instruction based on the solution;
and calling the remaining unmanned aerial vehicles in the hangar and the unmanned aerial vehicles in the working state to carry out cooperative operation based on the instruction.
It should be noted that different solutions have different instructions, for example, when it is recognized that an electrical device is on fire, a surviving unmanned aerial vehicle in a hangar can be dispatched immediately to the site for rescue, and meanwhile, an alternative unmanned aerial vehicle in the hangar can be dispatched immediately to the site for monitoring, so as to return a video picture in real time.
It is worth mentioning, still include to be in operating condition unmanned aerial vehicle schedules, specifically is: .
Identifying and classifying the risk types in the risk factors, wherein the risk types are classified into a type I risk and a type II risk;
and when the current risk type is judged to be the type I, establishing communication connection with the unmanned aerial vehicle within the preset range of the position of the risk point, and outputting a scheduling instruction to enable the unmanned aerial vehicle to inspect the position of the risk point for multiple times.
It should be noted that the class I risks, such as thread group dropping and rubber ring expanding, and the class II risks, such as fire risk and leakage risk, are not so high as to the class I risk emergency degree, so that the inspection operation can be performed by other unmanned aerial vehicles in the inspection working state, so as to reduce the inspection energy consumption and reduce the operation cost of the hangar.
It is worth mentioning that the method further comprises the step of dividing the risk grade, specifically:
identifying the variation of the risk factors in adjacent preset time, wherein the migration quantity of the position of the risk point is delta S, and the variation of the risk type is delta C;
invoking a level calculation to obtain the risk level based on the amount of change in the risk factor.
The rank calculation formula is:
Ls＝L0+αΔS+βΔC+θ；
wherein L issCalculating the result for said risk level, L0As a basic level, α is a parameter value of a migration amount Δ S of the position of the risk point, β is a parameter value of a variation Δ C of the risk type, two of the parameter values are dynamic setting values, β is less than or equal to 1, θ is a response value of the sensor, for example, L is taken0First order, α is 0.5, β is 1, Δ S is "8 cm", Δ C is "+ 1", θ is "2", then LsAnd 8, namely the current risk level is a first level, wherein the calculation result of the risk level is positioned at [2, 10) as the first level, at [11, 20) as the second level and at [21, 30) as the third level.
According to the embodiment of the invention, the method further comprises the following steps:
analyzing and identifying the position, the risk level and the risk type of the risk point of the risk data based on the big data;
the risk point position identification comprises the parameter identification of equipment type, working condition parameters, temperature and humidity light and regional altitude;
the risk grades comprise a first grade, a second grade and a third grade, and the risk types comprise a class I and a class II;
comparing similarity between the parameters identified according to the position of the risk point and a preset database, and acquiring a plurality of database samples, which meet preset value requirements with the equipment type, working condition parameters, temperature and humidity light and region altitude similarity threshold of the position of the risk point in the preset database, as a plurality of initial database samples;
performing similarity comparison according to the risk grades and risk types of the plurality of initial database samples and the risk data to obtain a database sample in the plurality of initial database samples with the maximum similarity comparison as a target database sample;
and taking the solution corresponding to the target database sample as a target solution.
It should be noted that, when analyzing and identifying the risk point position, the risk level and the risk type of the risk data according to the big data, the big data performs preset database similarity comparison on the device type, the working condition parameters, the temperature and humidity light and the region altitude of the risk point position, obtains a plurality of database samples with similarity thresholds meeting preset values in the preset database as a plurality of initial database samples, then performs similarity comparison on the plurality of initial database samples and the risk level and the risk type, obtains a certain database sample in the plurality of initial database samples with the largest similarity comparison value as a target database sample, and obtains a solution corresponding to the target database sample as a target solution, where the similarity comparison may be an euclidean similarity comparison or a cosine similarity comparison, and the preset similarity threshold may be 70%.
According to the embodiment of the invention, the method further comprises the following steps:
generating a corresponding instruction according to the solution, and calling the maintenance unmanned aerial vehicle with the matched performance and the matched type to carry out risk investigation or risk maintenance operation;
the maintenance unmanned aerial vehicle and the inspection unmanned aerial vehicle are in channel matching and communication connection, and parameters such as equipment type, working condition parameters, temperature and humidity light, regional altitude and the like of a target risk point position identified by inspection of the inspection unmanned aerial vehicle are obtained;
the maintenance unmanned aerial vehicle obtains environmental parameters such as weather, season, terrain, altitude and the like of a target risk point position according to the equipment type, the working condition parameters, the temperature and humidity light, the region altitude and the like;
inquiring a plurality of historical risk defect samples of equipment of corresponding types under the environmental parameters in a preset database according to the environmental parameters;
taking the defect samples with the fault probability larger than a preset value in the plurality of historical risk defect samples as target defects;
and the maintenance unmanned aerial vehicle carries out risk maintenance according to the target defects and the instructions.
