CN118710640B - Power transmission line defect identification and early warning method and system based on remote sensing monitoring - Google Patents
Power transmission line defect identification and early warning method and system based on remote sensing monitoring Download PDFInfo
- Publication number
- CN118710640B CN118710640B CN202411186943.8A CN202411186943A CN118710640B CN 118710640 B CN118710640 B CN 118710640B CN 202411186943 A CN202411186943 A CN 202411186943A CN 118710640 B CN118710640 B CN 118710640B
- Authority
- CN
- China
- Prior art keywords
- defect
- transmission line
- image information
- information
- early warning
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06311—Scheduling, planning or task assignment for a person or group
-
- 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
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Quality & Reliability (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Software Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Development Economics (AREA)
- Mathematical Physics (AREA)
- Educational Administration (AREA)
- Genetics & Genomics (AREA)
- Game Theory and Decision Science (AREA)
- Molecular Biology (AREA)
- Marketing (AREA)
- Physiology (AREA)
- Data Mining & Analysis (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Remote Sensing (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Databases & Information Systems (AREA)
Abstract
The invention relates to a method and a system for identifying and early warning defects of a power transmission line based on remote sensing monitoring, which belong to the technical field, the invention constructs a training set according to historical defect image information of the power transmission line, constructs a power transmission line defect identification model according to the training set, thereby identifying the remote sensing image information of the power transmission line through the power transmission line defect identification model, and acquiring defect characteristic data of the power transmission lines in each area, carrying out early warning according to the defect characteristic data of the power transmission lines in each area, generating early warning information, setting a priority maintenance scheme according to the early warning information, and carrying out work task allocation based on the priority maintenance scheme. According to the invention, the target defect characteristics in the training set are processed through the circulating space attention mechanism, so that the attention is focused on the target defect characteristics in the training set, the interference of the multi-scale characteristics on the transmission line defect recognition model can be restrained, and the recognition accuracy of the transmission line defect recognition can be improved.
Description
Technical Field
The invention relates to the technical field of power transmission line monitoring, in particular to a power transmission line defect identification and early warning method and system based on remote sensing monitoring.
Background
In recent years, unmanned aerial vehicles are rapidly popularized and applied in the power grid industry as a high-tech patrol sharp tool. Through the operation unmanned aerial vehicle flies along the circuit to take a photograph or laser scanning in step, combine intelligent AI data processing software, hidden danger defect in the circuit can be fast, accurately discovered. With the continuous improvement of the number and skill level of unmanned aerial vehicles in the national power grid industry, the 'machine inspection' of power grid inspection has come comprehensively. The technology of the unmanned aerial vehicle in China is at an international leading level, some manufacturers apply image deep learning to the front end of automatic inspection of the unmanned aerial vehicle, high-performance image automatic identification chips carried by the unmanned aerial vehicle are utilized to lock targets in real time to take pictures, meanwhile, some unmanned aerial vehicle automatic airlines are put into flight, a large amount of manpower is saved, inspection staff can be liberated from a large amount of manual labor, the inspection staff can be put into higher-order data analysis processing, the operation mode and the staff structure of an operation and maintenance team are optimized, and the reliability of a power grid is further improved. However, in the prior art, because the training process of the deep learning model may have interference of multi-scale features, the recognition accuracy of the defective power transmission line is too low, which is not beneficial to quick and accurate recognition of the defect of the power transmission line.
Disclosure of Invention
The invention overcomes the defects of the prior art and provides a method and a system for identifying and early warning defects of a power transmission line based on remote sensing monitoring.
In order to achieve the above purpose, the invention adopts the following technical scheme:
The invention provides a power transmission line defect identification and early warning method based on remote sensing monitoring, which comprises the following steps:
Constructing an unmanned aerial vehicle integrated control network, optimizing the unmanned aerial vehicle integrated control network, acquiring the optimized unmanned aerial vehicle integrated control network, and controlling the unmanned aerial vehicle to acquire remote sensing image information of the power transmission line through the unmanned aerial vehicle integrated control network;
acquiring historical defect image information of the power transmission line through the big data, constructing a training set according to the historical defect image information of the power transmission line, and constructing a power transmission line defect identification model according to the training set;
Identifying remote sensing image information of the power transmission line through a power transmission line defect identification model, acquiring defect characteristic data of the power transmission line in each region, and carrying out early warning according to the defect characteristic data of the power transmission line in each region to generate early warning information;
And setting a priority maintenance scheme according to the early warning information, and distributing work tasks based on the priority maintenance scheme.
