CN113963276A - Unmanned aerial vehicle autonomous inspection method and system for power transmission line - Google Patents
Unmanned aerial vehicle autonomous inspection method and system for power transmission line Download PDFInfo
- Publication number
- CN113963276A CN113963276A CN202111230826.3A CN202111230826A CN113963276A CN 113963276 A CN113963276 A CN 113963276A CN 202111230826 A CN202111230826 A CN 202111230826A CN 113963276 A CN113963276 A CN 113963276A
- Authority
- CN
- China
- Prior art keywords
- point cloud
- cloud data
- tower
- unmanned aerial
- aerial vehicle
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C1/00—Registering, indicating or recording the time of events or elapsed time, e.g. time-recorders for work people
- G07C1/20—Checking timed patrols, e.g. of watchman
Abstract
The application relates to the technical field of electric power unmanned aerial vehicle inspection, in particular to an unmanned aerial vehicle autonomous inspection method and system for a power transmission line. The method comprises the following steps: collecting and preprocessing laser point cloud data to obtain preprocessed laser point cloud data; establishing a three-dimensional model of the power line corridor by utilizing the preprocessed laser point cloud data; classifying the preprocessed laser point cloud data through Hough transformation and a Kmeans clustering algorithm to obtain tower point cloud and wire point cloud data; performing curve fitting on the wire point cloud data to obtain a curve fitting equation and calculating to obtain a wire point coordinate; determining a photographing point of each base tower according to the tower point cloud data to form an unmanned aerial vehicle autonomous inspection track connected with the photographing point of each base tower; unmanned aerial vehicle accomplishes independently flight based on the accurate location service of big dipper, realizes that transmission line's becomes more meticulous and patrols and examines to positioning system's reliability is low among the solution prior art, and it is low to patrol and examine the accuracy, the problem that operating capability requires height.
Description
Technical Field
The application relates to the technical field of electric power unmanned aerial vehicle inspection, in particular to an unmanned aerial vehicle autonomous inspection method and system for a power transmission line.
Background
For a long time, the inspection work of the power transmission line network with huge power grid in China mainly depends on a manual inspection mode. The timeliness, the safety and the accuracy of the routing inspection result are difficult problems which plague the power grid operation and maintenance department for a long time in the era of patrol. In recent years, unmanned aerial vehicles are rapidly popularized and applied in the power grid industry as a high-tech patrol sharp device. The flight control hand can rapidly and accurately discover hidden danger defects in the line by operating the unmanned aerial vehicle to fly along the line, synchronously photographing or scanning by laser and combining intelligent AI data processing software. Through utilizing unmanned aerial vehicle to carry out the work of patrolling and examining of transmission line network, improved and patrolled and examined efficiency, but new working method has also brought new challenge. Unmanned aerial vehicle patrols and examines and need carry out long-time flight control operation to unmanned aerial vehicle, and this requires very high to basic unit team personnel's unmanned aerial vehicle operating skill. Accidents such as 'explosion' and 'tower collision' are increased along with the expansion of the airplane patrol business. On the premise of safe flight, the patrolling team personnel with different unmanned aerial vehicle operating skills of the same line patrols the machine, and different patrolling conclusions can be obtained. Consequently, the machine patrols the operation mode of patrolling and examining of industry urgent need more intelligent, safer, more controllable to reduce unmanned aerial vehicle operation threshold, reduce the influence of relevant personnel experience to the work of patrolling and examining, further the lifting machine patrols the operating efficiency.
In the prior art, a method is a process that an unmanned aerial vehicle air route autonomously plans flight, a difference GPS is combined with LiDAR data, an algorithm is used for dividing the unmanned aerial vehicle air route into a flyable block and a no-fly block, an optimal flight path of unmanned aerial vehicle electric power inspection is autonomously planned according to a specified principle, and autonomous flight is realized; according to the method, only the point cloud is used for distinguishing the flyable area and the no-fly area, and the power line and the tower in the flyable area are not automatically identified and classified, so that the accuracy of routing inspection is reduced. The other method utilizes laser point cloud data to obtain power line and tower point clouds, and calculates the coordinates of the insulator through a curve fitting equation; setting a camera focal length and a safe flying distance according to the coordinates of the insulator to form an unmanned aerial vehicle flying track connecting each photographing point; the power line corridor three-dimensional point cloud is obtained, the power line point cloud is extracted, the relative position relation is obtained, and the adjustment information of the flight path is planned, so that the flight path is formed. The method simply carries out route planning and cannot meet the requirement of high-precision fine routing inspection.
However, in the prior art, GPS is mostly used as a positioning system of the drone. If the GPS system is encrypted, shielded and tailored for civil use in the United states, the whole positioning system has fundamental problems. The unmanned aerial vehicle of the existing power industry mostly needs a flight control hand to carry out long-time flight control operation, and has high requirements on the operation capacity of team personnel due to the fact that the unmanned aerial vehicle is greatly influenced by the environment and the weather. Although the existing unmanned aerial vehicle has a route planning function, the route planning function can be used for realizing an autonomous inspection function, but the existing unmanned aerial vehicle cannot be close to a pole tower for fine inspection and only can realize rough inspection.
Disclosure of Invention
The application provides an unmanned aerial vehicle autonomous inspection method and system for a power transmission line, and the problems that in the prior art, a positioning system is low in reliability, low in inspection accuracy and high in operation capability requirement can be solved to a certain extent by establishing a point cloud tower data model.