It should be noted that, when the solution generates a corresponding instruction to call the maintenance unmanned aerial vehicle with matching performance and category to perform risk troubleshooting or risk maintenance operation, in order to further improve the maintenance accuracy and maintenance efficiency of the maintenance unmanned aerial vehicle to the risk, the maintenance unmanned aerial vehicle and the inspection unmanned aerial vehicle perform channel matching and communication connection to obtain the device type, the operating condition parameters, the temperature and humidity light, the regional altitude and other parameters of the target risk point position identified by the inspection unmanned aerial vehicle, the maintenance unmanned aerial vehicle obtains the environmental parameters of the weather, the season, the terrain, the altitude and the like of the target risk point position according to the parameters, and then queries the defect state of the corresponding type device with higher risk failure rate under the same historical conditions in the preset database according to the environmental parameters to perform targeted maintenance, and takes the defect sample with failure probability larger than the preset value in the database as the target defect, and the targeted maintenance is carried out according to the instruction, so that the maintenance efficiency is improved.
According to the embodiment of the invention, the method further comprises the following steps:
establishing an equipment defect risk database;
the equipment defect risk database comprises historical defect risk data corresponding to risk points generated by various types of equipment under different working condition environments, statistics of defect risk point type frequency is carried out on the various types of equipment, and the historical defect risk data corresponding to the high-frequency defect risk points of the various types of equipment are obtained;
according to the historical defect risk data of each type of equipment, counting the environmental characteristics of each type of equipment when the high-frequency defect risk point is generated;
the environmental characteristics comprise a plurality of environmental parameters such as solar terms, climate, temperature and humidity, terrain, elevation and the like;
the method comprises the steps that an inspection unmanned aerial vehicle carries out similarity comparison in an equipment defect risk database according to environmental characteristics acquired when inspection equipment is inspected, and historical defect risk data corresponding to the equipment environmental characteristics of the inspection equipment meeting the requirement of a preset similarity value in the equipment defect risk database are acquired;
sending a calling instruction to the maintenance unmanned aerial vehicle according to the defect position corresponding to the historical defect risk data;
and the maintenance unmanned aerial vehicle overhauls the defect position according to the instruction.
It should be noted that, for the maintenance accuracy rate of promotion equipment defect risk, to defect risk data such as defect risk point and position of different grade type equipment under different environmental conditions establish equipment defect risk database, can accurately find defect point and defect position according to historical defect risk data under this type equipment corresponds environmental characteristics in the database, give again the instruction and give maintenance unmanned aerial vehicle and have a needle to overhaul, effectively promote equipment defect risk and patrol and examine and repair efficiency, specifically do: establishing an equipment defect risk database which comprises historical defect risk data corresponding to risk points generated by various types of equipment under different working condition environments, carrying out statistics on defect risk point type frequency of various types of equipment to obtain historical defect risk data of various types of equipment corresponding to high-frequency defect risk points, carrying out statistics on environmental characteristics including multiple environmental parameters such as solar terms, climate, temperature and humidity, terrain, altitude and the like when the high-frequency defect risk points of various types of equipment are generated according to the historical defect risk data of various types of equipment, carrying out similarity comparison on the environmental characteristics acquired when the unmanned inspection machine inspects the equipment in the equipment defect risk database to obtain historical defect risk data corresponding to the equipment environmental characteristics of the unmanned inspection machine which meet the requirement of a preset similarity value in the equipment defect risk database, and sending a calling instruction to the unmanned inspection machine according to defect positions corresponding to the historical defect risk data to overhaul defect positions, the inspection and maintenance efficiency of coping with the equipment defect risks in different environments can be greatly improved, and the equipment safety is improved.
A third aspect of the present invention provides a computer-readable storage medium, where the computer-readable storage medium includes a program of a risk determination method for a machine to patrol an unmanned aerial vehicle based on a power system, and when the program of the risk determination method for the unmanned aerial vehicle to patrol based on the power system is executed by a processor, the method implements the steps of the risk determination method for the unmanned aerial vehicle to patrol based on the power system.
According to the risk judgment method, system and medium for patrolling unmanned aerial vehicle based on the power system, the unmanned aerial vehicle can be used for replacing traditional manpower to patrol the power system, for example, overhead lines or power equipment are checked, the risk of patrolling can be identified by using a neural network model during the period, a corresponding solution is obtained based on big data analysis, and meanwhile, the unmanned aerial vehicle can be reasonably allocated based on different schemes, so that the unmanned aerial vehicle can cooperatively work, the working efficiency is improved, and the energy consumption is reduced.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described device embodiments are merely illustrative, for example, the division of the unit is only a logical functional division, and there may be other division ways in actual implementation, such as: multiple units or components may be combined, or may be integrated into another system, or some features may be omitted, or not implemented. In addition, the coupling, direct coupling or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection between the devices or units may be electrical, mechanical or other forms.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units; can be located in one place or distributed on a plurality of network units; some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, all the functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately regarded as one unit, or two or more units may be integrated into one unit; the integrated unit can be realized in a form of hardware, or in a form of hardware plus a software functional unit.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Alternatively, the integrated unit of the present invention may be stored in a computer-readable storage medium if it is implemented in the form of a software functional module and sold or used as a separate product. Based on such understanding, the technical solutions of the embodiments of the present invention may be essentially implemented or a part contributing to the prior art may be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, a ROM, a RAM, a magnetic or optical disk, or various other media that can store program code.