Further, in the method, an unmanned aerial vehicle integrated control network is constructed, and the unmanned aerial vehicle integrated control network is optimized to obtain the optimized unmanned aerial vehicle integrated control network, which specifically comprises the following steps:
Constructing an unmanned aerial vehicle integrated control network, testing the unmanned aerial vehicle integrated control network to obtain historical unmanned aerial vehicle control quantity upper limit change characteristics of the unmanned aerial vehicle integrated control network, and constructing an unmanned aerial vehicle control quantity upper limit characteristic prediction model based on a convolutional neural network;
Inputting historical unmanned aerial vehicle control quantity upper limit change characteristics of the unmanned aerial vehicle integrated control network into an unmanned aerial vehicle control quantity upper limit characteristic prediction model for training, and obtaining a trained unmanned aerial vehicle control quantity upper limit characteristic prediction model;
Acquiring the upper limit change characteristic of the unmanned aerial vehicle control quantity of the unmanned aerial vehicle integrated control network within the preset time, inputting the upper limit change characteristic of the unmanned aerial vehicle control quantity into a trained unmanned aerial vehicle control quantity upper limit characteristic prediction model for prediction, and acquiring the upper limit characteristic of the unmanned aerial vehicle control quantity of the unmanned aerial vehicle integrated control network with the current time stamp;
Acquiring the real-time unmanned aerial vehicle control quantity of the unmanned aerial vehicle integrated control network, and when the real-time unmanned aerial vehicle control quantity is larger than the unmanned aerial vehicle control quantity upper limit characteristic of the unmanned aerial vehicle integrated control network of the current time stamp, adjusting the real-time unmanned aerial vehicle control quantity according to the unmanned aerial vehicle control quantity upper limit characteristic of the unmanned aerial vehicle integrated control network of the current time stamp to acquire the optimized unmanned aerial vehicle integrated control network.
Further, in the method, the historical defect image information of the power transmission line is obtained through big data, a training set is constructed according to the historical defect image information of the power transmission line, and a power transmission line defect recognition model is constructed according to the training set, and the method specifically comprises the following steps:
Acquiring historical defect image information of the power transmission line through big data, classifying defect types of the historical defect image information of the power transmission line to acquire image information of each defect type, and constructing a training set of each defect type according to the image information of each defect type;
Inputting image information in training sets of each defect type into a feature pyramid network, acquiring defect features in each piece of image information, judging whether at least two defect features exist in the image information, and introducing a circulating space attention mechanism;
When at least two defect characteristics exist in the image information, acquiring the defect characteristics corresponding to the defect type label information of the current image information as relevant defect characteristics, and when only one defect characteristic exists in the image information, taking the defect characteristics corresponding to the defect type label information of the current image information as relevant defect characteristics;
And inputting the relevant defect characteristics into a circulating space attention mechanism, so that attention is focused on the relevant defect characteristics, acquiring an attention characteristic diagram, constructing a power transmission line defect recognition model based on a deep neural network, and inputting the trained attention characteristic diagram into the power transmission line defect recognition model for coding learning.
Further, in the method, remote sensing image information of the power transmission line is identified through a power transmission line defect identification model, defect characteristic data of the power transmission line in each region are obtained, and early warning is carried out according to the defect characteristic data of the power transmission line in each region, so that early warning information is generated, and the method specifically comprises the following steps:
inputting remote sensing image information of the power transmission line into the power transmission line defect identification model for identification, acquiring defect characteristic data of the power transmission line in each region, and presetting an early warning level standard;
performing early warning grade division on defect characteristic data of the power transmission lines in each area according to early warning grade standards, acquiring defect characteristic early warning grades of the power transmission lines in each area, and acquiring geographical position information of a target area where the defects exist in the power transmission lines;
generating early warning according to the defect feature early warning level of the power transmission line in each area, the geographical position information of the target area where the defect exists in the power transmission line and the defect feature data of the power transmission line in each area, and generating early warning information.
Further, in the method, a priority maintenance scheme is set according to the early warning information, and the method specifically comprises the following steps:
Acquiring geographic position information of a target area with the defect of the power transmission line according to the early warning information, constructing a search tag based on the geographic position information of the target area with the defect of the power transmission line, and searching according to the search tag to acquire a power supply area of the power transmission line;
Acquiring the quantity information of the supply users according to the power supply area of the power transmission line, constructing a quantity sorting table of the supply users, inputting the quantity information of the supply users into the quantity sorting table of the supply users for sorting, and acquiring a sorting result of the quantity of the supply users from large to small;
The priority maintenance scheme in the target area is set based on the result of the sorting of the number of supplies from large to small, and the priority maintenance scheme is output.