The embodiment of the application is realized as follows:
a first aspect of the embodiments of the present application provides a power transmission line unmanned aerial vehicle autonomous inspection method, including:
collecting laser point cloud data of a power line corridor, and preprocessing the laser point cloud data to obtain preprocessed laser point cloud data;
establishing a three-dimensional model of the power line corridor by utilizing the preprocessed laser point cloud data;
classifying the preprocessed laser point cloud data through Hough transformation and a Kmeans clustering algorithm to obtain tower point cloud and wire point cloud data;
obtaining a point cloud tower data model based on the three-dimensional model and the classified laser point cloud data;
performing curve fitting on the wire point cloud data to obtain a curve fitting equation and calculating to obtain a wire point coordinate;
carrying out position identification on the point cloud data of the tower through a convolutional neural network method to obtain a tower coordinate;
determining a photographing point of each base tower in the point cloud tower data model according to the tower point cloud data;
setting a camera focal length and a safe flying distance according to the wire point coordinates and the tower coordinates to form an unmanned aerial vehicle autonomous inspection track connected with the photographing point of each base tower;
unmanned aerial vehicle is based on the accurate location service of big dipper, the foundation unmanned aerial vehicle independently patrols and examines the orbit and independently fly, realizes patrolling and examining that becomes more meticulous of transmission line.
In some embodiments, the obtaining a three-dimensional model of the power line corridor comprises: acquiring laser point cloud data of the power line corridor by using an unmanned aerial vehicle carrying laser radar system, and settling and analyzing the preprocessed laser point cloud data to obtain characteristic data for establishing a three-dimensional model of the power line corridor; processing the characteristic data to obtain a three-dimensional model of the power line traffic, wherein the laser point cloud data comprises: laser data, image data, and camera data.
In some embodiments, the method for obtaining tower point cloud and wire point cloud data comprises: calculating the slope of the preprocessed laser point cloud data to obtain the line trend slope of the power transmission line; carrying out edge detection on the preprocessed laser point cloud data through a Canny algorithm to obtain edge points; carrying out Hough transformation and a Kmeans clustering algorithm on the edge points to obtain two cluster types for representing the slope of the straight line; obtaining wire point cloud data by comparing the two cluster categories with the line trend slope; and performing Kmeans clustering on the preprocessed laser point cloud data except the wire point cloud data to obtain tower point cloud data.
In some embodiments, a method of obtaining the coordinates of the wire points comprises: selecting the minimum value along the X, Y, Z direction in the corresponding coordinate values of the wire point cloud data to form a space point [ x ]min,ymin,zmin]As a space coordinate origin, performing coordinate conversion on the wire point cloud data through the space coordinate origin to obtain wire point cloud data subjected to relative coordinate processing; selecting the minimum value along the X direction and the corresponding Y value in the coordinate values corresponding to the wire point cloud data to form a plane point [ Xmin,y(xmin)]The wire point cloud data is used as a plane coordinate origin, and is subjected to rotary transformation on an X-Y plane through the plane coordinate origin to obtain the wire point cloud data subjected to rotary transformation; fitting the conducting wire point cloud data processed by the relative coordinates through a least square method to obtain X-Y plane straight line fitting; fitting the lead point cloud data subjected to rotation transformation to obtain X-Z plane straight line fitting; fitting the three-dimensional space by fitting the X-Y plane straight line and the X-Z plane straight line to obtain the fitting of the lead in the three-dimensional spaceDistributing; and obtaining the coordinates of the wire points according to the fitting distribution of the wires in the three-dimensional space.
In some embodiments, the method for determining the photo-taking point of each base tower includes: determining a corresponding initially determined photographing point according to a target to be inspected; and filtering the preliminarily determined photographing points according to the tower point cloud data to obtain the photographing point of each base tower.
In some embodiments, the preprocessing comprises removing repeated points in the laser point cloud data to obtain preprocessed laser point cloud data.
In some embodiments, the Beidou precise positioning service is used for performing real-time high-precision positioning through a Beidou intelligent position service system.
A second aspect of the embodiment of the application provides a transmission line unmanned aerial vehicle system of independently patrolling and examining, includes:
the data processing module is used for acquiring laser point cloud data of the power line corridor and preprocessing the laser point cloud data to obtain preprocessed laser point cloud data;
the identification module is used for classifying the preprocessed laser point cloud data through Hough transformation and a Kmeans clustering algorithm to obtain tower point cloud and wire point cloud data;
the first model building module is used for building a three-dimensional model of the power line corridor by utilizing the preprocessed laser point cloud data;
the second model building module is used for obtaining a point cloud tower data model based on the three-dimensional model and the classified laser point cloud data;
the first coordinate determination module is used for performing curve fitting on the wire point cloud data to obtain a curve fitting equation and calculating to obtain a wire point coordinate;
the second coordinate determination module is used for carrying out position identification on the tower point cloud data through a convolutional neural network method to obtain a tower coordinate;
the route planning module is used for determining a photographing point of each base tower in the point cloud tower data model according to the tower point cloud data; setting a camera focal length and a safe flying distance according to the wire point coordinates and the tower coordinates to form an unmanned aerial vehicle autonomous inspection track connected with the photographing point of each base tower;
the application module is used for unmanned aerial vehicle based on Beidou accurate positioning service, and the unmanned aerial vehicle autonomously patrols and examines the orbit and autonomously flies according to the orbit, so that the fine patrolling and examining of the power transmission line are realized.