Claims (10)
1. A risk judgment method for patrolling unmanned aerial vehicle based on a power system is characterized by comprising the following steps:
acquiring image information and environment information of a target area as test values;
inputting the test value into a trained recognition neural network model to obtain risk data;
analyzing the risk data based on big data and calling a preset database to output a solution;
and outputting a corresponding instruction based on the solution to call the remaining unmanned aerial vehicles in the hangar to operate.
2. The risk judgment method for patrolling unmanned aerial vehicle based on power system according to claim 1, wherein the obtaining of the image information and the environmental information of the target area as test values specifically comprises:
acquiring image information of the target area based on an image acquisition device arranged on the unmanned aerial vehicle;
acquiring environmental information of the target area based on a first sensor group arranged on the unmanned aerial vehicle and a second sensor group arranged in the target area;
and performing time matching combination on the image information and the environment information to obtain the test value.
3. The risk judgment method for patrolling unmanned aerial vehicle based on power system according to claim 2, wherein the test value is input into the trained recognition neural network model to obtain risk data, and specifically comprises:
inputting the test value into a trained recognition neural network model to be tested to obtain a simulation output value;
judging a risk factor based on the simulation output value, wherein the risk factor comprises a risk point position, a risk level and a risk type;
and extracting the position of the risk point, the risk level and the risk type to obtain the risk data.
4. The risk judgment method for patrolling unmanned aerial vehicle based on power system according to claim 3, wherein the neural network model recognition training method comprises the following steps:
acquiring image information, environmental information and risk results of historical detection data;
preprocessing image information, environmental information and risk results of the historical detection data to obtain a training sample set;
inputting the training sample set into the initialized recognition neural network model for training;
acquiring the accuracy of an output result;
and if the accuracy is greater than a preset accuracy threshold, stopping training to obtain the recognition neural network model.
5. The risk judgment method for the inspection of the unmanned aerial vehicle based on the power system according to claim 3, wherein the risk data is analyzed based on the big data and a preset database is called to output a solution, specifically:
analyzing the position of the risk point, the risk level and the risk type based on big data to obtain an analysis result;
calling the preset database to perform matching based on the analysis result, wherein the risk type corresponds to first data, the position of the risk point corresponds to second data, and the risk level corresponds to third data;
deriving the solution based on the first data and the second data and the third data.
6. The risk judgment method for patrolling unmanned aerial vehicle based on power system according to claim 5, wherein outputting a corresponding instruction based on the solution calls the remaining unmanned aerial vehicles in the hangar to perform operation, specifically:
generating the corresponding instruction based on the solution;
and calling the remaining unmanned aerial vehicles in the hangar and the unmanned aerial vehicles in the working state to carry out cooperative operation based on the instruction.
7. The risk judgment system for patrolling unmanned aerial vehicle based on power system is characterized by comprising a memory and a processor, wherein the memory comprises a risk judgment method program for patrolling unmanned aerial vehicle based on power system, and the risk judgment method program for patrolling unmanned aerial vehicle based on power system realizes the following steps when executed by the processor:
acquiring image information and environment information of a target area as test values;
inputting the test value into a trained recognition neural network model to obtain risk data;
analyzing the risk data based on big data and calling a preset database to output a solution;
and outputting a corresponding instruction based on the solution to call the remaining unmanned aerial vehicles in the hangar to operate.
8. The risk judgment system for the inspection of the unmanned aerial vehicle based on the power system according to claim 7, wherein the obtaining of the image information and the environmental information of the target area is used as a test value, and specifically comprises:
acquiring image information of the target area based on an image acquisition device arranged on the unmanned aerial vehicle;
acquiring environmental information of the target area based on a first sensor group arranged on the unmanned aerial vehicle and a second sensor group arranged in the target area;
and performing time matching combination on the image information and the environment information to obtain the test value.
9. The risk judgment system for the inspection of the unmanned aerial vehicle based on the power system according to claim 8, wherein the test value is input into the trained recognition neural network model to obtain risk data, specifically:
inputting the test value into a trained recognition neural network model to be tested to obtain a simulation output value;
judging a risk factor based on the simulation output value, wherein the risk factor comprises a risk point position, a risk level and a risk type;
and extracting the position of the risk point, the risk level and the risk type to obtain the risk data.
10. A computer-readable storage medium, wherein the computer-readable storage medium includes a risk judgment method program for patrolling unmanned aerial vehicle based on power system, and when the risk judgment method program for patrolling unmanned aerial vehicle based on power system is executed by a processor, the steps of the risk judgment method for patrolling unmanned aerial vehicle based on power system according to any one of claims 1 to 6 are implemented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111234265.4A CN113988573A (en) | 2021-10-22 | 2021-10-22 | Risk judgment method, system and medium for routing inspection unmanned aerial vehicle based on power system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111234265.4A CN113988573A (en) | 2021-10-22 | 2021-10-22 | Risk judgment method, system and medium for routing inspection unmanned aerial vehicle based on power system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113988573A true CN113988573A (en) | 2022-01-28 |
Family
ID=79740486
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111234265.4A Pending CN113988573A (en) | 2021-10-22 | 2021-10-22 | Risk judgment method, system and medium for routing inspection unmanned aerial vehicle based on power system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113988573A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050813A (en) * | 2023-03-31 | 2023-05-02 | 深圳市城市公共安全技术研究院有限公司 | Control method and equipment for photovoltaic operation and maintenance system and readable storage medium |
| CN116385913A (en) * | 2023-06-05 | 2023-07-04 | 四川康吉笙科技有限公司 | Monitoring method and system based on image recognition |
| CN117132119A (en) * | 2023-10-20 | 2023-11-28 | 国网湖北省电力有限公司 | 5G slice network-based power line inspection method, system and storage medium |
-
2021
- 2021-10-22 CN CN202111234265.4A patent/CN113988573A/en active Pending
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116050813A (en) * | 2023-03-31 | 2023-05-02 | 深圳市城市公共安全技术研究院有限公司 | Control method and equipment for photovoltaic operation and maintenance system and readable storage medium |
| CN116050813B (en) * | 2023-03-31 | 2023-06-06 | 深圳市城市公共安全技术研究院有限公司 | Control method and equipment for photovoltaic operation and maintenance system and readable storage medium |
| CN116385913A (en) * | 2023-06-05 | 2023-07-04 | 四川康吉笙科技有限公司 | Monitoring method and system based on image recognition |
| CN116385913B (en) * | 2023-06-05 | 2023-09-29 | 四川康吉笙科技有限公司 | Monitoring method and system based on image recognition |
| CN117132119A (en) * | 2023-10-20 | 2023-11-28 | 国网湖北省电力有限公司 | 5G slice network-based power line inspection method, system and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113988573A (en) | Risk judgment method, system and medium for routing inspection unmanned aerial vehicle based on power system | |
| CN108416294B (en) | Fan blade fault intelligent identification method based on deep learning | |
| CN110674861B (en) | Intelligent analysis method and device for power transmission and transformation inspection images | |
| CN111307823B (en) | System and method for detecting typical visual defects of power transformation equipment based on edge cloud cooperation | |
| CN108537154A (en) | Transmission line of electricity Bird's Nest recognition methods based on HOG features and machine learning | |
| CN116742799A (en) | Auxiliary power distribution monitoring and early warning system based on Internet of things technology | |
| CN112613454A (en) | Electric power infrastructure construction site violation identification method and system | |
| CN116184950B (en) | Multisource data extraction and analysis system for automobile production line | |
| CN115511367B (en) | Intelligent quality management system of production line | |
| CN106649915A (en) | Early warning system for defects of transmission and distribution power grid equipment | |
| CN111754737A (en) | Online identification and evaluation device and method for installation acceptance of metering device | |
| CN115169602A (en) | Maintenance method and device for power equipment, storage medium and computer equipment | |
| CN115060312A (en) | Building material safety monitoring system based on artificial intelligence | |
| CN114744756A (en) | Intelligent power transmission line inspection system based on machine vision | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN112085221B (en) | Intelligent operation and detection method and system for digital pole tower | |
| CN115879915B (en) | Cross-platform standardized overhaul method for power plant | |
| CN116866512A (en) | Photovoltaic power station inspection system and operation method thereof | |
| CN108573233B (en) | Power grid ceramic insulator identification method based on image processing technology | |
| CN116344378A (en) | Intelligent detection system for photovoltaic panel production and detection method thereof | |
| CN115689206A (en) | Intelligent monitoring method for transformer substation infrastructure progress based on deep learning | |
| CN115187880A (en) | Communication optical cable defect detection method and system based on image recognition and storage medium | |
| CN115086391A (en) | Fault expert system based on wearable distribution network inspection equipment and use method thereof | |
| CN112132819A (en) | Communication network management monitoring method based on artificial intelligence | |
| CN111930982A (en) | Intelligent labeling method for power grid images |
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 |