Further, in the method, the task allocation is performed based on the priority maintenance scheme, which specifically includes:
Acquiring distribution characteristic information of current maintenance personnel and geographical position information of a target area with a defect of the electric wire, and calculating Euclidean distance values of positions of the maintenance personnel and the geographical position information of the target area with the defect of the electric wire according to the distribution characteristic information of the current maintenance personnel and the geographical position information of the target area with the defect of the electric wire;
Introducing a genetic algorithm, setting a genetic algebra according to the genetic algorithm, initializing maintenance personnel working position allocation according to the positions of maintenance personnel and the Euclidean distance value before the geographical position information of the target area with the defect of the transmission line, and obtaining the working task position of each maintenance personnel;
Judging whether the Euclidean distance value before the position of the maintainer and the geographical position information of the power transmission line with the defect target area is larger than a preset Euclidean distance value, and outputting the working task position of each maintainer when the Euclidean distance value before the position of the maintainer and the geographical position information of the power transmission line with the defect target area is not larger than the preset Euclidean distance value;
And when the Euclidean distance value before the position of the maintenance personnel and the geographical position information of the transmission line with the defect target area is larger than the preset Euclidean distance value, reassigning the position of the work task of each maintenance personnel until the position of the maintenance personnel and the geographical position information of the transmission line with the defect target area are not larger than the preset Euclidean distance value.
The invention provides a defect identification and early warning system of a power transmission line based on remote sensing monitoring, which comprises a memory and a processor, wherein the memory comprises a defect identification and early warning method program of the power transmission line based on the remote sensing monitoring, and when the defect identification and early warning method program of the power transmission line based on the remote sensing monitoring is executed by the processor, the following steps are realized:
Constructing an unmanned aerial vehicle integrated control network, optimizing the unmanned aerial vehicle integrated control network, acquiring the optimized unmanned aerial vehicle integrated control network, and controlling the unmanned aerial vehicle to acquire remote sensing image information of the power transmission line through the unmanned aerial vehicle integrated control network;
acquiring historical defect image information of the power transmission line through the big data, constructing a training set according to the historical defect image information of the power transmission line, and constructing a power transmission line defect identification model according to the training set;
Identifying remote sensing image information of the power transmission line through a power transmission line defect identification model, acquiring defect characteristic data of the power transmission line in each region, and carrying out early warning according to the defect characteristic data of the power transmission line in each region to generate early warning information;
And setting a priority maintenance scheme according to the early warning information, and distributing work tasks based on the priority maintenance scheme.
The third aspect of the present invention provides a computer readable storage medium, where the computer readable storage medium includes a remote sensing monitoring-based power transmission line defect identification and early warning method program, and when the remote sensing monitoring-based power transmission line defect identification and early warning method program is executed by a processor, the steps of any one of the remote sensing monitoring-based power transmission line defect identification and early warning methods are implemented.
The invention solves the defects existing in the background technology, and has the following beneficial effects:
According to the invention, an unmanned aerial vehicle integrated control network is constructed, the unmanned aerial vehicle integrated control network is optimized, the optimized unmanned aerial vehicle integrated control network is obtained, an unmanned aerial vehicle is controlled by the unmanned aerial vehicle integrated control network to obtain remote sensing image information of a power transmission line, further, historical defect image information of the power transmission line is obtained through big data, a training set is constructed according to the historical defect image information of the power transmission line, a power transmission line defect recognition model is constructed according to the training set, thereby, the remote sensing image information of the power transmission line is recognized through the power transmission line defect recognition model, defect characteristic data of the power transmission line in each region are obtained, early warning is carried out according to the defect characteristic data of the power transmission line in each region, early warning information is generated, finally, a priority maintenance scheme is set according to the early warning information, and work task allocation is carried out based on the priority maintenance scheme. According to the invention, the target defect characteristics in the training set are processed through the circulating space attention mechanism, so that the attention is focused on the target defect characteristics in the training set, the interference of the multi-scale characteristics on the transmission line defect recognition model can be restrained, and the recognition accuracy of the transmission line defect recognition can be improved.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other embodiments of the drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 shows an overall method flow diagram of a power line defect identification and early warning method based on remote sensing monitoring;
FIG. 2 shows a first method flow chart of a power line defect identification and early warning method based on remote sensing monitoring;
FIG. 3 shows a second method flow chart of a power line defect identification and early warning method based on remote sensing monitoring;
fig. 4 shows a system block diagram of a power line defect identification and early warning system based on remote sensing monitoring.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, but the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
As shown in fig. 1, the first aspect of the present invention provides a method for identifying and early warning defects of a power transmission line based on remote sensing monitoring, which comprises the following steps:
s102, constructing an unmanned aerial vehicle integrated control network, optimizing the unmanned aerial vehicle integrated control network, acquiring the optimized unmanned aerial vehicle integrated control network, and controlling the unmanned aerial vehicle to acquire remote sensing image information of a power transmission line through the unmanned aerial vehicle integrated control network;
s104, acquiring historical defect image information of the power transmission line through big data, constructing a training set according to the historical defect image information of the power transmission line, and constructing a power transmission line defect recognition model according to the training set;
S106, identifying remote sensing image information of the power transmission line through a power transmission line defect identification model, acquiring defect characteristic data of the power transmission line in each area, and carrying out early warning according to the defect characteristic data of the power transmission line in each area to generate early warning information;
s108, setting a priority maintenance scheme according to the early warning information, and distributing work tasks based on the priority maintenance scheme.