The method has the advantages that the efficiency of data calculation is improved by preprocessing the laser point cloud data, and further, the preprocessed laser point cloud data is automatically identified by Hough transformation and a Kmeans clustering algorithm, so that automatic classification of towers and wires is realized, and the accuracy of routing inspection is improved; further, position recognition is carried out on the tower through a convolutional neural network method, so that automatic and accurate selection of a photographing point of fine inspection of the tower is realized; further, an autonomous and autonomous inspection track of the unmanned aerial vehicle is determined, so that the operation steps of operators are reduced, the working pressure is reduced, and the efficiency is improved; further, unmanned aerial vehicle is based on the autonomic flight of the accurate location service of big dipper to realize that transmission line's becomes more meticulous and patrol and examine, improve the reliability.
Drawings
Specifically, in order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments are briefly described below, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without any creative effort.
Fig. 1 shows a schematic flow diagram of an autonomous inspection method for an unmanned aerial vehicle of a power transmission line according to an embodiment of the present application;
fig. 2 shows a schematic flow chart of a method for obtaining a wire point coordinate in the unmanned aerial vehicle autonomous inspection method for the power transmission line according to the embodiment of the application.
Detailed Description
Certain exemplary embodiments will now be described to provide an overall understanding of the principles of the structure, function, manufacture, and use of the devices and methods disclosed herein. One or more examples of these embodiments are illustrated in the accompanying drawings. Those of ordinary skill in the art will understand that the devices and methods specifically described herein and illustrated in the accompanying drawings are non-limiting exemplary embodiments and that the scope of the various embodiments of the present application is defined solely by the claims. Features illustrated or described in connection with one exemplary embodiment may be combined with features of other embodiments. Such modifications and variations are intended to be included within the scope of the present application.
Reference throughout this specification to "embodiments," "some embodiments," "one embodiment," or "an embodiment," etc., means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment. Thus, appearances of the phrases "in various embodiments," "in some embodiments," "in at least one other embodiment," or "in an embodiment," or the like, throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments. Thus, the particular features, structures, or characteristics shown or described in connection with one embodiment may be combined, in whole or in part, with the features, structures, or characteristics of one or more other embodiments, without limitation. Such modifications and variations are intended to be included within the scope of the present application.
Flow charts are used herein to illustrate operations performed by systems according to some embodiments of the present application. It should be expressly understood that the operations of the flow diagrams may be performed out of order, with precision. Rather, these operations may be performed in the reverse order or simultaneously. Also, one or more other operations may be added to the flowchart. One or more operations may be removed from the flowchart.
Fig. 1 shows a flow diagram of an autonomous inspection method for an unmanned aerial vehicle of a power transmission line according to an embodiment of the present application.
In step 101, laser point cloud data of a power line corridor is collected and preprocessed to obtain preprocessed laser point cloud data.
In some embodiments, the preprocessing comprises removing repeated points in the laser point cloud data to obtain preprocessed laser point cloud data.
In some embodiments, there are duplicate points in the laser point cloud data (i.e., point cloud data) because it is inevitable that the signals will be received repeatedly during the data acquisition process. If more than two trains exist for the same spatial position, this may result in a reduction in the efficiency of data calculation. Therefore, repeated points in the laser point cloud data are removed, so that the calculation efficiency is improved, and the curve fitting is more accurate.
In step 102, a three-dimensional model of the power line corridor is established by using the preprocessed laser point cloud data.
In some embodiments, the obtaining a three-dimensional model of the power line corridor comprises: acquiring laser point cloud data of the power line corridor by using an unmanned aerial vehicle carrying laser radar system, and settling and analyzing the preprocessed laser point cloud data to obtain characteristic data for establishing a three-dimensional model of the power line corridor; processing the characteristic data to obtain a three-dimensional model of the power line traffic, wherein the laser point cloud data comprises: laser data, image data, and camera data.
In some embodiments, the unmanned aerial vehicle carries a laser radar system to fly above or to one side of the power transmission line, obtains laser data, image data and camera data of the power line corridor, and obtains account data of the power line corridor through post settlement processing and analysis, wherein the account data comprises characteristic data such as a line planing surface diagram, a section diagram, a span, sag and the like, and performs vectorization classification management on the power line corridor to establish a three-dimensional model (i.e., a digital elevation model) of the line corridor.
In step 103, classifying the preprocessed laser point cloud data through Hough transformation and a Kmeans clustering algorithm to obtain tower point cloud and wire point cloud data.
In some embodiments, the method for obtaining tower point cloud and wire point cloud data comprises: calculating the slope of the preprocessed laser point cloud data to obtain the line trend slope of the power transmission line; carrying out edge detection on the preprocessed laser point cloud data through a Canny algorithm to obtain edge points; carrying out Hough transformation and a Kmeans clustering algorithm on the edge points to obtain two cluster types for representing the slope of the straight line; obtaining wire point cloud data by comparing the two cluster categories with the line trend slope; and performing Kmeans clustering on the preprocessed laser point cloud data except the wire point cloud data to obtain tower point cloud data.
