CN115326075A - Path planning method for realizing wind field global automatic inspection based on unmanned aerial vehicle - Google Patents

Path planning method for realizing wind field global automatic inspection based on unmanned aerial vehicle Download PDF

Info

Publication number
CN115326075A
CN115326075A CN202211000415.XA CN202211000415A CN115326075A CN 115326075 A CN115326075 A CN 115326075A CN 202211000415 A CN202211000415 A CN 202211000415A CN 115326075 A CN115326075 A CN 115326075A
Authority
CN
China
Prior art keywords
inspection
cluster
aerial vehicle
unmanned aerial
fan
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202211000415.XA
Other languages
Chinese (zh)
Inventor
张世东
陈伟
王建国
尚天坤
黄新
高月锁
于延庆
秦威
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Electric Power New Energy Development Co ltd
Shanghai Minghua Power Technology Co ltd
Original Assignee
Shanghai Electric Power New Energy Development Co ltd
Shanghai Minghua Power Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Shanghai Electric Power New Energy Development Co ltd, Shanghai Minghua Power Technology Co ltd filed Critical Shanghai Electric Power New Energy Development Co ltd
Priority to CN202211000415.XA priority Critical patent/CN115326075A/en
Publication of CN115326075A publication Critical patent/CN115326075A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
    • G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
    • G01C21/20—Instruments for performing navigational calculations
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B64—AIRCRAFT; AVIATION; COSMONAUTICS
    • B64C—AEROPLANES; HELICOPTERS
    • B64C39/00—Aircraft not otherwise provided for
    • B64C39/02—Aircraft not otherwise provided for characterised by special use
    • B64C39/024—Aircraft not otherwise provided for characterised by special use of the remote controlled vehicle type, i.e. RPV
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/004—Artificial life, i.e. computing arrangements simulating life
    • G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E10/00—Energy generation through renewable energy sources
    • Y02E10/70—Wind energy
    • Y02E10/72—Wind turbines with rotation axis in wind direction

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Remote Sensing (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Mathematical Physics (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Biophysics (AREA)
  • Molecular Biology (AREA)
  • Computing Systems (AREA)
  • General Engineering & Computer Science (AREA)
  • Biomedical Technology (AREA)
  • Computational Linguistics (AREA)
  • Software Systems (AREA)
  • Artificial Intelligence (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Automation & Control Theory (AREA)
  • Wind Motors (AREA)

Abstract

The invention relates to a path planning method for realizing automatic inspection of the universe of a wind field based on an unmanned aerial vehicle. Compared with the prior art, the method has the advantages that the number of times of battery replacement for returning to the battery replacement point while traversing all the blades of the wind turbine generator in the cluster is minimized, the global inspection efficiency is improved, the cruising mileage of the unmanned aerial vehicle is utilized to the maximum, and the like.