The invention processes the target defect characteristics in the training set through the circulating space attention mechanism, so that the attention is concentrated in the target defect characteristics in the training set, the interference of the multi-scale characteristics on the transmission line defect recognition model can be restrained, and the recognition accuracy of the transmission line defect recognition can be improved.
As shown in fig. 2, further, in the method, an integrated control network of the unmanned aerial vehicle is constructed, and the integrated control network of the unmanned aerial vehicle after optimization is obtained by optimizing the integrated control network of the unmanned aerial vehicle, which specifically includes:
S202, constructing an unmanned aerial vehicle integrated control network, testing the unmanned aerial vehicle integrated control network to obtain historical unmanned aerial vehicle control quantity upper limit change characteristics of the unmanned aerial vehicle integrated control network, and constructing an unmanned aerial vehicle control quantity upper limit characteristic prediction model based on a convolutional neural network;
S204, inputting historical unmanned aerial vehicle control quantity upper limit change characteristics of an unmanned aerial vehicle integrated control network into an unmanned aerial vehicle control quantity upper limit characteristic prediction model for training, and obtaining a trained unmanned aerial vehicle control quantity upper limit characteristic prediction model;
S206, acquiring the upper limit change characteristics of the unmanned aerial vehicle control quantity of the unmanned aerial vehicle integrated control network within the preset time, inputting the upper limit change characteristics of the unmanned aerial vehicle control quantity of the unmanned aerial vehicle integrated control network into a trained unmanned aerial vehicle control quantity upper limit characteristic prediction model for prediction, and acquiring the upper limit characteristics of the unmanned aerial vehicle control quantity of the unmanned aerial vehicle integrated control network with the current time stamp;
S208, acquiring the real-time unmanned aerial vehicle control quantity of the unmanned aerial vehicle integrated control network, and when the real-time unmanned aerial vehicle control quantity is larger than the unmanned aerial vehicle control quantity upper limit characteristic of the unmanned aerial vehicle integrated control network of the current time stamp, adjusting the real-time unmanned aerial vehicle control quantity according to the unmanned aerial vehicle control quantity upper limit characteristic of the unmanned aerial vehicle integrated control network of the current time stamp, and acquiring the optimized unmanned aerial vehicle integrated control network.
In practice, because the information transmission has an upper limit, the unmanned aerial vehicle control quantity of the unmanned aerial vehicle integrated control network has an upper limit, and because the unmanned aerial vehicle integrated control network is controlled by a plurality of devices, the performance of the terminal device can be degraded to a certain extent (such as the information transmission quantity is reduced in unit time) after the terminal device is used for a certain period, the unmanned aerial vehicle control quantity of the unmanned aerial vehicle integrated control network has an upper limit, and the unmanned aerial vehicle control quantity in real time can be adjusted according to the unmanned aerial vehicle control quantity upper limit characteristic of the unmanned aerial vehicle integrated control network of the current time stamp, so that the unmanned aerial vehicle integrated control network control unmanned aerial vehicle control quantity meets the preset requirement, and the stability of the unmanned aerial vehicle integrated control network is ensured.
As shown in fig. 3, in the method, further, historical defect image information of the power transmission line is obtained through big data, a training set is constructed according to the historical defect image information of the power transmission line, and a power transmission line defect recognition model is constructed according to the training set, which specifically includes:
S302, acquiring historical defect image information of a power transmission line through big data, classifying defect types of the historical defect image information of the power transmission line to acquire image information of each defect type, and constructing a training set of each defect type according to the image information of each defect type;
s304, inputting image information in training sets of each defect type into a feature pyramid network, acquiring defect features in each piece of image information, judging whether at least two defect features exist in the image information, and introducing a circulating space attention mechanism;
S306, when at least two defect characteristics exist in the image information, acquiring the defect characteristics corresponding to the defect type label information of the current image information as relevant defect characteristics, and when only one defect characteristic exists in the image information, taking the defect characteristics corresponding to the defect type label information of the current image information as relevant defect characteristics;
S308, inputting relevant defect characteristics into a circulation space attention mechanism, enabling attention to be focused on the relevant defect characteristics, acquiring an attention characteristic diagram, constructing a transmission line defect recognition model based on a deep neural network, and inputting the attention characteristic diagram focused in training into the transmission line defect recognition model for coding learning.
It should be noted that, the defect image information includes data such as a crack defect image, a corrosion defect image, a burned defect image, and the like, and since at least two defect types, such as a crack defect, a corrosion defect, and the like, may exist in one image in the training set image information of each defect type, the training set of a plurality of defect types should be input into the deep neural network for training during training, and when label information of at least two defect types appears in one image during training, the label information is interfered at this time, and by the method, a cyclic spatial attention mechanism is fused, so that attention is focused on related defect features, interference of multi-scale defect features to the transmission line defect identification model can be suppressed, thereby improving prediction accuracy of the model.