In some embodiments, due to the complexity of the corridors among the wire gears of the power transmission line, the fast automatic identification of the wires and the towers is realized by adopting Hough transformation and a Kmeans clustering method. Calculating the slope of the preprocessed laser point cloud data to obtain the line trend slope of the power transmission line; carrying out edge detection on the collected two-dimensional image by using a Canny algorithm; and Hough transform is carried out on the image to obtain a straight line for representing the two-dimensional image. And performing Kmeans clustering according to the slope of the straight line, and clustering to obtain two cluster types, wherein the two cluster types are two types used for representing the slope of the straight line. And comparing the two clusters of line trend slopes with the line trend slopes of the power transmission line, and if the line trend slopes are consistent with the slopes of the two clusters of lines, taking the point cloud data corresponding to the two clusters of lines as wire data. And (4) independently classifying the tower point cloud data in the clustering initial point, and performing once Kmeans clustering on the rest point cloud data to obtain independent and independent tower classification data. And judging the range of the tower area, generating a planar projection range of the tower area according to the line trend, classifying and identifying the point cloud data which is not classified, wherein the point cloud data in the tower area is the tower point cloud data.
In step 104, a point cloud tower data model is obtained based on the three-dimensional model and the classified laser point cloud data.
In some embodiments, the point cloud data is processed into a standard digital elevation model, a point cloud tower data model is established by combining the classified point cloud data to realize three-dimensional digitization of a power line corridor, the lower part of a line is divided into types of common ground objects in line channels such as towers, wires, ground wires, trees, channels, railways, rivers and the like, the ground surface form and the ground surface attachments along the power line are recovered, and the requirements of the power transmission line of each voltage class on the safe running distance of various different ground objects are met. And (3) carrying out automatic measurement and automatic classification of clearance distances of crossing spanning objects such as the channel tree barriers and the like by using a space measurement technology, carrying out automatic analysis of hidden defects and hidden dangers, and automatically generating a report.
In step 105, a curve fitting equation is obtained by performing curve fitting on the wire point cloud data, and a wire point coordinate is obtained by calculation.
In some embodiments, the wire point cloud data is repaired by adopting a space curve fitting mode, and fitting of an H-dimensional space curve is realized by utilizing a step-by-step dimensionality reduction method. According to the distribution characteristic that the leads are linearly distributed on the horizontal plane, performing two-dimensional plane linear fitting on the point cloud data of the leads to realize first dimension reduction; according to the distribution characteristics of a parabola presented by a wire on a plane vertical to a horizontal plane, performing two-dimensional curve fitting on wire point cloud data to realize secondary dimensionality reduction; and the distribution of the three-dimensional overall space of the conducting wire is obtained by completing the fitting of the whole three-dimensional space.
Fig. 2 shows a schematic flow chart of a method for obtaining a wire point coordinate in the unmanned aerial vehicle autonomous inspection method for the power transmission line according to the embodiment of the application.
In step 201, the minimum value along the direction X, Y, Z in the coordinate values corresponding to the wire point cloud data is selected to form a spatial point [ x ]min,ymin,zmin]And as a space coordinate origin, performing coordinate conversion on the wire point cloud data through the space coordinate origin to obtain wire point cloud data subjected to relative coordinate processing.
In some embodiments, the storage efficiency is reduced due to a large number of digits of coordinate values of the collected point cloud data, so that the point cloud data is relocated by selecting a proper coordinate origin. Aiming at the wire point cloud data needing coordinate conversion, selecting the minimum value along the X direction, the minimum value along the Y direction and the minimum value along the Z direction in the corresponding coordinate values of the wire point cloud data to form a space point [ X [ ]min,ymin,zmin]Taking the space point as the origin of space coordinate, and converting the coordinates of the wire point via the origin of space coordinateGenerating corresponding relative coordinates (i.e. relative coordinate point set Ω ═ P (x)i,yi) i 1,2, … n) to obtain relative coordinate processed wire point cloud data.
In step 202, the minimum value along the X direction and the corresponding Y value in the coordinate values corresponding to the wire point cloud data are selected to form a plane point [ X ]min,y(xmin)]And as a plane coordinate origin, performing rotation transformation on the wire point cloud data on an X-Y plane through the plane coordinate origin to obtain the wire point cloud data subjected to rotation transformation.
In some embodiments, the minimum value along the X direction in the coordinate values of the wire point cloud data and the corresponding Y value are selected to form a plane point [ X ]min,y(xmin)]The wire points are rotated on the X-Y plane with the plane point as a center point (i.e., a plane coordinate origin) to obtain data parallel to the X axis (i.e., a point set Φ parallel to the X axis ═ P (X) (X axis)i,yi,zi) i ═ 1,2, … n }), and further obtaining the wire point cloud data after rotation transformation according to the formula (1).
Wherein X' is the X coordinate value parallel to the X axis after rotation.
In step 203, fitting the wire point cloud data processed by the relative coordinates by a least square method to obtain an X-Y plane straight line fitting.
In some embodiments, a set of relative coordinate points is taken as a set of relative coordinate points Ω ═ P (x)i,yi) i is 1,2, … n, calculated as follows:
wherein k is the slope of the straight line fitting of the X-Y plane, and b is the intercept of the straight line fitting of the plane.
In step 204, fitting the rotation transformed wire point cloud data to obtain an X-Z plane straight line fitting.
In some embodiments, a set of points Ω ═ P (X) parallel to the X axis is takeni,yi) 1,2, … n, the following calculations are performed:
in the formula: ca，Cb，CcThe coefficients of the times of the curve equation are respectively from small to large.