Description

Path planning method for realizing wind field global automatic inspection based on unmanned aerial vehicle
Technical Field
The invention relates to the field of wind power generation, in particular to a path planning method for realizing global automatic inspection of a wind field based on an unmanned aerial vehicle.
Background
Wind power generation as a renewable energy source develops faster and faster, and the installed capacity is larger and larger. With the use of more and more wind farms, the operation and maintenance of the wind power equipment are also more challenging. At present, most wind fields are mainly distributed in remote areas with complicated geographical and climatic environments, such as suburbs, mountain areas, offshore areas, gobi and the like, the distance between fans is relatively far, and the access is difficult. The blades are used as key parts for capturing wind energy and converting the wind energy into electric energy, and work at high altitude and all weather all the year round, so that thunder, hail, rain, snow, sand, dust, strong wind and the like can possibly damage the blades of the fan, and if the blades of the fan are not inspected, treated and repaired in time, the service life and the power generation benefit of the fan can be influenced, and even serious accidents can be developed. The current patrol inspection of all fan blades in a wind field is mainly completed manually, and the detection has the problems of high strength, high cost, high danger, low efficiency, low reliability and the like due to the detection accuracy, speed, safety and easiness in being limited by the aspects of weather environment, geographical environment and the like.
In recent years, along with the rapid development of the unmanned aerial vehicle technology and the increasingly mature equipment technology, the wind power inspection mode based on the unmanned aerial vehicle technology is greatly developed, the accurate hovering navigation technology of the unmanned aerial vehicle is relied on, a corresponding high-definition camera is carried, and the inspection efficiency of wind power operation and maintenance is greatly improved. However, dozens of fans are contained in most wind fields, the fans are far away in interval and difficult to reach, the research on the existing wind power inspection technology based on the unmanned aerial vehicle mostly aims at a single fan, the unmanned aerial vehicle flies back to change the power and moves to the next target fan after the single fan is detected, on one hand, the mode cannot fully utilize the endurance mileage of an unmanned aerial vehicle battery, on the other hand, all fans in the field are not taken as a whole inspection target to be considered, and the inspection paths of all fans in the field are not fully planned, so that the optimization target is realized, and the inspection efficiency is improved.
Disclosure of Invention
The invention aims to overcome the defects in the prior art and provide a path planning method for realizing the global automatic inspection of a wind field based on an unmanned aerial vehicle.
The purpose of the invention can be realized by the following technical scheme:
according to one aspect of the invention, a path planning method for realizing global automatic inspection of a wind field based on an unmanned aerial vehicle is provided, the method is used for the unmanned aerial vehicle to perform inspection planning on the wind field, and the method comprises the steps of clustering whole-field fans and optimizing the sum of inspection paths among clustering centers and all inspection paths of fan blades in the clusters.
As a preferred technical scheme, the method adopts a double-layer path planning algorithm, and specifically comprises the following steps:
the first layer of path planning realizes the clustering classification of the whole fan and optimizes the routing inspection path among clustering centers;
and planning paths in a second layer, namely taking a cluster center as an unmanned aerial vehicle starting point and a power switching point, and taking the sum of all paths of all fan blades in the cluster from take-off to inspection of the unmanned aerial vehicle as an optimization target, so that routing inspection path optimization in each cluster is realized.
As a preferred technical solution, the first layer path planning includes: firstly, dividing all fans into K clusters by using a K-means clustering algorithm, and calculating the center K of each cluster i Coordinates; then, the particle swarm algorithm or the simulated annealing algorithm is utilized to carry out routing inspection path planning among the clustering centers on the K clustering centers, so that routing inspection paths among the K clustering areas are realizedOptimizing the path, and realizing the full coverage of the wind field inspection with the least power changing points.
As a preferred technical solution, the first layer path planning specifically includes the following steps:
101, acquiring the geographical coordinates, the height of a tower of the wind turbine and the physical information of the length of a blade of all the wind turbines in a wind field;
102, inputting the total number t of the fans and the number k of clusters according to geographic coordinates (two-dimensional coordinates) of all the fans;
step 103, randomly initializing k clustering center coordinates;
104, performing iterative computation by using a K-means clustering algorithm so as to divide all fans in the domain into K clusters according to the coordinate positions, and computing the updated central coordinate K of each cluster i ；
105, enabling all fans in each cluster to reach the cluster center k by adopting an objective function i The sum of the plane distances of (a) is minimum;
106, after iterative computation, the information of each cluster comprises the cluster center coordinate, the fan number in the cluster and the corresponding fan geographic coordinate (two-dimensional coordinate);
and 107, realizing routing inspection path optimization planning among the k clustering centers according to the geographic coordinates (two-dimensional coordinates) of the k clustering centers through a particle swarm or simulated annealing algorithm.
As a preferred technical solution, the second layer path planning includes:
for each cluster and the corresponding cluster center, firstly, the cluster center is used as a starting point of take-off of the unmanned aerial vehicle and a power change point of return, the sum of all paths of all fan blades in the cluster from take-off of the unmanned aerial vehicle to inspection is used as an optimization target, the remaining endurance time of the unmanned aerial vehicle is used as a constraint for judging whether to continue inspection or return power change, and then an inspection route in the cluster of the unmanned aerial vehicle is optimized through a particle swarm algorithm, so that the power change times of the planning route which returns to the power change point while traversing all the wind turbine generator blades in the cluster are minimum.
As a preferred technical solution, the second layer path planning specifically includes the following steps:
step 201, obtaining the output result of the first layer planning, i.e. the kth i Acquiring a cluster center point and height coordinates of corresponding fans in the cluster according to the cluster center coordinates and the serial numbers of all fans in the cluster, wherein the cluster center coordinates are two-dimensional coordinates, and converting the two-dimensional coordinates into three-dimensional coordinates;
step 202, setting a routing inspection unified flow, including ascending, cruising, descending and routing inspection photographing;
step 203, randomly initializing a routing inspection sequence, sequentially calculating routing inspection paths of each fan, and further calculating the sum S of the paths of all fans in the cluster after routing inspection is finished;
step 204, optimizing the sum S of the routing inspection paths of all the undetected fans by adopting a particle swarm algorithm, and starting routing inspection by the unmanned aerial vehicle according to an optimization result;
step 205, starting inspection according to a set flow, including ascending, cruising, descending and inspection photographing;
step 206, finishing inspection to complete a whole blade;
step 207, judging whether the whole fan blade is inspected, if so, turning to step 210; if not, go to step 208;
step 208, judging whether the remaining endurance time of the battery is greater than the time required for the next complete blade to be inspected, if so, going to step 209; if not, returning to the battery replacement point for replacing the battery;
step 209, continuing to inspect the next blade, and returning to step 206;
step 210, judging whether the remaining battery endurance time is greater than the time required for ascending, cruising, descending and polling the first blade of the next fan; if yes, go to step 211; if not, returning to the battery replacement point for replacing the battery;
and step 211, continuing to inspect the next fan until step 205.
As a preferred technical solution, the calculating process of the sum S of the paths of all the fans in step 203 specifically includes:
step 2031, an ascending stage: from the point of departure
Figure BDA0003807130540000031
At a velocity v 1 Ascends to cruise altitude point H 1 The absolute height = the highest value of the wind turbine altitude in the cluster + the height of the wind turbine tower + the length of the wind turbine blade +5 m, the absolute height being called the cruising altitude, i.e. the absolute height
Figure BDA0003807130540000041
Wherein h is h In order to be at the cruising altitude,
Figure BDA0003807130540000042
is the highest value of the wind turbine altitude in the cluster, h t Is the height of the tower of the fan, /) b Is the fan blade length;
step 2032, a cruise stage: at cruising altitude, point H directly above the center of the cluster 1 At a velocity v 2 Fly to a point H right above a target fan at a constant speed 2 The flight length of
Figure BDA0003807130540000043
Wherein
Figure BDA0003807130540000044
Is the longitude and latitude coordinate of the clustering center,
Figure BDA0003807130540000045
the longitude and latitude coordinates of the target fan are obtained;
step 2033, a descending stage: from cruise altitude point H 2 At a velocity v 3 Descending to the center position O of the target fan cabin by the descending height
Figure BDA0003807130540000046
Wherein
Figure BDA0003807130540000047
A target fan altitude coordinate;
step 2034, a patrol photographing stage: taking the central position of a fan cabin as an O starting point, sequentially carrying out a circle of inspection photographing along the front and back surfaces of each blade, and inspecting a stage path l x ＝6×l b ；
Step 2035, starting from the starting point, and completing the inspection of the whole fan, the flight path of the unmanned aerial vehicle is as follows: s = h h +l+h d +l x ；
Step 2036, k i The fan inspection optimization target in each cluster is as follows:
Figure BDA0003807130540000048
wherein n is the number of fans in the cluster.
As a preferred technical solution, the step 208 specifically includes:
after the unmanned aerial vehicle detects each complete blade, automatically calculating and judging whether the endurance time meets the time required for detecting the next complete blade or not according to the residual electric quantity, the physical information of the blade and the environmental parameter variable, and if so, continuing; if not, returning to the battery replacement point to replace the battery.
As a preferred technical solution, the step 210 specifically includes:
after the unmanned aerial vehicle detects each complete fan blade, automatically calculating and judging whether the endurance time meets the time required by the unmanned aerial vehicle to go through the ascending, cruising and descending processes and detect the next complete blade or not according to the residual electric quantity, the geographic information of the fan and the next target fan, the physical information of the blades and the environmental parameter variable, and if yes, continuing; if not, returning to the battery replacement point to replace the battery.
According to the method, in the optimization process, after the routing inspection route is determined, the unmanned aerial vehicle flies according to the routing inspection route, the surface of the blade of the wind turbine generator is photographed through a carried high-definition camera in the flying process, and then the method for detecting the image recognition target is used for diagnosing the surface fault of the blade.
Compared with the prior art, the invention has the following advantages:
1. the automatic routing method for the global inspection of the wind field provided by the invention solves the problems that fans in the wind field are far apart and difficult to inspect and access and the like. And solving the fewest unmanned aerial vehicle battery replacement points through a K-means clustering algorithm, and realizing the full coverage of the global fan patrol.