Further, in the method, remote sensing image information of the power transmission line is identified through a power transmission line defect identification model, defect characteristic data of the power transmission line in each region are obtained, and early warning is carried out according to the defect characteristic data of the power transmission line in each region, so that early warning information is generated, and the method specifically comprises the following steps:
inputting remote sensing image information of the power transmission line into the power transmission line defect identification model for identification, acquiring defect characteristic data of the power transmission line in each region, and presetting an early warning level standard;
performing early warning grade division on defect characteristic data of the power transmission lines in each area according to early warning grade standards, acquiring defect characteristic early warning grades of the power transmission lines in each area, and acquiring geographical position information of a target area where the defects exist in the power transmission lines;
generating early warning according to the defect feature early warning level of the power transmission line in each area, the geographical position information of the target area where the defect exists in the power transmission line and the defect feature data of the power transmission line in each area, and generating early warning information.
It should be noted that, the criteria of the early warning level may be set according to the defect type and the size of the defect, where the early warning level includes a low early warning level, a medium early warning level, a high early warning level, and the like.
Further, in the method, a priority maintenance scheme is set according to the early warning information, and the method specifically comprises the following steps:
Acquiring geographic position information of a target area with the defect of the power transmission line according to the early warning information, constructing a search tag based on the geographic position information of the target area with the defect of the power transmission line, and searching according to the search tag to acquire a power supply area of the power transmission line;
Acquiring the quantity information of the supply users according to the power supply area of the power transmission line, constructing a quantity sorting table of the supply users, inputting the quantity information of the supply users into the quantity sorting table of the supply users for sorting, and acquiring a sorting result of the quantity of the supply users from large to small;
The priority maintenance scheme in the target area is set based on the result of the sorting of the number of supplies from large to small, and the priority maintenance scheme is output.
It should be noted that, because maintenance personnel may be limited, a more reasonable priority maintenance scheme can be formulated by the method.
Further, in the method, the task allocation is performed based on the priority maintenance scheme, which specifically includes:
Acquiring distribution characteristic information of current maintenance personnel and geographical position information of a target area with a defect of the electric wire, and calculating Euclidean distance values of positions of the maintenance personnel and the geographical position information of the target area with the defect of the electric wire according to the distribution characteristic information of the current maintenance personnel and the geographical position information of the target area with the defect of the electric wire;
Introducing a genetic algorithm, setting a genetic algebra according to the genetic algorithm, initializing maintenance personnel working position allocation according to the positions of maintenance personnel and the Euclidean distance value before the geographical position information of the target area with the defect of the transmission line, and obtaining the working task position of each maintenance personnel;
Judging whether the Euclidean distance value before the position of the maintainer and the geographical position information of the power transmission line with the defect target area is larger than a preset Euclidean distance value, and outputting the working task position of each maintainer when the Euclidean distance value before the position of the maintainer and the geographical position information of the power transmission line with the defect target area is not larger than the preset Euclidean distance value;
And when the Euclidean distance value before the position of the maintenance personnel and the geographical position information of the transmission line with the defect target area is larger than the preset Euclidean distance value, reassigning the position of the work task of each maintenance personnel until the position of the maintenance personnel and the geographical position information of the transmission line with the defect target area are not larger than the preset Euclidean distance value.
By the method, the power transmission line to be maintained in the target area can be configured, so that each maintenance area can respond quickly, and the work task allocation of maintenance personnel is more reasonable.
In addition, the unmanned aerial vehicle is controlled to acquire the remote sensing image information of the power transmission line through the unmanned aerial vehicle integrated control network, and the method can further comprise the following steps:
The method comprises the steps of acquiring a current unmanned aerial vehicle flight route through an unmanned aerial vehicle integrated control network, acquiring remote sensing image feature data information under each influence factor through big data, inputting the remote sensing image feature data information under each influence factor into a graphic neural network, taking the influence factors as a first graphic node of the graphic neural network, taking the remote sensing image feature data information as a second graphic node of the graphic neural network, constructing an adjacency matrix according to the first graphic node and the second graphic node, inputting the adjacency matrix into a knowledge graph for storage, acquiring influence factor information of the unmanned aerial vehicle flight route within a preset range within a preset time, inputting the influence factor information of the unmanned aerial vehicle flight route within the preset range within the preset time into the knowledge graph, acquiring remote sensing image prediction feature data information of each timestamp, taking a corresponding time period as a working remote sensing task of the unmanned aerial vehicle when the remote sensing image prediction feature data information is larger than a preset remote sensing image feature threshold, taking the corresponding time period as a working time period of the unmanned aerial vehicle, and acquiring remote sensing image data of the working task of the power transmission line within the working time period of the unmanned aerial vehicle.