In step 205, fitting the three-dimensional space by fitting the X-Y plane straight line and the X-Z plane straight line to obtain the fitting distribution of the wires in the three-dimensional space.
In step 206, the coordinates of the wire points are obtained according to the fitting distribution of the wires in the three-dimensional space.
In some embodiments, a step length is set in the X direction, a y coordinate value on a corresponding fitting straight line is obtained, the obtained y coordinate value is subjected to rotation transformation to obtain a coordinate value parallel to the X axis, the coordinate value parallel to the X axis is substituted into a curve equation to obtain coordinate values of the wire point along zd, and finally, the coordinate values of each wire point (i.e., the coordinate value parallel to the X axis and the coordinate value along zd) are added to a corresponding coordinate origin (i.e., a plane coordinate origin and a space coordinate origin) to obtain coordinates of the fitted space wire point.
In step 106, carrying out position identification on the tower point cloud data through a convolutional neural network method to obtain a tower coordinate.
In some embodiments, each base tower identified by classification is processed, a convolutional neural network depth method is adopted to identify the content in the tower point cloud data, the position (namely, the tower coordinate) of the power component is automatically marked, the marking result can be checked and modified, the defect and the omission are checked, and the power component data which are identified and marked are stored.
In step 107, according to the tower point cloud data, a photographing point of each base tower in the point cloud tower data model is determined.
In some embodiments, the method for determining the photo-taking point of each base tower includes: determining a corresponding initially determined photographing point according to a target to be inspected; and filtering the preliminarily determined photographing points according to the tower point cloud data to obtain the photographing point of each base tower.
In some embodiments, the position where the target to be inspected stays is reversely calculated by combining the camera resolution and the focal length according to the photography principle, and an initial photographing point (i.e., a photographing point set meeting the condition) is obtained by combining the camera pitch angle. According to the point cloud data of the tower, filtering the preliminarily determined photographing points, removing the photographing points which conflict with the point cloud data of the tower or are too close to each other and easily collide with the tower, removing the photographing points which can cause collision with surrounding obstacles due to too small or too large camera pitch angle and have poor photo effect, and leaving a reasonable photographing point set.
In step 108, according to the coordinates of the wire points and the coordinates of the towers, the focal length and the safe flying distance of the camera are set, and an unmanned aerial vehicle autonomous inspection track connected with the photographing point of each base tower is formed.
In some embodiments, according to the coordinates of the wire points and the coordinates of the tower (i.e., the simulated photographing points of the unmanned aerial vehicle), all the photographing point sets are combined, and the principle of shortest path is taken. And selecting a photographing point based on each target to form an optimal air route with the shortest time consumption, and performing three-dimensional simulated flight preview on the air route in the tower after the air route planning is completed to visually check the effect of the operation of the air route used by the airplane.
In step 109, the unmanned aerial vehicle autonomously flies according to the autonomous patrol track of the unmanned aerial vehicle based on the Beidou accurate positioning service, so that the refined patrol of the power transmission line is realized.
In some embodiments, the Beidou precise positioning service is used for performing real-time high-precision positioning through a Beidou intelligent position service system.
In some embodiments, unmanned aerial vehicle independently patrols and examines the orbit according to the unmanned aerial vehicle of planning, adopts big dipper high accuracy positioning service to carry out the independently flight of power service, realizes centimetre level's positioning accuracy, can satisfy the position requirement that unmanned aerial vehicle independently patrols and examines. With the help of big dipper intelligence position service system, carry out real-time high accuracy location to unmanned aerial vehicle, master unmanned aerial vehicle's speed of a ship or plane, course and accurate position, supplementary unmanned aerial vehicle flight reaches the flight mission requirement.
In some embodiments, an unmanned aerial vehicle management control system based on Beidou precise location services is built. Wherein, man-machine management control system includes unmanned aerial vehicle management and control platform. The unmanned aerial vehicle management and control platform can manage unmanned aerial vehicle routes, unmanned aerial vehicle route information and the like manufactured by laser radar data. Meanwhile, unmanned aerial vehicle monitoring and scheduling can be carried out.
The unmanned aerial vehicle management and control platform provides real-time task management, flight data synchronization, equipment and team management functions, enables 'flight principle' of the unmanned aerial vehicle to manage the operation condition of the unmanned aerial vehicle in real time, gets through the linking barriers of an operation field and a rear team, can manage multiple unmanned aerial vehicles and cross-region tasks, and enables operation of the industrial unmanned aerial vehicle to be more efficient. In addition, in daily management, the flight data stored in the cloud can be scheduled, so that the flight is more standard, and lean management is realized. As a flight manager of an administrator, the flight crew task is reasonably scheduled through the management platform, the operation and equipment conditions are known, and the logistics support of the flight can be effectively guaranteed.
In some embodiments, the Beidou CORS system (i.e., based on Beidou satellite positioning) may provide precise location services for unmanned aerial vehicle positioning, device positioning, personnel positioning. The position service system based on the Beidou accurate positioning is a dynamic and real-time positioning frame reference, and meanwhile, the position information and the information of a tower target can be timely and accurately acquired. The system is a product of deep integration of various high and new technologies such as a satellite positioning technology, an internet technology, a mobile communication technology and the like. The system mainly comprises a positioning base station, a data processing module, a data transmission module, a positioning navigation data broadcasting module, a user application module and the like, and a plurality of reference stations can be utilized to form a reference station network to obtain a high-precision positioning result. Each base station is connected with the monitoring center into a whole through a data transmission module, and efficient positioning service is provided for users.
In some embodiments, the drone is used for field flight, collecting relevant data. And uploading the flight path to a control center of the unmanned aerial vehicle management control system, and submitting the routing inspection data to the control center. And finally, the unmanned aerial vehicle can accurately perform fine inspection of the power service on the power transmission line according to the planned path.
The application also provides a transmission line unmanned aerial vehicle system of independently patrolling and examining, include: the data processing module is used for acquiring laser point cloud data of the power line corridor and preprocessing the laser point cloud data to obtain preprocessed laser point cloud data; the identification module is used for classifying the preprocessed laser point cloud data through Hough transformation and a Kmeans clustering algorithm to obtain tower point cloud and wire point cloud data; the first model building module is used for building a three-dimensional model of the power line corridor by utilizing the preprocessed laser point cloud data; the second model building module is used for obtaining a point cloud tower data model based on the three-dimensional model and the classified laser point cloud data; the first coordinate determination module is used for performing curve fitting on the wire point cloud data to obtain a curve fitting equation and calculating to obtain a wire point coordinate; the second coordinate determination module is used for carrying out position identification on the tower point cloud data through a convolutional neural network method to obtain a tower coordinate; the route planning module is used for determining a photographing point of each base tower in the point cloud tower data model according to the tower point cloud data; setting a camera focal length and a safe flying distance according to the wire point coordinates and the tower coordinates to form an unmanned aerial vehicle autonomous inspection track connected with the photographing point of each base tower; the application module is used for unmanned aerial vehicle based on Beidou accurate positioning service, and the unmanned aerial vehicle autonomously patrols and examines the orbit and autonomously flies according to the orbit, so that the fine patrolling and examining of the power transmission line are realized.
The method has the advantages that the efficiency of data calculation is improved by preprocessing the laser point cloud data, and further, the preprocessed laser point cloud data is automatically identified by Hough transformation and a Kmeans clustering algorithm, so that automatic classification of towers and wires is realized, and the accuracy of routing inspection is improved; further, position recognition is carried out on the tower through a convolutional neural network method, so that automatic and accurate selection of a photographing point of fine inspection of the tower is realized; further, an autonomous and autonomous inspection track of the unmanned aerial vehicle is determined, so that the operation steps of operators are reduced, the working pressure is reduced, and the efficiency is improved; further, unmanned aerial vehicle is based on the autonomic flight of the accurate location service of big dipper to realize that transmission line's becomes more meticulous and patrol and examine, improve the reliability.
Additionally, the order in which elements and sequences of the processes described herein are processed, the use of alphanumeric characters, or the use of other designations, is not intended to limit the order of the processes and methods described herein, unless explicitly claimed. While various presently contemplated embodiments of the invention have been discussed in the foregoing disclosure by way of example, it is to be understood that such detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments herein. For example, although the system components described above may be implemented by hardware devices, they may also be implemented by software-only solutions, such as installing the described system on an existing server or mobile device.
Similarly, it should be noted that in the preceding description of embodiments of the application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the embodiments. This method of disclosure, however, is not intended to require more features than are expressly recited in the claims. Indeed, the embodiments may be characterized as having less than all of the features of a single embodiment disclosed above.
The entire contents of each patent, patent application publication, and other material cited in this application, such as articles, books, specifications, publications, documents, and the like, are hereby incorporated by reference into this application. Except where the application is filed in a manner inconsistent or contrary to the present disclosure, and except where the claim is filed in its broadest scope (whether present or later appended to the application) as well. It is noted that the descriptions, definitions and/or use of terms in this application shall control if they are inconsistent or contrary to the statements and/or uses of the present application in the material attached to this application.
Claims (8)
1. The utility model provides a transmission line unmanned aerial vehicle independently patrols and examines method which characterized in that includes:
collecting laser point cloud data of a power line corridor, and preprocessing the laser point cloud data to obtain preprocessed laser point cloud data;
establishing a three-dimensional model of the power line corridor by utilizing the preprocessed laser point cloud data;
classifying the preprocessed laser point cloud data through Hough transformation and a Kmeans clustering algorithm to obtain tower point cloud and wire point cloud data;
obtaining a point cloud tower data model based on the three-dimensional model and the classified laser point cloud data;
performing curve fitting on the wire point cloud data to obtain a curve fitting equation and calculating to obtain a wire point coordinate;
carrying out position identification on the point cloud data of the tower through a convolutional neural network method to obtain a tower coordinate;
determining a photographing point of each base tower in the point cloud tower data model according to the tower point cloud data;
setting a camera focal length and a safe flying distance according to the wire point coordinates and the tower coordinates to form an unmanned aerial vehicle autonomous inspection track connected with the photographing point of each base tower;
unmanned aerial vehicle is based on the accurate location service of big dipper, the foundation unmanned aerial vehicle independently patrols and examines the orbit and independently fly, realizes patrolling and examining that becomes more meticulous of transmission line.