2. The invention adopts a double-layer path planning algorithm: the first layer of path planning realizes the clustering classification of the whole fan and optimizes the routing inspection path among clustering centers; and the second layer of path planning takes the clustering center as an unmanned aerial vehicle starting point and a power changing point, and takes the sum of all paths of all fan blades in the cluster from take-off to inspection of the unmanned aerial vehicle as a main optimization target, so that inspection path optimization in each cluster is realized.
3. In the second layer path planning process, the sum of all fan paths in the cluster is inspected by the unmanned aerial vehicle as a main optimization target, the remaining endurance time of the unmanned aerial vehicle is used as a main constraint for judging whether to continue inspection or return to power conversion, the inspection route in the cluster of the unmanned aerial vehicle is optimized through a particle swarm algorithm and the like, the power conversion times of the planning route returning to a power conversion point while traversing all wind turbine generator blades in the cluster are minimized, the universe inspection efficiency is improved, and the endurance mileage of the unmanned aerial vehicle can be utilized to the maximum.
Drawings
FIG. 1 is a schematic diagram of cluster center path optimization according to the present invention;
FIG. 2 is a schematic view of the whole process of fan inspection according to the present invention;
FIG. 3 is a flow chart of a first layer path planning of the present invention;
fig. 4 is a flow chart of the second layer path planning of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, shall fall within the scope of protection of the present invention.
The invention provides a path planning method for unmanned aerial vehicle inspection in a wind field universe, which solves the problem of dividing all fans into K clusters by using a K-means clustering algorithm according to coordinate information of all fans in the fieldAnd calculating the center k of each cluster i And (4) coordinates. And then, routing inspection paths among the K clustering centers are planned by utilizing a particle swarm algorithm or a simulated annealing algorithm and the like, so that routing inspection path optimization among the K clustering areas is realized, and the full coverage of wind field routing inspection is realized by using the minimum power change points. Then, for each cluster and the corresponding cluster center, researching that the cluster center is used as a takeoff starting point and a return power change point of the unmanned aerial vehicle, the sum of all paths of all fan blades in the cluster from takeoff to inspection completion of the unmanned aerial vehicle is used as a main optimization target, the remaining endurance time of the unmanned aerial vehicle is used as a main constraint for judging whether to continue inspection or return power change, optimizing an inspection route in the unmanned aerial vehicle cluster through a particle swarm algorithm and the like, and enabling the power change times of a planning route which returns to the power change point while traversing all the wind turbine blades in the cluster to be minimum. The unmanned aerial vehicle flies according to the routing inspection route, the blades of the wind turbine generator are photographed through the carried high-definition camera in the flying process, and then an image recognition target detection method is adopted for diagnosing the surface faults of the blades. According to the method, the time cost and the labor cost in the manual inspection process are saved on the premise of improving the safety, the inspection paths of all fans in the domain are subjected to double-layer planning, the global inspection efficiency is improved, and the endurance mileage of the unmanned aerial vehicle is utilized to the maximum.
The invention discloses a path planning method for realizing global automatic inspection of a wind field based on an unmanned aerial vehicle, which is used for the unmanned aerial vehicle to perform inspection planning on the wind field, and comprises the following steps: the method comprises the steps of clustering and classifying the fans in the whole field, optimizing the sum of routing inspection paths among clustering centers and all routing inspection paths of all fan blades in the clusters, shooting the blades of the wind turbine generator by a high-definition camera carried by an unmanned aerial vehicle in the process, and then adopting an image recognition method for diagnosing the surface faults of the blades.
The method adopts a double-layer path planning algorithm, and comprises the following steps: the first layer of path planning realizes the clustering classification of the whole fan and optimizes the routing inspection path among clustering centers; and the second layer of path planning takes the clustering center as an unmanned aerial vehicle starting point and a power changing point, and takes the sum of all paths of all fan blades in the cluster from take-off to inspection of the unmanned aerial vehicle as an optimization target, so that inspection path optimization in each cluster is realized.
As shown in fig. 1, the first-layer path planning specifically includes: dividing all fans into K clusters by using a K-means clustering algorithm, and calculating the center K of each cluster i Coordinates; and then, routing inspection paths among the K clustering centers are planned by utilizing a particle swarm algorithm or a simulated annealing algorithm, routing inspection path optimization among the K clustering areas is realized, and the wind field routing inspection full coverage is realized by the least electricity changing points.
The second layer path planning specifically includes: for each cluster and the corresponding cluster center, researching that the cluster center is used as a takeoff starting point and a return power change point of the unmanned aerial vehicle, the sum of all paths of all fan blades in the cluster from takeoff to inspection of the unmanned aerial vehicle is used as an optimization target, the remaining endurance time of the unmanned aerial vehicle is used as a constraint for judging whether to continue inspection or return power change, and optimizing an inspection route in the cluster of the unmanned aerial vehicle through a particle swarm algorithm, so that the power change times of the planning route which returns to the power change point while traversing all the wind turbine generator blades in the cluster are minimum.
As shown in fig. 3, the first-layer path planning specifically includes the following steps:
step 1, acquiring the geographical coordinates, the height of a tower of the wind turbine and the physical information of the length of a blade of all the wind turbines in a wind field;
step 2, inputting the total number t of the fans and the number k of clusters according to geographic coordinates (two-dimensional coordinates) of all the fans;
step 3, randomly initializing k clustering center coordinates;
step 4, iterative calculation is carried out by utilizing a K-means clustering algorithm so as to divide all fans in the domain into K clusters according to the coordinate positions, and the updated central coordinate K of each cluster is calculated i ；
Step 5, enabling all fans in each cluster to reach the cluster center k through an objective function i The sum of the plane distances of (a);
step 6, after iterative computation, the information of each cluster comprises the cluster center coordinate, the fan number in the cluster and the corresponding fan geographic coordinate (two-dimensional coordinate);
and 7, realizing routing inspection path optimization planning among the k clustering centers according to the geographic coordinates (two-dimensional coordinates) of the k clustering centers through a particle swarm or simulated annealing algorithm.
As shown in fig. 4, the second-layer path planning specifically includes the following steps:
step 1, obtaining a first-layer planning output result, namely a kth i Acquiring a cluster center coordinate (two-dimensional coordinate) and serial numbers of all fans in the cluster, acquiring a cluster center point and height coordinates of corresponding fans in the cluster, and converting the two-dimensional coordinate into a three-dimensional coordinate;
step 2, stipulating a routing inspection unified flow: ascending, cruising, descending and polling for photographing;
step 3, randomly initializing a routing inspection sequence, sequentially calculating routing inspection paths of each fan, and further calculating the sum S of the paths of all fans in the cluster after routing inspection is finished;
step 4, optimizing the sum S of the routing inspection paths of all the undetected fans by adopting a particle swarm algorithm, and starting routing inspection by the unmanned aerial vehicle according to an optimization result;
and 5, starting inspection according to a specified flow: ascending, cruising, descending and polling photographing;
step 6, finishing the inspection to obtain a whole blade;
step 7, judging whether the whole fan blade is inspected, if so, turning to step 10; if not, go to step 8;
step 8, judging whether the remaining endurance time of the battery is greater than the time required for inspecting the next complete blade, and if so, going to step 9; if not, returning to the battery replacement point for replacing the battery;
step 9, continuously inspecting the next blade, and returning to the step 6;
step 10, judging whether the remaining endurance time of the battery is greater than the time required for ascending, cruising, descending and polling the first blade of the next fan; if yes, go to step 11; if not, returning to the battery replacement point for replacing the battery;
and step 11, continuing to inspect the next fan until step 5.
As shown in fig. 2, the calculation process of the sum S of the paths of all the fans in step 3 specifically includes:
step 1, an ascending stage: from the point of departure
Figure BDA0003807130540000071
(cluster center) at velocity v 1 Ascends to cruise altitude point H 1 The absolute height = the highest value of the wind turbine altitude + the wind turbine tower height + the wind turbine blade length +5 m in the cluster, the absolute height being called the cruising altitude, i.e. the wind turbine blade height
Figure BDA0003807130540000072
Wherein h is h In order to be at the cruising altitude,
Figure BDA0003807130540000073
is the highest value of the wind turbine altitude in the cluster, h t For the height of the tower of the fan, /) b Is the fan blade length;
step 2, a cruise stage: at cruising altitude, point H directly above the center of the cluster 1 At a velocity v 2 Fly to a point H right above a target fan at a constant speed 2 The flight length of
Figure BDA0003807130540000081
Wherein
Figure BDA0003807130540000082
Is the longitude and latitude coordinate of the clustering center,
Figure BDA0003807130540000083
the longitude and latitude coordinates of the target fan are obtained;
step 3, a descending stage: from cruise altitude point H 2 At a velocity v 3 Descending to the center position O of the target fan cabin by the descending height
Figure BDA0003807130540000084
Wherein
Figure BDA0003807130540000085
Is a target windMachine altitude coordinates;
step 4, a polling photographing stage: taking the central position of a fan cabin as an O starting point, sequentially carrying out a circle of inspection photographing along the front and back surfaces of each blade, and inspecting a stage path l x ＝6×l b ；
Step 5, starting from the initial point, and finishing the inspection of the whole fan, wherein the flight path of the unmanned aerial vehicle is as follows: s = h h +l+h d +l x ；
Step 6, kth i The fan inspection optimization target in each cluster is as follows:
Figure BDA0003807130540000086
wherein n is the number of fans in the cluster.
The step 8 specifically comprises: after the unmanned aerial vehicle detects each complete blade, automatically calculating and judging whether the endurance time meets the time required for detecting the next complete blade or not according to the residual electric quantity, the physical information of the blade and the environmental parameter variable, and if so, continuing; if not, returning to the battery replacement point to replace the battery.
The step 10 specifically includes: after the unmanned aerial vehicle detects each complete fan blade, automatically calculating and judging whether the endurance time meets the time required by the unmanned aerial vehicle to go through the ascending, cruising and descending processes and detect the next complete blade or not according to the residual electric quantity, the geographic information of the fan and the next target fan, the physical information of the blades and the environmental parameter variable, and if so, continuing; if not, returning to the battery replacement point to replace the battery.
While the invention has been described with reference to specific embodiments, the invention is not limited thereto, and various equivalent modifications and substitutions can be easily made by those skilled in the art within the technical scope of the invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (10)

1. A path planning method for achieving wind field global automatic inspection based on an unmanned aerial vehicle is characterized in that the method is used for the unmanned aerial vehicle to perform inspection planning on a wind field, and the method comprises the steps of clustering whole-field fans and optimizing the sum of inspection paths among clustering centers and all inspection paths of fan blades in the clusters.
2. The path planning method for realizing the global automatic inspection of the wind field based on the unmanned aerial vehicle according to the claim 1 is characterized in that the method adopts a double-layer path planning algorithm, and specifically comprises the following steps:
the first layer of path planning realizes the clustering classification of the whole fan and optimizes the routing inspection path among clustering centers;
and planning paths in a second layer, namely taking a cluster center as an unmanned aerial vehicle starting point and a power switching point, and taking the sum of all paths of all fan blades in the cluster from take-off to inspection of the unmanned aerial vehicle as an optimization target, so that routing inspection path optimization in each cluster is realized.
3. The method for planning the wind field global automatic inspection based on the unmanned aerial vehicle according to claim 2, wherein the first layer of path planning comprises: firstly, dividing all fans into K clusters by using a K-means clustering algorithm, and calculating the center K of each cluster i Coordinates; and then, performing routing inspection path planning among the clustering centers on the K clustering centers by using a particle swarm algorithm or a simulated annealing algorithm, realizing routing inspection path optimization among the K clustering areas, and realizing full coverage of wind field routing inspection by using the minimum number of power switching points.
4. The method for planning the wind farm global automatic inspection based on the unmanned aerial vehicle according to claim 3, wherein the first-layer path planning specifically comprises the following steps:
101, acquiring physical information of all fans in a wind field, such as geographical coordinates, height of a fan tower, length of a blade and the like;
102, inputting the total number t of the fans and the number k of clusters according to the geographical coordinates of all the fans;
step 103, randomly initializing k clustering center coordinates;
104, performing iterative computation by using a K-means clustering algorithm so as to divide all fans in the domain into K clusters according to the coordinate positions, and computing the updated central coordinate K of each cluster i ；
105, enabling all fans in each cluster to reach the cluster center k by adopting an objective function i The sum of the plane distances of (a) is minimum;
106, after iterative computation, the information of each cluster comprises the cluster center coordinate, the fan number in the cluster and the corresponding fan geographic coordinate;
and 107, optimizing and planning routing inspection paths among the k clustering centers according to the geographic coordinates of the k clustering centers through a particle swarm or simulated annealing algorithm.
5. The method for planning the wind field global automatic inspection based on the unmanned aerial vehicle according to claim 2, wherein the second layer path planning comprises:
for each cluster and the corresponding cluster center, firstly, the cluster center is used as a take-off starting point and a return power change point of the unmanned aerial vehicle, the sum of all paths of all fan blades in the cluster from take-off to inspection of the unmanned aerial vehicle is used as an optimization target, the remaining endurance time of the unmanned aerial vehicle is used as a constraint for judging whether inspection is continued or power change is returned, then, an inspection route in the cluster of the unmanned aerial vehicle is optimized through a particle swarm algorithm, and the power change times of the planning route returning to the power change point while traversing all the fan blades in the cluster are minimized.
6. The method for planning the wind farm global automatic inspection-based path based on the unmanned aerial vehicle according to claim 5, wherein the second-layer path planning specifically comprises the following steps:
step 201, obtaining the first layer planning output result, i.e. the kth i The coordinates of the cluster center and the serial numbers of all fans in the cluster are obtained, and then the height coordinates of the cluster center and the corresponding fans in the cluster are obtained, wherein the coordinate of the cluster center is twoA dimensional coordinate converting the two-dimensional coordinate into a three-dimensional coordinate;
step 202, setting a routing inspection unified flow, including ascending, cruising, descending and routing inspection photographing;
step 203, randomly initializing a routing inspection sequence, sequentially calculating routing inspection paths of each fan, and further calculating the sum S of the paths of all fans in a cluster after routing inspection is finished;
step 204, optimizing the sum S of the routing inspection paths of all the undetected fans by adopting a particle swarm algorithm, and starting routing inspection by the unmanned aerial vehicle according to an optimization result;
step 205, starting inspection according to a set flow, including ascending, cruising, descending and inspection photographing;
step 206, finishing inspection to complete a whole blade;
step 207, judging whether the whole fan blade is inspected, if so, turning to step 210; if not, go to step 208;
step 208, judging whether the remaining endurance time of the battery is greater than the time required for the next complete blade to be inspected, if so, going to step 209; if not, returning to the battery replacement point for replacing the battery;
step 209, continuing to inspect the next blade, and returning to step 206;
step 210, judging whether the remaining battery endurance time is longer than the time required by ascending, cruising, descending and polling the first blade of the next fan; if yes, go to step 211; if not, returning to the power swapping point for swapping power;
and step 211, continuing to inspect the next fan until step 205.
7. The method for planning the wind farm global automatic inspection based on the unmanned aerial vehicle according to claim 6, wherein the step 203 of calculating the sum S of the paths of all the fans specifically comprises:
step 2031, an ascending stage: from the point of departure
Figure FDA0003807130530000031
At a velocity v 1 Ascended to cruise altitude point H 1 The absolute height = theThe wind turbine altitude maximum + wind turbine tower height + wind turbine blade length +5 m in the cluster, the absolute height is called the cruise altitude, i.e.
Figure FDA0003807130530000032
Wherein h is h In order to be at the cruising altitude,
Figure FDA0003807130530000033
is the highest value of the wind turbine altitude in the cluster, h t Is the height of the tower of the fan, /) b Is the fan blade length;
step 2032, a cruise stage: at cruising altitude, point H directly above the center of the cluster 1 At a velocity v 2 Fly to a point H right above a target fan at a constant speed 2 The flight length of
Figure FDA0003807130530000034
Wherein
Figure FDA0003807130530000035
Is the longitude and latitude coordinate of the clustering center,
Figure FDA0003807130530000036
the longitude and latitude coordinates of the target fan are obtained;
step 2033, a descending stage: from cruise altitude point H 2 At a velocity v 3 Descending to the center position O of the target fan cabin by the descending height
Figure FDA0003807130530000037
Wherein
Figure FDA0003807130530000038
A target fan altitude coordinate;
step 2034, a patrol photographing stage: taking the central position of a fan cabin as an O starting point, sequentially carrying out a circle of inspection photographing along the front and back surfaces of each blade, and inspecting a stage path l x ＝6×l b ；
Step 2035, fromThe starting point begins, patrols and examines to accomplishing a whole fan, and unmanned aerial vehicle flight path does: s = h h +l+h d +l x ；
Step 2036, k i The fan inspection optimization target in each cluster is as follows:
Figure FDA0003807130530000039
wherein n is the number of the fans in the cluster.
8. The method for planning the wind farm global automatic inspection tour path based on the unmanned aerial vehicle as claimed in claim 6, wherein the step 208 specifically comprises:
after the unmanned aerial vehicle detects each complete blade, automatically calculating and judging whether the endurance time meets the time required for detecting the next complete blade or not according to the residual electric quantity, the physical information of the blade and the environmental parameter variable, and if yes, continuing; if not, returning to the battery replacement point to replace the battery.
9. The method for planning the wind farm global automatic inspection tour path based on the unmanned aerial vehicle as claimed in claim 6, wherein the step 210 specifically comprises:
after the unmanned aerial vehicle detects each complete fan blade, automatically calculating and judging whether the endurance time meets the time required by the unmanned aerial vehicle to go through the ascending, cruising and descending processes and detect the next complete blade or not according to the residual electric quantity, the geographic information of the fan and the next target fan, the physical information of the blades and the environmental parameter variable, and if so, continuing; if not, returning to the battery replacement point to replace the battery.
10. The path planning method for achieving wind farm global automatic inspection based on the unmanned aerial vehicle is characterized in that after the inspection route is determined, the unmanned aerial vehicle flies according to the inspection route, the surface of the blade of the wind turbine generator is photographed through a carried high-definition camera in the flying process, and then the method of detecting the image recognition target is used for diagnosing the surface fault of the blade.
CN202211000415.XA 2022-08-19 2022-08-19 Path planning method for realizing wind field global automatic inspection based on unmanned aerial vehicle Pending CN115326075A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211000415.XA CN115326075A (en) 2022-08-19 2022-08-19 Path planning method for realizing wind field global automatic inspection based on unmanned aerial vehicle

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211000415.XA CN115326075A (en) 2022-08-19 2022-08-19 Path planning method for realizing wind field global automatic inspection based on unmanned aerial vehicle

Publications (1)

Publication Number Publication Date
CN115326075A true CN115326075A (en) 2022-11-11

Family

ID=83926837

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211000415.XA Pending CN115326075A (en) 2022-08-19 2022-08-19 Path planning method for realizing wind field global automatic inspection based on unmanned aerial vehicle

Country Status (1)

Country Link
CN (1) CN115326075A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116307336A (en) * 2023-05-22 2023-06-23 北京阿帕科蓝科技有限公司 Method and device for planning path of electricity exchanging and computer equipment
CN117268402A (en) * 2023-11-17 2023-12-22 黑龙江哲讯信息技术有限公司 Unmanned aerial vehicle reconnaissance path planning method based on 5G communication technology

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116307336A (en) * 2023-05-22 2023-06-23 北京阿帕科蓝科技有限公司 Method and device for planning path of electricity exchanging and computer equipment
CN116307336B (en) * 2023-05-22 2023-10-24 北京阿帕科蓝科技有限公司 Method and device for planning path of electricity exchanging and computer equipment
CN117268402A (en) * 2023-11-17 2023-12-22 黑龙江哲讯信息技术有限公司 Unmanned aerial vehicle reconnaissance path planning method based on 5G communication technology
CN117268402B (en) * 2023-11-17 2024-01-30 黑龙江哲讯信息技术有限公司 Unmanned aerial vehicle reconnaissance path planning method based on 5G communication technology

Similar Documents

Publication Publication Date Title
He et al. Research of multi-rotor UAVs detailed autonomous inspection technology of transmission lines based on route planning
CN110282143B (en) Inspection method for offshore wind farm unmanned aerial vehicle
CN115326075A (en) Path planning method for realizing wind field global automatic inspection based on unmanned aerial vehicle
CN106762451B (en) Fan blade damage detection method, device and system based on unmanned aerial vehicle
CN108390645A (en) Photovoltaic panel Fault Locating Method based on unmanned plane and thermal imaging
CN110554704A (en) unmanned aerial vehicle-based fan blade autonomous inspection method
CN112734970B (en) Automatic inspection system and method for unmanned aerial vehicle in wind farm based on LoRaWAN positioning technology
CN112904877A (en) Automatic fan blade inspection system and method based on unmanned aerial vehicle
Cui et al. Path planning algorithms for power transmission line inspection using unmanned aerial vehicles
CN111998832A (en) Laser point cloud-based inspection method for accurately positioning target object by using unmanned aerial vehicle
CN110673628A (en) Inspection method for oil-gas pipeline of composite wing unmanned aerial vehicle
CN114898232A (en) Photovoltaic power station unmanned aerial vehicle inspection method and system based on photovoltaic string data analysis
CN115275870B (en) Inspection system based on high-altitude line maintenance
CN113342041A (en) Method and system for realizing automatic inspection of fan blade power generation equipment by unmanned aerial vehicle
Guo et al. Detecting and positioning of wind turbine blade tips for uav-based automatic inspection
CN115442532A (en) Method, system, equipment and storage medium for inspecting fan without stopping
CN115720080A (en) Inspection control system and inspection control method for power generation area of photovoltaic power station
CN114610070A (en) Unmanned aerial vehicle-cooperated wind power plant intelligent inspection method
CN113744427A (en) Navigation mark inspection system and inspection method based on unmanned aerial vehicle remote sensing
Sherman et al. Solar uav for the inspection and monitoring of photovoltaic (Pv) systems in solar power plants
US20230267364A1 (en) Processing images of wind farms and plant farms captured by a drone
CN115065169A (en) Electric power monitoring system based on 5G and Internet of things technology
Che et al. Inspection of Electric Transmission Line Fault Based on UAV Lidar.
CN115937084A (en) Method for determining attitude of impeller of wind driven generator
CN114021906A (en) Unattended wind power generation operation and maintenance management method and system

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