It is to be noted that the influence factors include visibility, haze and other data, and the rationality of data acquisition of the unmanned aerial vehicle can be further improved through the method. The remote sensing image characteristic data information comprises data such as definition, brightness and the like.
In addition, the method can further comprise the steps of obtaining remote sensing image characteristic information of each camera parameter set under each influence factor and influence factors of areas where the current unmanned aerial vehicle is located through big data, obtaining remote sensing image characteristic information of the unmanned aerial vehicle of each camera parameter according to the remote sensing image characteristic information of each camera parameter set under each influence factor and the influence factors of the areas where the current unmanned aerial vehicle is located, obtaining an adjustable range of the camera parameters of a camera of the current unmanned aerial vehicle, judging whether at least one camera parameter exists in each camera parameter so that the remote sensing image characteristic information of the unmanned aerial vehicle is larger than data of a preset remote sensing image characteristic threshold, when at least one camera parameter exists in each camera parameter so that the remote sensing image characteristic information of the unmanned aerial vehicle is larger than the data of the preset remote sensing image characteristic threshold, randomly outputting one camera parameter so that the remote sensing image characteristic information of the unmanned aerial vehicle is larger than the data of the preset remote sensing image characteristic threshold, and collecting the remote sensing image characteristic information of the unmanned aerial vehicle until at least one time period exists in the remote sensing image data of the unmanned aerial vehicle.
It should be noted that, due to the influence of the environment, no parameter exists in any way of adjusting the shooting parameters, so that the remote sensing image characteristic information of the unmanned aerial vehicle is larger than the data of the preset remote sensing image characteristic threshold value, and therefore, the image with the preset standard cannot be obtained.
As shown in fig. 4, the second aspect of the present invention provides a power transmission line defect identifying and early warning system 4 based on remote sensing monitoring, where the power transmission line defect identifying and early warning system 4 based on remote sensing monitoring includes a memory 41 and a processor 42, and the memory 41 includes a power transmission line defect identifying and early warning method program based on remote sensing monitoring, and when the power transmission line defect identifying and early warning method program based on remote sensing monitoring is executed by the processor 42, the following steps are implemented:
Constructing an unmanned aerial vehicle integrated control network, optimizing the unmanned aerial vehicle integrated control network, acquiring the optimized unmanned aerial vehicle integrated control network, and controlling the unmanned aerial vehicle to acquire remote sensing image information of the power transmission line through the unmanned aerial vehicle integrated control network;
acquiring historical defect image information of the power transmission line through the big data, constructing a training set according to the historical defect image information of the power transmission line, and constructing a power transmission line defect identification model according to the training set;
Identifying remote sensing image information of the power transmission line through a power transmission line defect identification model, acquiring defect characteristic data of the power transmission line in each region, and carrying out early warning according to the defect characteristic data of the power transmission line in each region to generate early warning information;
And setting a priority maintenance scheme according to the early warning information, and distributing work tasks based on the priority maintenance scheme.
Further, in the system, an unmanned aerial vehicle integrated control network is constructed, and the unmanned aerial vehicle integrated control network is optimized, so that the optimized unmanned aerial vehicle integrated control network is obtained, and the system specifically comprises:
Constructing an unmanned aerial vehicle integrated control network, testing the unmanned aerial vehicle integrated control network to obtain historical unmanned aerial vehicle control quantity upper limit change characteristics of the unmanned aerial vehicle integrated control network, and constructing an unmanned aerial vehicle control quantity upper limit characteristic prediction model based on a convolutional neural network;
Inputting historical unmanned aerial vehicle control quantity upper limit change characteristics of the unmanned aerial vehicle integrated control network into an unmanned aerial vehicle control quantity upper limit characteristic prediction model for training, and obtaining a trained unmanned aerial vehicle control quantity upper limit characteristic prediction model;
Acquiring the upper limit change characteristic of the unmanned aerial vehicle control quantity of the unmanned aerial vehicle integrated control network within the preset time, inputting the upper limit change characteristic of the unmanned aerial vehicle control quantity into a trained unmanned aerial vehicle control quantity upper limit characteristic prediction model for prediction, and acquiring the upper limit characteristic of the unmanned aerial vehicle control quantity of the unmanned aerial vehicle integrated control network with the current time stamp;
Acquiring the real-time unmanned aerial vehicle control quantity of the unmanned aerial vehicle integrated control network, and when the real-time unmanned aerial vehicle control quantity is larger than the unmanned aerial vehicle control quantity upper limit characteristic of the unmanned aerial vehicle integrated control network of the current time stamp, adjusting the real-time unmanned aerial vehicle control quantity according to the unmanned aerial vehicle control quantity upper limit characteristic of the unmanned aerial vehicle integrated control network of the current time stamp to acquire the optimized unmanned aerial vehicle integrated control network.