2. The unmanned aerial vehicle autonomous inspection method according to claim 1, wherein the obtaining of the three-dimensional model of the power line corridor comprises:
acquiring laser point cloud data of the power line corridor by using an unmanned aerial vehicle carrying laser radar system, and settling and analyzing the preprocessed laser point cloud data to obtain characteristic data for establishing a three-dimensional model of the power line corridor; processing the characteristic data to obtain a three-dimensional model of the power line traffic, wherein the laser point cloud data comprises: laser data, image data, and camera data.
3. The unmanned aerial vehicle autonomous inspection method according to claim 1, wherein the method for obtaining tower point cloud and wire point cloud data comprises:
calculating the slope of the preprocessed laser point cloud data to obtain the line trend slope of the power transmission line;
carrying out edge detection on the preprocessed laser point cloud data through a Canny algorithm to obtain edge points;
carrying out Hough transformation and a Kmeans clustering algorithm on the edge points to obtain two cluster types for representing the slope of the straight line;
obtaining wire point cloud data by comparing the two cluster categories with the line trend slope;
and performing Kmeans clustering on the preprocessed laser point cloud data except the wire point cloud data to obtain tower point cloud data.
4. The unmanned aerial vehicle autonomous inspection method according to claim 1, wherein the method for obtaining the coordinates of the wire points comprises:
selecting the minimum value along the X, Y, Z direction in the corresponding coordinate values of the wire point cloud data to form a space point [ x ]min,ymin,zmin]As a space coordinate origin, performing coordinate conversion on the wire point cloud data through the space coordinate origin to obtain wire point cloud data subjected to relative coordinate processing;
selecting the minimum value along the X direction and the corresponding Y value in the coordinate values corresponding to the wire point cloud data to form a plane point [ Xmin,y(xmin)]The wire point cloud data is used as a plane coordinate origin, and is subjected to rotary transformation on an X-Y plane through the plane coordinate origin to obtain the wire point cloud data subjected to rotary transformation;
fitting the conducting wire point cloud data processed by the relative coordinates through a least square method to obtain X-Y plane straight line fitting;
fitting the lead point cloud data subjected to rotation transformation to obtain X-Z plane straight line fitting;
fitting the three-dimensional space by fitting the X-Y plane straight line and the X-Z plane straight line to obtain fitting distribution of the conducting wires in the three-dimensional space;
and obtaining the coordinates of the wire points according to the fitting distribution of the wires in the three-dimensional space.
5. The unmanned aerial vehicle autonomous inspection method according to claim 1, wherein the method for determining the photographing point of each base tower comprises the following steps:
determining a corresponding initially determined photographing point according to a target to be inspected; and filtering the preliminarily determined photographing points according to the tower point cloud data to obtain the photographing point of each base tower.
6. The unmanned aerial vehicle autonomous inspection method according to claim 1, wherein the preprocessing comprises removing repeated points in the laser point cloud data to obtain preprocessed laser point cloud data.
7. The unmanned aerial vehicle autonomous inspection method according to claim 1, wherein the Beidou precise positioning service is real-time high-precision positioning through a Beidou intelligent position service system.
8. The utility model provides a transmission line unmanned aerial vehicle system of independently patrolling and examining which characterized in that includes:
the data processing module is used for acquiring laser point cloud data of the power line corridor and preprocessing the laser point cloud data to obtain preprocessed laser point cloud data;
the identification module is used for classifying the preprocessed laser point cloud data through Hough transformation and a Kmeans clustering algorithm to obtain tower point cloud and wire point cloud data;
the first model building module is used for building a three-dimensional model of the power line corridor by utilizing the preprocessed laser point cloud data;
the second model building module is used for obtaining a point cloud tower data model based on the three-dimensional model and the classified laser point cloud data;
the first coordinate determination module is used for performing curve fitting on the wire point cloud data to obtain a curve fitting equation and calculating to obtain a wire point coordinate;
the second coordinate determination module is used for carrying out position identification on the tower point cloud data through a convolutional neural network method to obtain a tower coordinate;
the route planning module is used for determining a photographing point of each base tower in the point cloud tower data model according to the tower point cloud data; setting a camera focal length and a safe flying distance according to the wire point coordinates and the tower coordinates to form an unmanned aerial vehicle autonomous inspection track connected with the photographing point of each base tower;
the application module is used for unmanned aerial vehicle based on Beidou accurate positioning service, and the unmanned aerial vehicle autonomously patrols and examines the orbit and autonomously flies according to the orbit, so that the fine patrolling and examining of the power transmission line are realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111230826.3A CN113963276A (en) | 2021-10-22 | 2021-10-22 | Unmanned aerial vehicle autonomous inspection method and system for power transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111230826.3A CN113963276A (en) | 2021-10-22 | 2021-10-22 | Unmanned aerial vehicle autonomous inspection method and system for power transmission line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113963276A true CN113963276A (en) | 2022-01-21 |
Family
ID=79465987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111230826.3A Pending CN113963276A (en) | 2021-10-22 | 2021-10-22 | Unmanned aerial vehicle autonomous inspection method and system for power transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113963276A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114518768A (en) * | 2022-01-25 | 2022-05-20 | 武汉飞流智能技术有限公司 | Power transmission line inspection method, device, equipment and storage medium |
| CN114639024A (en) * | 2022-03-03 | 2022-06-17 | 江苏方天电力技术有限公司 | Automatic laser point cloud classification method for power transmission line |
| CN114782947A (en) * | 2022-06-22 | 2022-07-22 | 韶关市擎能设计有限公司 | Point cloud matching method, point cloud matching system and storage medium for power transmission and distribution line |
| CN115275870A (en) * | 2022-09-28 | 2022-11-01 | 合肥优晟电力科技有限公司 | Inspection system based on high-altitude line maintenance |
| CN115318760A (en) * | 2022-07-29 | 2022-11-11 | 武汉理工大学 | Unmanned aerial vehicle laser cleaning method and system for power transmission tower |
| CN115661357A (en) * | 2022-11-11 | 2023-01-31 | 太原明远工程监理有限公司 | Spatial model construction method and system based on fused point cloud data |
| CN115685222A (en) * | 2022-11-14 | 2023-02-03 | 国网湖北省电力有限公司超高压公司 | Laser point cloud data-based power line tower automatic detection method |
-
2021
- 2021-10-22 CN CN202111230826.3A patent/CN113963276A/en active Pending
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114518768A (en) * | 2022-01-25 | 2022-05-20 | 武汉飞流智能技术有限公司 | Power transmission line inspection method, device, equipment and storage medium |
| CN114639024A (en) * | 2022-03-03 | 2022-06-17 | 江苏方天电力技术有限公司 | Automatic laser point cloud classification method for power transmission line |
| CN114782947A (en) * | 2022-06-22 | 2022-07-22 | 韶关市擎能设计有限公司 | Point cloud matching method, point cloud matching system and storage medium for power transmission and distribution line |
| CN114782947B (en) * | 2022-06-22 | 2022-10-04 | 韶关市擎能设计有限公司 | Point cloud matching method, point cloud matching system and storage medium for power transmission and distribution line |
| CN115318760A (en) * | 2022-07-29 | 2022-11-11 | 武汉理工大学 | Unmanned aerial vehicle laser cleaning method and system for power transmission tower |
| CN115318760B (en) * | 2022-07-29 | 2024-04-16 | 武汉理工大学 | Unmanned aerial vehicle laser cleaning method and system for power transmission tower |
| CN115275870A (en) * | 2022-09-28 | 2022-11-01 | 合肥优晟电力科技有限公司 | Inspection system based on high-altitude line maintenance |
| CN115275870B (en) * | 2022-09-28 | 2022-12-06 | 合肥优晟电力科技有限公司 | Inspection system based on high-altitude line maintenance |
| CN115661357A (en) * | 2022-11-11 | 2023-01-31 | 太原明远工程监理有限公司 | Spatial model construction method and system based on fused point cloud data |
| CN115685222A (en) * | 2022-11-14 | 2023-02-03 | 国网湖北省电力有限公司超高压公司 | Laser point cloud data-based power line tower automatic detection method |
| CN115685222B (en) * | 2022-11-14 | 2023-06-23 | 国网湖北省电力有限公司超高压公司 | Automatic power line tower detection method based on laser point cloud data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113963276A (en) | Unmanned aerial vehicle autonomous inspection method and system for power transmission line | |
| CN108955702B (en) | Lane-level map creation system based on three-dimensional laser and GPS inertial navigation system | |
| CN112000130B (en) | Multi-machine collaborative high-precision map building positioning system of unmanned aerial vehicle | |
| CN112884931B (en) | Unmanned aerial vehicle inspection method and system for transformer substation | |
| CN108109437B (en) | Unmanned aerial vehicle autonomous route extraction and generation method based on map features | |
| CN113189615B (en) | Method for inspecting power transmission line by using vertical take-off and landing fixed wing unmanned aerial vehicle | |
| CN112230680B (en) | Unmanned aerial vehicle power line inspection control method | |
| CN112033414A (en) | Unmanned aerial vehicle inspection route generation method, device, equipment and medium | |
| CN110727288A (en) | Point cloud-based accurate three-dimensional route planning method for power inspection | |
| CN114114314A (en) | Power transmission line inspection detection system and detection method based on laser point cloud | |
| CN110472477B (en) | Method for monitoring icing by carrying infrared camera by RTK unmanned aerial vehicle | |
| CN113050696A (en) | Method, device and equipment for determining routing inspection route of power transmission line and storage medium | |
| CN113534844B (en) | Method and device for inspecting transmission line of rotorcraft in unknown environment | |
| CN112684806A (en) | Electric power inspection unmanned aerial vehicle system based on dual obstacle avoidance and intelligent identification | |
| CN113033508B (en) | Point cloud-based fine routing inspection waypoint rapid generation method | |
| CN111258331A (en) | Unmanned aerial vehicle power line operation and maintenance system and method | |
| CN114187297A (en) | Power transmission line wind deflection checking method and checking system | |
| CN113674355A (en) | Target identification and positioning method based on camera and laser radar | |
| CN113077561A (en) | Intelligent inspection system for unmanned aerial vehicle | |
| CN111146866B (en) | Power transmission channel control method | |
| CN114089786A (en) | Autonomous inspection system based on unmanned aerial vehicle vision and along mountain highway | |
| CN113758478A (en) | Routing inspection flight planning method and system for long-distance power transmission and transformation line unmanned aerial vehicle | |
| CN115825984A (en) | Power transmission line inspection system and inspection method based on laser point cloud | |
| CN116958472A (en) | Transmission line crossing detection analysis method | |
| CN111244822A (en) | Fixed-wing unmanned aerial vehicle line patrol method, system and device in complex geographic environment |
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 |