Further, in the system, the historical defect image information of the power transmission line is obtained through big data, a training set is constructed according to the historical defect image information of the power transmission line, and a power transmission line defect recognition model is constructed according to the training set, and the system specifically comprises:
Acquiring historical defect image information of the power transmission line through big data, classifying defect types of the historical defect image information of the power transmission line to acquire image information of each defect type, and constructing a training set of each defect type according to the image information of each defect type;
Inputting image information in training sets of each defect type into a feature pyramid network, acquiring defect features in each piece of image information, judging whether at least two defect features exist in the image information, and introducing a circulating space attention mechanism;
When at least two defect characteristics exist in the image information, acquiring the defect characteristics corresponding to the defect type label information of the current image information as relevant defect characteristics, and when only one defect characteristic exists in the image information, taking the defect characteristics corresponding to the defect type label information of the current image information as relevant defect characteristics;
And inputting the relevant defect characteristics into a circulating space attention mechanism, so that attention is focused on the relevant defect characteristics, acquiring an attention characteristic diagram, constructing a power transmission line defect recognition model based on a deep neural network, and inputting the trained attention characteristic diagram into the power transmission line defect recognition model for coding learning.
Further, in the system, remote sensing image information of the power transmission line is identified through a power transmission line defect identification model, defect characteristic data of the power transmission line in each region are obtained, and early warning is performed according to the defect characteristic data of the power transmission line in each region, so that early warning information is generated, and the system specifically comprises:
inputting remote sensing image information of the power transmission line into the power transmission line defect identification model for identification, acquiring defect characteristic data of the power transmission line in each region, and presetting an early warning level standard;
performing early warning grade division on defect characteristic data of the power transmission lines in each area according to early warning grade standards, acquiring defect characteristic early warning grades of the power transmission lines in each area, and acquiring geographical position information of a target area where the defects exist in the power transmission lines;
generating early warning according to the defect feature early warning level of the power transmission line in each area, the geographical position information of the target area where the defect exists in the power transmission line and the defect feature data of the power transmission line in each area, and generating early warning information.
Further, in the system, a priority maintenance scheme is set according to the early warning information, and the system specifically comprises:
Acquiring geographic position information of a target area with the defect of the power transmission line according to the early warning information, constructing a search tag based on the geographic position information of the target area with the defect of the power transmission line, and searching according to the search tag to acquire a power supply area of the power transmission line;
Acquiring the quantity information of the supply users according to the power supply area of the power transmission line, constructing a quantity sorting table of the supply users, inputting the quantity information of the supply users into the quantity sorting table of the supply users for sorting, and acquiring a sorting result of the quantity of the supply users from large to small;
The priority maintenance scheme in the target area is set based on the result of the sorting of the number of supplies from large to small, and the priority maintenance scheme is output.
Further, in the system, the task allocation is performed based on the priority maintenance scheme, which specifically includes:
Acquiring distribution characteristic information of current maintenance personnel and geographical position information of a target area with a defect of the electric wire, and calculating Euclidean distance values of positions of the maintenance personnel and the geographical position information of the target area with the defect of the electric wire according to the distribution characteristic information of the current maintenance personnel and the geographical position information of the target area with the defect of the electric wire;
Introducing a genetic algorithm, setting a genetic algebra according to the genetic algorithm, initializing maintenance personnel working position allocation according to the positions of maintenance personnel and the Euclidean distance value before the geographical position information of the target area with the defect of the transmission line, and obtaining the working task position of each maintenance personnel;
Judging whether the Euclidean distance value before the position of the maintainer and the geographical position information of the power transmission line with the defect target area is larger than a preset Euclidean distance value, and outputting the working task position of each maintainer when the Euclidean distance value before the position of the maintainer and the geographical position information of the power transmission line with the defect target area is not larger than the preset Euclidean distance value;
And when the Euclidean distance value before the position of the maintenance personnel and the geographical position information of the transmission line with the defect target area is larger than the preset Euclidean distance value, reassigning the position of the work task of each maintenance personnel until the position of the maintenance personnel and the geographical position information of the transmission line with the defect target area are not larger than the preset Euclidean distance value.
The third aspect of the present invention provides a computer readable storage medium, where the computer readable storage medium includes a remote sensing monitoring-based power transmission line defect identification and early warning method program, and when the remote sensing monitoring-based power transmission line defect identification and early warning method program is executed by a processor, the steps of any one of the remote sensing monitoring-based power transmission line defect identification and early warning methods are implemented.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units is merely a logical function division, and there may be additional divisions of actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described as separate components may or may not be physically separate, and components displayed as units may or may not be physical units, may be located in one place or distributed on a plurality of network units, and may select some or all of the units according to actual needs to achieve the purpose of the embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated in one unit, where the integrated units may be implemented in a form of hardware or a form of hardware plus a form of software functional unit.
It will be appreciated by those of ordinary skill in the art that implementing all or part of the steps of the above method embodiments may be implemented by hardware associated with program instructions, where the above program may be stored in a computer readable storage medium, where the program when executed performs the steps comprising the above method embodiments, where the above storage medium includes a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic or optical disk, or other various media that may store program code.
Or the above-described integrated units of the invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods of the embodiments of the present invention. The storage medium includes various media capable of storing program codes such as a removable storage device, a ROM, a RAM, a magnetic disk or an optical disk.
The foregoing is merely illustrative embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily think about variations or substitutions within the technical scope of the present invention, and the invention should be covered. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (7)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411186943.8A CN118710640B (en) | 2024-08-28 | 2024-08-28 | Power transmission line defect identification and early warning method and system based on remote sensing monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411186943.8A CN118710640B (en) | 2024-08-28 | 2024-08-28 | Power transmission line defect identification and early warning method and system based on remote sensing monitoring |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118710640A CN118710640A (en) | 2024-09-27 |
| CN118710640B true CN118710640B (en) | 2025-01-03 |
Family
ID=92806042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411186943.8A Active CN118710640B (en) | 2024-08-28 | 2024-08-28 | Power transmission line defect identification and early warning method and system based on remote sensing monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118710640B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115082813A (en) * | 2022-06-27 | 2022-09-20 | 北京智芯半导体科技有限公司 | Detection method, unmanned aerial vehicle, detection system and medium |
| CN117173447A (en) * | 2023-07-17 | 2023-12-05 | 北京智芯微电子科技有限公司 | Artificial intelligence-based drone autonomous inspection method and device for transmission lines |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115457006B (en) * | 2022-09-23 | 2023-08-22 | 华能澜沧江水电股份有限公司 | Unmanned aerial vehicle inspection defect classification method and device based on similarity consistency self-distillation |
| CN118413855A (en) * | 2024-03-21 | 2024-07-30 | 国网湖南省电力有限公司 | UAV self-organizing network method, system and power transmission line inspection method |
-
2024
- 2024-08-28 CN CN202411186943.8A patent/CN118710640B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115082813A (en) * | 2022-06-27 | 2022-09-20 | 北京智芯半导体科技有限公司 | Detection method, unmanned aerial vehicle, detection system and medium |
| CN117173447A (en) * | 2023-07-17 | 2023-12-05 | 北京智芯微电子科技有限公司 | Artificial intelligence-based drone autonomous inspection method and device for transmission lines |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118710640A (en) | 2024-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116188475B (en) | Intelligent control method, system and medium for automatic optical detection of appearance defects | |
| CN115908424A (en) | Building health detection method, system and medium based on three-dimensional laser scanning | |
| CN110580475A (en) | line diagnosis method based on unmanned aerial vehicle inspection, electronic device and storage medium | |
| CN112581443A (en) | Light-weight identification method for surface damage of wind driven generator blade | |
| CN116301055B (en) | Unmanned aerial vehicle inspection method and system based on building construction | |
| CN117740811B (en) | New energy automobile awning performance detection method, system and storage medium | |
| CN111401418A (en) | Employee dressing specification detection method based on improved Faster r-cnn | |
| CN112070135A (en) | Power equipment image detection method and device, power equipment and storage medium | |
| CN112613454A (en) | Electric power infrastructure construction site violation identification method and system | |
| CN116362630B (en) | Tin paste printer management method, system and medium based on Internet of things | |
| CN115049793B (en) | Digital twinning-based visualized prediction method and device for growth of trees of power transmission line | |
| CN116882790B (en) | Carbon emission equipment management method and system for mine ecological restoration area | |
| CN113988573A (en) | Risk judgment method, system and medium for inspection drone based on power system | |
| CN117314919A (en) | Packaging bag production analysis method, system and storage medium based on machine vision | |
| CN116344378B (en) | Intelligent detection system for photovoltaic panel production and detection method thereof | |
| CN115984158A (en) | Defect analysis method and device, electronic equipment and computer readable storage medium | |
| CN118823587A (en) | Construction project area measurement method and system based on drone aerial photography | |
| CN118938964B (en) | Unmanned aerial vehicle-based electric power construction site safety inspection early warning system | |
| CN118710640B (en) | Power transmission line defect identification and early warning method and system based on remote sensing monitoring | |
| CN110633702A (en) | Unmanned aerial vehicle-based line maintenance charge calculation method, server and storage medium | |
| CN119937629A (en) | A UAV inspection method and device | |
| CN115272284A (en) | Power transmission line defect identification method based on image quality evaluation | |
| CN117114420B (en) | Image recognition-based industrial and trade safety accident risk management and control system and method | |
| CN119006437A (en) | Defect detection method and device for PCB, medium and electronic equipment | |
| CN114723748A (en) | Detection method, device and equipment of motor controller and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |