CN118444693B - A method and system for generating wind turbine inspection routes based on drones - Google Patents
A method and system for generating wind turbine inspection routes based on drones Download PDFInfo
- Publication number
- CN118444693B CN118444693B CN202410518436.3A CN202410518436A CN118444693B CN 118444693 B CN118444693 B CN 118444693B CN 202410518436 A CN202410518436 A CN 202410518436A CN 118444693 B CN118444693 B CN 118444693B
- Authority
- CN
- China
- Prior art keywords
- fan
- hub
- blade
- latitude
- longitude
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000007689 inspection Methods 0.000 title claims abstract description 47
- 238000005452 bending Methods 0.000 claims abstract description 43
- 238000013145 classification model Methods 0.000 claims abstract description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 22
- 238000006243 chemical reaction Methods 0.000 claims description 16
- 230000008569 process Effects 0.000 claims description 15
- 206010061274 Malocclusion Diseases 0.000 claims description 9
- 238000012937 correction Methods 0.000 claims description 9
- 239000013598 vector Substances 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 claims description 5
- 238000007635 classification algorithm Methods 0.000 claims description 4
- 230000001174 ascending effect Effects 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 3
- 238000013211 curve analysis Methods 0.000 claims description 3
- 238000011065 in-situ storage Methods 0.000 claims description 3
- 238000012804 iterative process Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000005259 measurement Methods 0.000 abstract description 4
- 238000003384 imaging method Methods 0.000 description 6
- 238000003860 storage Methods 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000006978 adaptation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- HOWHQWFXSLOJEF-MGZLOUMQSA-N systemin Chemical compound NCCCC[C@H](N)C(=O)N[C@@H](CCSC)C(=O)N[C@@H](CCC(N)=O)C(=O)N[C@@H]([C@@H](C)O)C(=O)N[C@@H](CC(O)=O)C(=O)OC(=O)[C@@H]1CCCN1C(=O)[C@H]1N(C(=O)[C@H](CC(O)=O)NC(=O)[C@H](CCCN=C(N)N)NC(=O)[C@H](CCCCN)NC(=O)[C@H](CO)NC(=O)[C@H]2N(CCC2)C(=O)[C@H]2N(CCC2)C(=O)[C@H](CCCCN)NC(=O)[C@H](CO)NC(=O)[C@H](CCC(N)=O)NC(=O)[C@@H](NC(=O)[C@H](C)N)C(C)C)CCC1 HOWHQWFXSLOJEF-MGZLOUMQSA-N 0.000 description 1
- 108010050014 systemin Proteins 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/40—Control within particular dimensions
- G05D1/46—Control of position or course in three dimensions
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/20—Control system inputs
- G05D1/24—Arrangements for determining position or orientation
- G05D1/247—Arrangements for determining position or orientation using signals provided by artificial sources external to the vehicle, e.g. navigation beacons
- G05D1/249—Arrangements for determining position or orientation using signals provided by artificial sources external to the vehicle, e.g. navigation beacons from positioning sensors located off-board the vehicle, e.g. from cameras
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Wind Motors (AREA)
- Structures Of Non-Positive Displacement Pumps (AREA)
Abstract
The application discloses a fan inspection route generation method based on an unmanned aerial vehicle, which adopts a completely autonomous flight mode, and the longitude and latitude of the fan and the elevation of the central point of the hub are automatically re-measured when the inspection is carried out every time, so that errors caused by the longitude and latitude are avoided. The method comprises the steps of adding a classification model when identifying the yaw angle and the phase angle of the blade of the fan, improving the identification rate in a redundant mode, correcting the position of the fan at last after the yaw angle and the phase angle of the blade of the fan reach the front of the hub, ensuring that the position of the fan has no deviation, solving the problem that deviation occurs between measurement and longitude and latitude in the prior art, introducing a curve fitting equation of the pre-bending of the blade, solving the problem that the blade can exceed a camera picture when the front edge and the rear edge are inspected.
Description
Technical Field
The invention relates to the field of new energy, in particular to a fan routing inspection route generation method and system based on an unmanned aerial vehicle, which can be used for automatically generating a route in the fan routing inspection of the unmanned aerial vehicle.
Background
At present, most wind energy capturing devices are wind turbine generators composed of a tower, a fan case and fan blades, wherein the fan blades need to continuously rotate under the action of wind force to complete energy conversion, and the safety and reliability of the wind turbine generators are key points for ensuring the normal operation of the wind turbine generators. The fan blade is regularly inspected regularly, so that fault detection and fault information confirmation can be timely carried out, and maintenance and repair of the fan blade can be carried out in advance according to the fault grade. The fan blade inspection is a key step for ensuring long-term normal operation of the wind turbine generator.
For inspection of fan blades, operation and maintenance personnel check whether the surface of the fan blade is abnormal or not through a handheld telescope. The manual inspection has higher working strength and lower efficiency. Manual inspection based on visual inspection and empirical judgment cannot guarantee the accuracy of fault detection, and is accompanied by high inspection cost. In recent years, part of wind farms are equipped with unmanned aerial vehicles for blade inspection, but the unmanned aerial vehicle inspection operation is complex, and some airlines are difficult to operate manually. In this way, an automatic route generation algorithm is introduced in a recent part of fan inspection schemes, so that inspection efficiency is greatly improved. However, the current automatic route generation algorithm needs to manually input fan parameters (such as fan longitude and latitude, tower height and the like), and certain errors exist in calculating the yaw angle of the fan, so that the accuracy of subsequent route generation is greatly affected. Unmanned aerial vehicle-based fan routing inspection route generation method and system CN115480589A, and the longitude and latitude and tower of the fan are required to be additionally provided. In actual flight, because a part of areas have no network RTK signal, certain deviation can appear in each starting of the unmanned aerial vehicle, and re-measurement is needed. Nor does the patent provide a corresponding solution. In addition, the yaw angle and the phase angle of the blades of the fan are influenced by a segmentation image algorithm, and no other redundant method exists. Finally, the influence of the blade pre-bending is not taken into account in the course design.
Disclosure of Invention
The technical problem to be solved by the application is to ensure the reliability of equipment, provide a fan inspection route generating method based on unmanned aerial vehicle, through a completely autonomous flight mode, and the longitude and latitude of the fan and the elevation of the central point of the hub are automatically re-measured when the inspection is carried out every time, so that errors caused by the longitude and latitude are avoided. And adding a classification model when identifying the yaw angle and the phase angle of the blades of the fan, and improving the identification rate in a redundant mode. After the wind reaches the front of the hub, the wind is finally corrected, the position of the wind is guaranteed to have no deviation, the problem that deviation occurs between measurement and longitude and latitude in the prior art is solved, meanwhile, a curve fitting equation of the blade pre-bending is introduced, the problem that the blade exceeds a camera picture when the front edge and the rear edge are inspected is solved, the key parameters, the yaw angle and the blade phase angle of the wind are automatically acquired by the unmanned aerial vehicle, the blade pre-bending is detected by the curve fitting algorithm, and an accurate unmanned aerial vehicle blade inspection route is finally generated.
The technical scheme of the application is as follows:
The utility model provides a fan inspection route generation method based on unmanned aerial vehicle, the fan includes the wind tower and sets up the impeller on wind tower top, the impeller includes wheel hub and three blade along wheel hub circumference evenly distributed, unmanned aerial vehicle carries on cloud platform and the GPS positioning system that is provided with the camera, its characterized in that includes following step:
S1, defining longitude and latitude waypoints of a fan, wherein the longitude and latitude waypoints of the fan comprise a first fan longitude and latitude waypoint and a second fan longitude and latitude waypoint, the longitude and latitude of the first fan longitude and latitude waypoint is the longitude and latitude (lng 1,lat1) of the unmanned aerial vehicle, the altitude of the first fan longitude and latitude waypoint is higher than that of surrounding obstacles, a holder is adjusted to be horizontally shot, the direction of the head of the unmanned aerial vehicle is adjusted in a rotating manner in situ, so that a fan tower is completely appeared in a picture acquired by a camera, the position of the unmanned aerial vehicle is A, the longitude and latitude is lkng 1,lat1, the altitude of the second fan longitude and latitude waypoint is identical to that of the first fan longitude and latitude waypoint, the longitude and latitude of the second fan longitude and latitude waypoint are corresponding to the longitude and latitude when the picture shot by the camera is opposite to the center of the tower, the position of the unmanned aerial vehicle is F, the longitude and latitude (lng 2,lat2), and latitude (lng 3,lat3) of the fan tower is calculated, and the position of the fan tower is D;
S2, generating a route from the unmanned aerial vehicle to the upper side of the fan according to the acquired longitude and latitude (lng 3,lat3) of the fan tower, wherein the route from the unmanned aerial vehicle to the upper side of the fan comprises four waypoints, the first waypoint is a position F where the unmanned aerial vehicle is located, the longitude and latitude of the second waypoint are identical to the longitude and latitude of the first waypoint (lng 1,lat1), the height is the height h 1 of the center of the fan hub, the longitude and latitude of the third waypoint are (lng 1,lat1), the height h 2 is larger than the sum of the height h 1 of the center of the fan hub and the length l of the fan blade, the longitude and latitude of the fourth waypoint are the longitude and latitude (lng 3,lat3) of the fan tower, the height of the fourth waypoint is identical to the height of the third waypoint and h 2, and after the fourth waypoint is reached, the cradle head is adjusted to be shot vertically downwards, and a top view of the fan is acquired;
s3, calculating a yaw angle alpha of the fan based on a top view of the fan;
S4, generating an initial route reaching the front of the hub according to the calculated yaw angle alpha of the fan, wherein the initial route reaching the front of the hub comprises two waypoints, the height of a first waypoint of the initial route reaching the front of the hub is h 2, the longitude and latitude of a second waypoint of the initial route reaching the front of the hub are the same as those of the first waypoint of the initial route reaching the front of the hub, the height of the second waypoint of the initial route reaching the front of the hub is h 1, the position of the second waypoint of the initial route reaching the front of the hub is Q, the position of the second waypoint reaching the Q cradle head is adjusted to be horizontally shot, and the direction of the machine head is adjusted to be the yaw angle of the fan to 180 degrees;
S5, acquiring a front view of the hub of the fan from a camera in the cradle head, and generating a route right in front of the calibrated hub based on a hub identification algorithm. The calibrated front route of the hub comprises two waypoints, a first waypoint of the calibrated front route of the hub is a position Q, the direction of a machine head and a shooting gesture are unchanged, a second waypoint of the calibrated front route of the hub is a picture center point of the hub, which is shot by a camera, and a front view of the fan hub is obtained based on the second waypoint of the calibrated front route of the hub;
S6, calculating a fan blade phase angle beta and a blade pre-bending based on the front hub view obtained in the step S5;
S7, generating a routing inspection route by combining longitude and latitude (lng 3,lat3) of a fan tower, a fan yaw angle alpha, a fan blade phase angle beta, tower height, blade pre-bending and fan blade length l.
Preferably, the calculating the longitude and latitude (lng 3,lat3) of the fan tower in S1 specifically includes the following steps:
101 At the longitude and latitude waypoint of the first fan, based on a tower identification algorithm, the fan tower is completely appeared in the picture acquired by the camera, a fan tower image I 1 of the longitude and latitude waypoint of the first fan is acquired, and at the moment, the position of the center point of the tower in the fan tower image I 1 is (mu 1,v1);
102 Based on the tower image I 1 of the fan, calculating the deflection angle c of the fan relative to the direction of the unmanned aerial vehicle head by combining with the internal parameters of the camera;
103 The flying direction is perpendicular to the machine head, the shooting gesture and the machine head direction are kept unchanged, the corresponding longitude and latitude navigation point of the second fan when the shooting picture of the camera is right opposite to the center of the tower barrel is obtained, the center image I 2 of the tower barrel is obtained, and the position of the center point of the tower barrel in the center image I 2 of the tower barrel is (mu 2,v2);
104 Based on the longitude and latitude (lng 1,lat1) of the position A of the unmanned aerial vehicle, the deflection angle c of the fan relative to the head direction of the unmanned aerial vehicle and the longitude and latitude (lng 2,lat2) of the position F of the unmanned aerial vehicle, the longitude and latitude (lng 3,lat3) corresponding to the position D of the fan tower is calculated.
The step S2 specifically comprises the following steps:
201 The unmanned aerial vehicle continuously flies upwards, no obstacle exists above the unmanned aerial vehicle, in the ascending process, the image transmission picture and the unmanned aerial vehicle height are used as parameters to carry out the recognition of the engine room and the hub, 202) when the engine room is recognized and detected to be a target in the picture, the unmanned aerial vehicle height is corrected, the center point of the engine room is positioned at the center of the picture, and the corresponding unmanned aerial vehicle height is the corrected height h' 1 of the center of the fan hub.
S3 specifically comprises the following steps:
301 Inputting the fan top view into a fan yaw angle class model, obtaining the output class of the fan yaw angle and the corresponding confidence coefficient conf α1, converting the output class into [ -180 degrees, 180 degrees ] intervals according to the class, and obtaining the angle alpha 1 of the yaw angle estimated by classification, wherein
The method comprises the steps of i, inputting a current top view based on a fan yaw angle classification model, obtaining an output category, calculating an angle interval corresponding to the category, and calculating the angle interval after outputting the category.
302 Dividing the fan top view into a binary image only comprising a fan area by utilizing a dividing algorithm, and clustering all straight lines according to angles;
303 Straight line detection is carried out on the top view of the fan, a straight line with an intersection point with the edge of a picture is eliminated, two straight lines respectively representing the engine room and the fan blade are obtained, a hub area is taken as an origin of coordinates, the positive directions of an x axis and a y axis are taken as the lower left side, and the angle of an included angle between the x axis and the straight line where the engine room is positioned is calculated, so that the yaw angle alpha 2 of the fan on the top view of the fan is obtained;
304 Determining the position of the hub according to the intersection point of the two straight lines, and calculating the yaw angle alpha' of the engine room at the moment based on the hub serving as an origin point. Based on α 1 and α 2, a comprehensive confidence level for the nacelle yaw angle is calculated as conf α＝0.5*(confα1+confα2). Let x= |α 1-α2 | where The overall confidence in the nacelle yaw angle is highest when the values of α 1 and α 2 are equal, and lowest when α 1 and α 2 differ by 90 °. If the integrated confidence coefficient is greater than the set threshold value of the yaw angle of the nacelle, the integrated confidence coefficient (probability) of the yaw angle of the nacelle, which is given by the classification algorithm, is represented based on the yaw angle α '=α 1 of the nacelle when the hub is the origin, and if the integrated confidence coefficient is less than the threshold value of the yaw angle of the nacelle, the integrated confidence coefficient (probability) of the yaw angle of the nacelle, which is given by the classification algorithm, is represented based on the yaw angle α' =α 2;confα1 of the nacelle when the hub is the origin;
305 According to the yaw angle alpha' of the engine room based on the wheel hub as the origin, adding the yaw angle rho of the cradle head to obtain a yaw angle cradle head correction output value alpha out of the fan, and converting the yaw angle output value of the fan into a fixed interval to obtain the yaw angle alpha of the fan.
Step 305) specifically includes the steps of limiting and correcting the fan yaw angle holder correction output value alpha out to obtain a fan yaw angle when the north is 0 ° and the holder yaw angle is ρ, and the fan yaw angle holder correction output value alpha out =90° +α' +ρ The fan yaw angle α is limited to (-180, 180).
The step S5 of calibrating the center position of the hub specifically comprises the following steps:
501 The unmanned aerial vehicle flies to the front of the hub, and other obstacles are not generated in the flying process;
502 The camera shoots a picture and carries out hub identification to obtain a hub image I 3;
503 Acquiring the center point (x 1,y1) of the hub identification frame, and comparing the center point with the center position (x 2,y2) of the hub image I 3 to obtain the flight direction of the control unmanned aerial vehicle Distance fromAcquiring a front view I 4 of a fan hub;
504 Controlling the unmanned aerial vehicle to fly based on the flying direction and the distance in the step 503), and circularly executing 502), wherein the step 503) is that the distance between the position of the picture center point and the center point of the hub identification frame is smaller than a set threshold value, and the position of the unmanned aerial vehicle is the navigation point right in front of the center of the calibrated hub.
Step S6 of calculating the phase angle of the fan blade specifically comprises the following steps:
601a) After the front view of the fan hub is obtained, the front view of the fan hub is input into a blade phase angle classification model, the output category of the fan blade phase angle and the corresponding confidence level conf β1 are obtained, the front view of the fan hub is converted into an angle interval according to the category, and the obtained classified estimated blade phase angle beta 1 =i is the output category of the fan blade phase angle, i is a positive integer in the [0,U-1] interval;
602a) Inputting a current front view based on a blade phase angle classification model, acquiring an output class, and calculating a corresponding angle interval;
603a) Searching blades from the front view four sides of the fan hub to the center in sequence to obtain end points of 3 or 4 fan bodies extending to the image edges;
604a) Calculating an angle by taking the hub as an origin of coordinates, connecting the hub with an endpoint of an image edge, setting the position of the hub in a front view I 4 of the fan hub to be (mu 3,v3), setting the endpoint to be (mu 4,v4), and setting the angle to be
605A) Excluding the straight line of the tower barrel part, screening out an included angle beta 2 between the first blade in the anticlockwise direction and the tower barrel, wherein the confidence of the included angle beta 2 is conf β2;
606a) The phase angle beta of the fan blade is calculated,
Based on β 1 and β 2, a comprehensive confidence conf β＝0.5*(confβ1+confβ2 of the fan blade phase angle is calculated. Let x= |β 1-β2 |whereThe integrated confidence is highest when β 1 and β 2 are the same, and lowest when β 1 and β 2 are 60 ° apart. If the integrated confidence is greater than the threshold value of the set fan blade phase angle, the algorithm output result is beta=beta 1, and if the integrated confidence is less than the threshold value of the fan blade phase angle, the algorithm output result is beta=beta 2.
The step S6 of calculating the blade pre-bending specifically comprises the following steps:
601b) Blade segmentation is carried out on a front view of a fan hub, the hub center is taken as an origin, the phase angle direction is taken as an x-axis positive direction, the x-axis anticlockwise 90 degrees is taken as a y-axis positive direction, and a two-dimensional rectangular coordinate system is established
602B) Taking points along the positive direction of the x axis according to the set interval, calculating y values corresponding to the blade areas, and generating a plurality of data points;
according to the phase angle beta of the fan blade, taking the hub center as an origin, taking the phase angle direction as the positive x-axis direction, taking the anticlockwise 90 degrees of the x-axis direction as the positive y-axis direction, and establishing a two-dimensional rectangular coordinate system
603B) Fitting all data points by curves, and obtaining a curve analysis function from a two-dimensional rectangular coordinate systemConversion to hub rectangular coordinatesTwo-dimensional rectangular coordinate systemIs a coordinate system rotated according to the phase angle;
Because the pre-bending of the three blades is uniform, only one blade pre-bending resolution is required. In a two-dimensional rectangular coordinate system And taking points along the positive direction of the x-axis according to the set interval, calculating the average value of the corresponding y of the blade area, and generating a plurality of data points.
604B) Four parameter equation is selectedAnd (3) carrying out curve fitting, wherein d represents a baseline of the blade pre-bending, a represents a maximum value of the blade pre-bending, c represents a position parameter of an inflection point, b represents a slope parameter of the curve, carrying data points in, setting an error expected threshold epsilon, counting error mean epsilon 1 between the true values and the estimated values of all points in an iterative process, and adjusting parameters according to the error mean epsilon 1 until the error mean is controlled within the expected threshold epsilon 1 < epsilon, wherein a corresponding analytical formula is an equation of curve fitting, and the blade pre-bending is represented by the curve equation because the blade pre-bending causes the blade to bend.
The step S7 specifically includes the following steps:
701 Based on fan yaw angle α, fan blade phase angle β, inherent parameters impeller elevation angle θ and blade cone angle of the fan Calculating the routing inspection route in the rectangular coordinates of the hubThe angle of the first blade becomes β' =270 ° - β. According to the elevation angle of the impeller, the corresponding rotation matrix under the coordinate system is as follows: Obtaining a first blade direction vector The angle between the other two blades and the first blade is known, the blade pre-bending design is the same, the direction vectors of the second blade and the third blade are obtained by replacing the angle of the blades, and the coordinate mapping expression before and after conversion is brought into the curve equation of the blade pre-bending to obtain the rectangular coordinates of each blade on the hubThe lower curve fitting analytic expression;
702 Known blade length/in coordinate system In the process of inspecting the front edge, a blade pre-bending curve equation obtained through coordinate system conversion The x variable is equally divided into An Zhao n values in the interval of [0, l x v β ] to generate n coordinate systemsIs the waypoint of (2) Wherein epsilon g is the distance between the unmanned aerial vehicle and the blade when the unmanned aerial vehicle patrols and examines the front edge of the blade, and the unmanned aerial vehicle obtains a blade patrol route after passing through the waypoints in sequence;
when the trailing edge is inspected, the waypoint is Epsilon h is the distance from the blade when the trailing edge of the blade is inspected, and for the leeward side, the waypoint is The windward waypoint is Epsilon m is the distance from the blade when the blade is inspected on the windward side.
703 Generating a route from the initial position of the unmanned aerial vehicle by combining the longitude and latitude (lng 3,lat3) of a wind turbine tower, knowing the yaw angle alpha of the wind turbine and the corrected hub height h' 1, and knowing that the pre-bending of the blades is based on a hub rectangular coordinate systemIs characterized by that the rectangular coordinate system of the wheel hubConversion to a tower rectangular coordinate system based on the bottom of a fan towerThe corresponding conversion matrix is: Rectangular coordinate system of tower And converting the coordinate system, and adding the influence of the hub center point height and the yaw angle.
704 In the inspection fan blade, the leading edge, trailing edge, windward side (pressure side) and leeward side (suction side) of the inspection blade.
A computing system comprising one or more processors, memory, and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods of claims 1-9.
The invention has the beneficial effects that:
The invention discloses a fan inspection route generation method based on an unmanned aerial vehicle, which is capable of automatically planning an accurate inspection route through a fan assembly (tower, chassis, hub and the like) recognition algorithm and a yaw angle model without inputting fan parameters, wherein the method comprises the steps of inspecting waypoints on the route, the head direction of the unmanned aerial vehicle, the cradle head angle and photographing action of each waypoint and the like, and the whole flying process does not need manual participation, so that the method can be universally used for unmanned aerial vehicle fan blade inspection tasks of any scene.
According to the application, through a completely autonomous flight mode, the longitude and latitude of the fan and the elevation of the central point of the hub are automatically re-measured each time the inspection is carried out, so that errors caused by the longitude and latitude are avoided. And adding a classification model when identifying the yaw angle and the phase angle of the blades of the fan, and improving the identification rate in a redundant mode. After the wind reaches the front part of the hub, the wind is finally corrected, the position of the fan is guaranteed to have no deviation, the problem that deviation occurs between measurement and longitude and latitude in the prior art is solved, meanwhile, a curve fitting equation of the pre-bending of the blade is introduced, and the problem that the blade exceeds the picture of the camera when the front edge and the rear edge are inspected is solved. In the steps S1 and S2, the longitude and latitude of the tower barrel and the height of the hub are calculated through the automatic real-time identification and multi-view geometric method, so that the error problem possibly occurring when the GPS positioning is relied is effectively avoided. The method enables the position calculation to be more accurate, and lays a solid foundation for subsequent operations. In step S3, the present application combines the conventional image processing technique with an advanced deep learning classifier algorithm for calculating the fan yaw angle. The hybrid method significantly improves the robustness of yaw angle identification, and can maintain high accuracy even in complex environments. In the step S5, the position of the unmanned aerial vehicle is adjusted through a real-time identification technology, and the fan hub is ensured to be always positioned in the center of a picture. The step not only further corrects the height and the position of the center point of the hub, but also effectively eliminates errors possibly occurring in the previous calculation process, and improves the overall accuracy. In step S7, the parameters of the blade pre-bending machine and the like are combined, the inspection route of four surfaces corresponding to one blade is generated, and then the rest inspection route can be generated only by modifying the phase angle of the corresponding blade, so that the route has universality and can adapt to different fan stop angles.
Drawings
FIG. 1 is a schematic diagram of the positions of an unmanned aerial vehicle and a fan tower when detecting longitude and latitude waypoints;
FIG. 2 (a) is a schematic plan view of calculating azimuth distance of longitude and latitude;
FIG. 2 (b) is a schematic view of calculating the latitude and longitude azimuth distance;
FIG. 3 is a schematic illustration of a tower normalized imaging plan;
FIG. 4 (a) is a top view of a blower;
FIG. 4 (b) is a top view binary diagram of a blower;
FIG. 4 (c) is a fan windward angle identification process;
FIG. 5 (a) is a front view of a fan hub;
FIG. 5 (b) is a front view of a fan hub;
FIG. 5 (c) fan blade phase angle identification process;
FIG. 6 (a) is a schematic view of fan blade phase angle;
FIG. 6 (b) the corresponding binary image of the blade is rotated clockwise to establish a two-dimensional rectangular coordinate system
Fig. 7 hub rectangular coordinate system
FIG. 8 tower rectangular coordinate system based on bottom of fan tower
FIG. 9 blade pre-bend waypoint generation;
FIG. 10 (a) leading and trailing edge routes;
fig. 10 (b) windward and leeward routes.
Detailed Description
The invention is described in detail below with reference to the drawings and the specific embodiments.
The following description of the embodiments of the present invention will be made more apparent and fully hereinafter with reference to the accompanying drawings, in which some, but not all embodiments of the invention are shown. All other embodiments, which can be made by one of ordinary skill in the art without undue burden on the person of ordinary skill in the art based on embodiments of the present invention, are within the scope of the present invention.
The utility model provides a fan inspection route generation method based on unmanned aerial vehicle, the fan includes the wind tower and sets up the impeller on wind tower top, the impeller includes wheel hub and three blade along wheel hub circumference evenly distributed, unmanned aerial vehicle carries on and includes cloud platform and the GPS positioning system that is provided with the camera, includes following step:
S1, defining longitude and latitude waypoints of a fan, wherein the longitude and latitude waypoints of the fan comprise a first fan longitude and latitude waypoint and a second fan longitude and latitude waypoint, the longitude and latitude of the first fan longitude and latitude waypoint is the longitude and latitude (lng 1,lat1) of an unmanned aerial vehicle, the altitude of the first fan longitude and latitude waypoint is higher than that of surrounding obstacles, a holder is adjusted to horizontally shoot, the direction of a head of the unmanned aerial vehicle is adjusted in a rotating manner in situ, so that a fan tower is completely displayed in a picture acquired by a camera, the position of the unmanned aerial vehicle is A, the longitude and latitude is (lng 1,lat1), the altitude of the second fan longitude and latitude waypoint is the same as that of the first fan longitude and latitude waypoint, the longitude and latitude of the second fan longitude and latitude waypoint are corresponding to the longitude and latitude of the moment when the picture taken by the camera is opposite to the center of the tower, the position of the unmanned aerial vehicle is F, the longitude and latitude of the unmanned aerial vehicle is (lng 2,lat2), and the longitude and latitude of the fan tower is calculated (lng 3,lat3), and the position of the fan tower is D;
S2, generating a route for the unmanned aerial vehicle to reach the upper part of the fan according to the acquired longitude and latitude (lng 3,lat3) of the fan tower, wherein the route for the unmanned aerial vehicle to reach the upper part of the fan comprises four waypoints, the first waypoint is a position F where the unmanned aerial vehicle is located, the longitude and latitude of the second waypoint are identical to the longitude and latitude of the first waypoint (lng 1,lat1), the height is the height h 1 of the center of the fan hub, the longitude and latitude of the third waypoint are (lng 1,lat1), the height h 2 is larger than the sum of the height h 1 of the center of the fan hub and the length l of the fan blade, the longitude and latitude of the fourth waypoint are the longitude and latitude (lng 3,lat3) of the fan tower, the height of the fourth waypoint is identical to the height of the third waypoint and h 2, and after the fourth waypoint is reached, the cradle head is adjusted to be vertically shot downwards, and a top view of the fan is acquired;
s3, calculating a yaw angle alpha of the fan based on a top view of the fan;
S4, generating an initial route reaching the front of the hub according to the calculated yaw angle alpha of the fan, wherein the initial route reaching the front of the hub comprises two waypoints, the height of a first waypoint of the initial route reaching the front of the hub is h 2, the longitude and latitude of a second waypoint of the initial route reaching the front of the hub are the same as those of the first waypoint of the initial route reaching the front of the hub, the height of the second waypoint of the initial route reaching the front of the hub is h 1, the position of the second waypoint of the initial route reaching the front of the hub is Q, the position of the second waypoint reaching the Q cradle head is adjusted to be horizontally shot, and the direction of the machine head is adjusted to be the yaw angle of the fan to 180 degrees;
S5, as shown in FIG. 5, a front view of the hub of the fan is obtained from a camera in the cradle head, and a route right in front of the calibrated hub is generated based on a hub identification algorithm. The calibrated front route of the hub comprises two waypoints, a first waypoint of the calibrated front route of the hub is a position Q, the direction of a machine head and a shooting gesture are unchanged, a second waypoint of the calibrated front route of the hub is a picture center point of the hub, which is shot by a camera, and a front view of the fan hub is obtained based on the second waypoint of the calibrated front route of the hub;
S6, calculating a fan blade phase angle beta and a blade pre-bending based on the front hub view obtained in the step S5;
S7, generating a routing inspection route by combining longitude and latitude (lng 3,lat3) of a fan tower, a fan yaw angle alpha, a fan blade phase angle beta, tower height, blade pre-bending and fan blade length l.
The calculating of the longitude and latitude (lng 3,lat3) of the fan tower in S1 specifically includes the following steps:
101 At the longitude and latitude waypoint of the first fan, based on a tower identification algorithm, the fan tower is completely appeared in the picture acquired by the camera, a fan tower image I 1 of the longitude and latitude waypoint of the first fan is acquired, and at the moment, the position of the center point of the tower in the fan tower image I 1 is (mu 1,v1);
102 Based on the tower image I 1 of the fan, calculating the deflection angle c of the fan relative to the direction of the unmanned aerial vehicle head by combining with the internal parameters of the camera;
103 The flying direction is perpendicular to the machine head, the shooting gesture and the machine head direction are kept unchanged, the corresponding longitude and latitude navigation point of the second fan when the shooting picture of the camera is right opposite to the center of the tower barrel is obtained, the center image I 2 of the tower barrel is obtained, and the position of the center point of the tower barrel in the center image I 2 of the tower barrel is (mu 2,v2);
104 Based on the longitude and latitude (lng 1,lat1) of the position A of the unmanned aerial vehicle, the deflection angle c of the fan relative to the head direction of the unmanned aerial vehicle and the longitude and latitude (lng 2,lat2) of the position F of the unmanned aerial vehicle, calculating the longitude and latitude (lng 3,lat3) corresponding to the position D of the fan tower;
A is the camera position of the unmanned aerial vehicle, the corresponding longitude and latitude is (lng 1,lat1), D is the center point of the tower, the position of the tower on the normalized imaging plane of the fan tower image I 1 is C, the position of the center point of the tower on the image is ((mu 1,v1)), the camera internal parameter (f x,fy,cx,cy) is known, and the coordinates (x c,yc, 1) of the C point are: Specifically, F x and F y are products of the camera focal length F and physical dimensions dx and dy of a single pixel in the x-axis direction and the y-axis direction, that is, F x＝F*dx,fy =fxdy, dx and dy representing the actual length units occupied by one pixel in the x-axis direction and the y-axis direction, respectively. The c x and c y sub-tables represent the translation amounts of the x-axis and the y-axis of the origin, and with a as the origin of coordinates, the coordinates of a are (0, 0), and on the two-dimensional plane, B is the point of the center of the screen on the normalized imaging plane, and according to the definition of the normalized imaging plane, the distance L AB = 1 between a and B, therefore +_bac = atan (L BC). As shown in fig. 1, a is the position of the longitude and latitude waypoint of the first fan, B is the position of the center point of the picture in the normalized imaging plane at this time, and C is the position of the tower on the normalized imaging plane (shown in fig. 3);
The direction of the unmanned aerial vehicle head is kept unchanged, the unmanned aerial vehicle flies to a second waypoint along the direction perpendicular to the head, as shown in fig. 1, F is the position of the unmanned aerial vehicle camera corresponding to the waypoint, and the center of the tower is located at the center of the picture. At the moment, the longitude and latitude corresponding to the unmanned plane is (lng 2,lat2), and the real distance between A and D is obtained according to the longitude and latitude of A and F and the angle BAC The azimuth angle a of the point D relative to the point a is obtained.
As shown in fig. 2 (a), knowing that the azimuth angle of the point D relative to the point a is a, the true distance of the AD is L AD, the translational distance from the point a to the point D is L AD*sin(a),LAD x cos (a), and the longitude and latitude of the point a is (lng 1,lat1), as shown in fig. 2 (b), the tangent plane radius ARC of the current latitude=arc x cos (lat 1), where the average radius ARC of the earth takes a value of 6371.393 km (this number is the average of the distances from the earth center to all points on the earth surface). The longitude and latitude of the D point is (lng 3,lat3), where lng3＝lng1+LAD*sin(a)/[ARC*cos(lat1)*2π/360],lat3＝lat1+LAD*cos(a)/(ARC*2π/360).
The step S2 specifically comprises the following steps:
201 The unmanned aerial vehicle continuously flies upwards, so that no obstacle (such as a fan blade, an electric wire and the like) exists above the unmanned aerial vehicle, and in the ascending process, the image transmission picture and the height of the unmanned aerial vehicle are taken as parameters to identify a cabin and a hub;
202 When the nacelle recognizes and detects the occurrence of the target in the picture, the height of the unmanned aerial vehicle is corrected, the center point of the nacelle is positioned at the center of the picture, and the corresponding height of the unmanned aerial vehicle is the corrected height h' 1 of the center of the fan hub.
The step S3 specifically comprises the following steps:
301 Inputting the fan top view into a fan yaw angle class model, obtaining a corresponding output class and a corresponding confidence coefficient conf α1, and converting the class into [ -180 degrees, 180 degrees ] intervals according to the class to obtain an angle alpha 1 of a yaw angle estimated by classification, wherein I is an output category, in this embodiment, i belongs to a positive integer in the [0,71] interval, the top view of the fan is correspondingly divided into 72 categories (-180 degrees to 180 degrees), the angle interval corresponding to each category is 5 degrees, the current top view is input based on a fan yaw angle classification model, the output category is obtained, and the angle interval corresponding to the category is calculated. And after the category is output, calculating an angle interval. The class identified by the fan yaw angle of this embodiment is 2, with a fan yaw angle of between 10 and 15 degrees.
302 Dividing the fan top view into binary images only comprising fan areas by using a dividing algorithm, and clustering all the straight lines according to angles. As shown in fig. 4 (b), two straight lines are finally obtained, and the positions corresponding to the hub regions can be determined according to the intersection points of the straight lines.
303 Straight line detection is carried out on the top view of the fan, a straight line with an intersection point with the edge of a picture is eliminated, two straight lines respectively representing the engine room and the fan blade are obtained, a hub area is taken as an origin of coordinates, the positive directions of an x axis and a y axis are taken as the lower left side, and the angle of an included angle between the x axis and the straight line where the engine room is located is calculated, so that the yaw angle alpha 2 of the fan on the top view of the fan is obtained. 304 Determining the position of the hub according to the intersection point of the two straight lines, and calculating the yaw angle alpha' of the engine room at the moment based on the hub serving as an origin point. Based on α 1 and α 2, a comprehensive confidence level for the nacelle yaw angle is calculated as conf α＝0.5*(confα1+confα2). Let x= |α 1-α2 | whereThe overall confidence in the nacelle yaw angle is highest when the values of α 1 and α 2 are equal, and lowest when α 1 and α 2 differ by 90 °. If the integrated confidence coefficient is greater than the set threshold value of the yaw angle of the nacelle, the yaw angle alpha '=alpha 1 of the nacelle, and if the integrated confidence coefficient is less than the threshold value of the yaw angle of the nacelle, the yaw angle alpha' =alpha 2.confα1 of the nacelle represents the integrated confidence coefficient (probability) of the yaw angle of the nacelle given by the classification algorithm;
305 Adding the cradle head yaw angle rho to obtain a fan yaw angle cradle head correction output value alpha out according to the engine room yaw angle alpha', and converting the fan yaw angle output value into a fixed interval to obtain the fan yaw angle alpha.
Step 305) specifically includes the steps of limiting and correcting the fan yaw angle holder correction output value alpha out to obtain a fan yaw angle when the north is 0 ° and the holder yaw angle is ρ, and the fan yaw angle holder correction output value alpha out =90° +α' +ρ The results were limited to (-180, 180).
The step S5 of calibrating the center position of the hub specifically comprises the following steps:
501 The unmanned aerial vehicle flies to the front of the hub, and other obstacles are not generated in the flying process;
502 The camera shoots a picture and carries out hub identification to obtain a hub image I 3;
503 Acquiring the center point (x 1,y1) of the hub identification frame, and comparing the center point with the center position (x 2,y2) of the hub image I 3 to obtain the flight direction of the control unmanned aerial vehicle Distance fromA fan hub elevation I 4 is obtained.
In this embodiment, the width of the picture shot by the camera is w, and the height is h, and the picture center x 2＝w/2,y2 =h/2. And the unmanned aerial vehicle is adjusted according to the deviation value, so that the hub is positioned at the front view center of the fan hub.
504 Controlling the unmanned aerial vehicle to fly based on the flying direction and the distance in the step 503), and circularly executing 502), wherein the step 503) is that the distance between the position of the picture center point and the center point of the hub identification frame is smaller than a set threshold value, and the position of the unmanned aerial vehicle is the navigation point right in front of the center of the calibrated hub.
Step S6 of calculating the phase angle of the fan blade specifically comprises the following steps:
601a) In the embodiment, the front view of the fan hub is divided into 24 types (0-120 degrees), the corresponding angle interval of each type is 5 degrees, and the phase angle classification model of the blade is trained. After the front view of the fan hub is obtained, the front view is input into a blade phase angle classification model, the corresponding output category and the corresponding confidence level conf β1 are obtained, the output category and the corresponding confidence level conf β1 are converted into a [0 DEG, 120 DEG ] interval, and the obtained classified estimated blade phase angle beta 1 =i. 5,i is the output category and is a positive integer in the [0,23] interval.
As shown in fig. 5 (b) and 5 (c), after the front view of the fan hub is obtained, the hub center is the picture center, in order to reduce the influence of other parts, a binary image only including the fan area is obtained by using a segmentation algorithm, and based on the binary image, the blades are sequentially searched from four sides to the center, so as to obtain the intersection points, usually 4 intersection points, of the blades or the tower extending to the four sides of the image. When the fan is at or approximately at a positive 'Y' or an inverse 'Y' stop, one of the blades is in a vertical state and coincides with the fan tower, so that the intersection point is 3.
602A) And inputting the current front view based on the blade phase angle classification model, acquiring an output class, and calculating a corresponding angle interval.
603A) The blades were searched sequentially from the front view four sides of the fan hub toward the center, resulting in 3 or 4 fan bodies extending to the end points of the image edges.
604A) Calculating an angle by taking the hub as an origin of coordinates, connecting the hub with an endpoint of an image edge, setting the position of the hub in a front view I 4 of the fan hub to be (mu 3,v3), setting the endpoint to be (mu 4,v4), and setting the angle to be
The center of the hub is taken as an origin, and the origin and each intersection point are respectively connected.
605A) Knowing that the included angle between the three blades is 120 degrees, excluding the straight line of the tower barrel part, screening out an included angle beta 2 between the first blade in the anticlockwise direction and the tower barrel, wherein the confidence coefficient of the included angle beta 2 is conf β2;
606a) From the results of 602 a) and 605 a), the fan blade phase angle β is calculated in combination, fig. 6 (a).
Based on β 1 and β 2, a comprehensive confidence conf β＝0.5*(confβ1+confβ2 of the fan blade phase angle is calculated. Let x= |β 1-β2 |whereThe integrated confidence is highest when β 1 and β 2 are the same, and lowest when β 1 and β 2 are 60 ° apart. If the integrated confidence is greater than the threshold value of the set fan blade phase angle, the algorithm output result is beta=beta 1, and if the integrated confidence is less than the threshold value of the fan blade phase angle, the algorithm output result is beta=beta 2.
The step S6 of calculating the blade pre-bending specifically comprises the following steps:
601b) Blade segmentation is carried out on a front view of a fan hub, the hub center is taken as an origin, the phase angle direction is taken as an x-axis positive direction, the x-axis anticlockwise 90 degrees is taken as a y-axis positive direction, and a two-dimensional rectangular coordinate system is established
602B) And taking points along the positive direction of the x axis according to the set interval, calculating y values corresponding to the blade areas, and generating a plurality of data points.
According to the phase angle beta of the fan blade, as shown in fig. 6 (b), a two-dimensional rectangular coordinate system is established by taking the hub center as an origin, the phase angle direction as the positive x-axis direction, and the anti-clockwise 90-degree x-axis direction as the positive y-axis direction
603B) Curve fitting all data points as shown in fig. 7, and extracting the curve analysis function from the two-dimensional rectangular coordinate systemConversion to hub rectangular coordinatesTwo-dimensional rectangular coordinate systemAccording to the coordinate system after the phase angle is rotated, the blade direction is set to be the x axis for convenient calculation and value taking in the embodiment.
Because the pre-bending of the three blades is uniform, only one blade pre-bending resolution is required. In a two-dimensional rectangular coordinate systemAnd taking points along the positive direction of the x-axis according to the set interval, calculating the average value of the corresponding y of the blade area, and generating a plurality of data points.
604B) Four parameter equation is selectedCurve fitting is performed, where d represents a baseline of the blade pre-bending, a represents a maximum of the blade pre-bending, c represents a position parameter of the inflection point, and b represents a slope parameter of the curve. This expression is based on the shape of an S-shaped curve, with the denominator value approaching 1 and the curve approaching the baseline d when x is small and approaching infinity and the curve approaching the maximum a when x is large. And c, controlling the inflection point position of the curve, and d, controlling the slope of the curve. And (3) bringing all data points into the expected threshold epsilon, counting error average epsilon 1 between the true values and the estimated values of all the data points in the iterative process, and adjusting parameters according to the error average epsilon 1 until the error average is controlled within the expected threshold epsilon 1 < epsilon, wherein a corresponding analytical formula is a curve fitting equation, and the blade pre-bending is represented by the curve equation due to the bending of the blade. Epsilon represents the error expectation threshold.
The step S7 specifically includes the following steps:
701 Based on fan yaw angle α, fan blade phase angle β, inherent parameters impeller elevation angle θ and blade cone angle of the fan To calculate the routing. Establishing a two-dimensional rectangular coordinate system according to the phase angle direction of the bladeIn order to generate a plurality of data points to be fitted, the blade coordinate system is converted into a uniform hub rectangular coordinate in the subsequent course generating processIs a kind of medium. For the convenience of calculation, a rectangular coordinate system based on a hub as shown in FIG. 7 is usedIn the rectangular coordinates of the hubThe angle of the first blade becomes β' =270 ° - β. According to the elevation angle of the impeller, the corresponding rotation matrix under the coordinate system is as follows: Obtaining a first blade direction vector The included angles between the other two blades and the first blade are known, the pre-bending design of the blades is the same, and the direction vectors of the second blade and the third blade are obtained by replacing the angle of the blades. And (3) introducing the coordinate mapping expression before and after conversion into a curve equation of the pre-bending of the blade to obtain curve fitting analysis type of each blade under the coordinate system of the hub.
Two-dimensional rectangular coordinate systemIs a two-dimensional coordinate system, and the rectangular coordinate of the hubRectangular coordinate system of towerAre three-dimensional coordinate systems.
702 Known blade length/in coordinate systemIn the process of inspecting the front edge, the blade pre-bending curve equation z=obtained through coordinate system conversion The x-axis and the y-axis of (a) respectively correspond toWherein the x-variable is An Zhao n equally divided within the interval of [0, i x v β ], as shown in FIG. 9, n coordinate-based systems can be generatedIs the waypoint of (2) Wherein v β is the first blade direction vector, ε g is the distance between the unmanned aerial vehicle and the blade when inspecting the front edge of the blade, and the unmanned aerial vehicle obtains the blade inspection route through these waypoints in turn. Similarly, when the trailing edge is inspected, the waypoint isEpsilon h is the distance from the blade when inspecting the trailing edge of the blade. For lee, the waypoint is The windward waypoint isEpsilon m is the distance from the blade when the blade is inspected on the windward side. In the rectangular coordinate system of the hubNext, x may be set to 0.
703 Establishing a tower rectangular coordinate system based on the bottom of the fan towerAnd combining the longitude and latitude (lng 3,lat3) of the fan tower, and generating a route taking the initial position of the unmanned aerial vehicle as a starting point, as shown in fig. 10. The yaw angle alpha of the fan and the corrected hub height h' 1 are known, and the pre-bending of the blades is known to be based on a rectangular coordinate system of the hubIs characterized by that the rectangular coordinate system of the wheel hubConversion to a tower rectangular coordinate system based on the bottom of a fan towerThe corresponding conversion matrix is as follows: All the waypoints are represented by projection coordinates, and in the embodiment, the waypoint x= [ x 0,x1,x2]T ] corresponds to projection coordinates of x' = [ x 0,x1,x2,1]T ]. Converted into a rectangular coordinate system of a tower barrel And then converted into longitude and latitude. The coordinate system is converted and the influence of the height of the central point of the hub and the yaw angle is added. The application adopts ENU to enable the tower cylinder rectangular coordinate systemReconvert to longitude, latitude and altitude.
704 In inspecting fan blades, each blade needs to inspect the leading edge, trailing edge, windward side (pressure side) and leeward side (suction side). In the embodiment, the blades are respectively numbered as blade 1, blade 2 and blade 3, and the inspection sequence may be as follows, blade 1-leading edge, blade 1-trailing edge, blade 1-leeward side, blade 1-windward side, blade 2-leading edge, blade 2-trailing edge, blade 2-leeward side, blade 2-windward side, blade 3-leading edge, blade 3-trailing edge, blade 3-leeward side and blade 3-windward side. Wherein, the inspection is generally started from the front of the center of the hub, as shown in G1 of fig. 10 (a), after the inspection of the blade 1-front edge reaches G2, wherein the waypoint v g calculated in 2 is used, after the trailing edge blade tip of the blade 1 is safely reached through waypoints G3, G4 and G5, the inspection of the trailing edge of the blade 1 is started, and the waypoint v h is used to reach G6. The nacelle is then turned right behind by G6, G7 and H1 to a start position for inspecting the blade 1-lee side, and the inspection is started from H1 to H2 from the blade root, as shown in fig. 10 (b). Through H2, H3, H4 and H5, the wind-driven vehicle reaches the upper part of the windward side. Then, the inspection is completed through H5 and H6, and the using waypoint is v r. For blade 2 and blade 3, the corresponding blade phase angles are modified to calculate the corresponding waypoints.
A computing system comprising one or more processors, memory, and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods of claims 1-9.
The foregoing is merely a preferred embodiment of the present invention and it should be noted that modifications and adaptations to those skilled in the art may be made without departing from the principles of the present invention, which are intended to be comprehended within the scope of the present invention.
Thus far, the technical solution of the present invention has been described in connection with the preferred embodiments shown in the drawings, but it is easily understood by those skilled in the art that the scope of protection of the present invention is not limited to these specific embodiments. Equivalent modifications and substitutions for related technical features may be made by those skilled in the art without departing from the principles of the present invention, and such modifications and substitutions will fall within the scope of the present invention.
In the description provided herein, numerous specific details are set forth. However, it is understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure and aiding in the understanding of one or more of the various inventive aspects. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
Those skilled in the art will appreciate that the modules or units or groups of devices in the examples disclosed herein may be arranged in a device as described in this embodiment, or alternatively may be located in one or more devices different from the devices in this example. The modules in the foregoing examples may be combined into one module or may be further divided into a plurality of sub-modules.
Those skilled in the art will appreciate that the modules in the apparatus of the embodiments may be adaptively changed and disposed in one or more apparatuses different from the embodiments. The modules or units or groups of embodiments may be combined into one module or unit or group, and furthermore they may be divided into a plurality of sub-modules or sub-units or groups. Any combination of all features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or units of any method or apparatus so disclosed, may be used in combination, except insofar as at least some of such features and/or processes or units are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings), may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features but not others included in other embodiments, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.
Furthermore, some of the embodiments are described herein as methods or combinations of method elements that may be implemented by a processor of a computer system or by other means of performing the functions. Thus, a processor with the necessary instructions for implementing the described method or method element forms a means for implementing the method or method element. Furthermore, the elements of the apparatus embodiments described herein are examples of apparatus for performing the functions performed by the elements for the purpose of practicing the invention.
The various techniques described herein may be implemented in connection with hardware or software or, alternatively, with a combination of both. Thus, the methods and apparatus of the present invention, or certain aspects or portions of the methods and apparatus of the present invention, may take the form of program code (i.e., instructions) embodied in tangible media, such as floppy diskettes, CD-ROMs, hard drives, or any other machine-readable storage medium, wherein, when the program is loaded into and executed by a machine, such as a computer, the machine becomes an apparatus for practicing the invention.
In the case of program code execution on programmable computers, the computing device will generally include a processor, a storage medium readable by the processor (including volatile and non-volatile memory and/or storage elements), at least one input device, and at least one output device. Wherein the memory is configured to store program code and the processor is configured to perform the method of the invention in accordance with instructions in said program code stored in the memory.
By way of example, and not limitation, computer readable media comprise computer storage media and communication media. Computer-readable media include computer storage media and communication media. Computer storage media stores information such as computer readable instructions, data structures, program modules, or other data. Communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. Combinations of any of the above are also included within the scope of computer readable media.
As used herein, unless otherwise specified the use of the ordinal terms "first," "second," "third," etc., to describe a general object merely denote different instances of like objects, and are not intended to imply that the objects so described must have a given order, either temporally, spatially, in ranking, or in any other manner.
While the invention has been described with respect to a limited number of embodiments, those skilled in the art, having benefit of the above description, will appreciate that other embodiments are contemplated within the scope of the invention as described herein. Furthermore, it should be noted that the language used in the specification has been principally selected for readability and instructional purposes, and may not have been selected to delineate or circumscribe the inventive subject matter. Accordingly, many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is intended to be illustrative, but not limiting, of the scope of the invention, which is defined by the appended claims.
Claims (9)
1. The utility model provides a fan inspection route generation method based on unmanned aerial vehicle, the fan includes the wind tower and sets up the impeller on wind tower top, the impeller includes wheel hub and three blade along wheel hub circumference evenly distributed, unmanned aerial vehicle carries on cloud platform and the GPS positioning system that is provided with the camera, its characterized in that includes following step:
S1, defining longitude and latitude waypoints of a fan, wherein the longitude and latitude waypoints of the fan comprise a first fan longitude and latitude waypoint and a second fan longitude and latitude waypoint, the longitude and latitude of the first fan longitude and latitude waypoint is the longitude and latitude (lng 1,lat1) of an unmanned aerial vehicle, the altitude of the first fan longitude and latitude waypoint is higher than that of surrounding obstacles, a holder is adjusted to horizontally shoot, the direction of a head of the unmanned aerial vehicle is adjusted in a rotating manner in situ, so that a fan tower is completely displayed in a picture acquired by a camera, the position of the unmanned aerial vehicle is A, the longitude and latitude is (lng 1,lat1), the altitude of the second fan longitude and latitude waypoint is the same as that of the first fan longitude and latitude waypoint, the longitude and latitude of the second fan longitude and latitude waypoint are corresponding to the longitude and latitude of the moment when the picture taken by the camera is opposite to the center of the tower, the position of the unmanned aerial vehicle is F, the longitude and latitude of the unmanned aerial vehicle is (lng 2,lat2), and the longitude and latitude of the fan tower is calculated (lng 3,lat3), and the position of the fan tower is D;
S2, generating a route from the unmanned aerial vehicle to the upper side of the fan according to the acquired longitude and latitude (lng 3,lat3) of the fan tower, wherein the route from the unmanned aerial vehicle to the upper side of the fan comprises four waypoints, the first waypoint is a position F where the unmanned aerial vehicle is located, the longitude and latitude of the second waypoint are identical to the longitude and latitude of the first waypoint (lng 1,lat1), the height is the height h 1 of the center of the fan hub, the longitude and latitude of the third waypoint are (lng 1,lat1), the height h 2 is larger than the sum of the height h 1 of the center of the fan hub and the length l of the fan blade, the longitude and latitude of the fourth waypoint are the longitude and latitude (lng 3,lat3) of the fan tower, the height of the fourth waypoint is identical to the height of the third waypoint and h 2, and after the fourth waypoint is reached, the cradle head is adjusted to be shot vertically downwards, and a top view of the fan is acquired;
s3, calculating a yaw angle alpha of the fan based on a top view of the fan;
S4, generating an initial route reaching the front of the hub according to the calculated yaw angle alpha of the fan, wherein the initial route reaching the front of the hub comprises two waypoints, the height of a first waypoint of the initial route reaching the front of the hub is h 2, the longitude and latitude of a second waypoint of the initial route reaching the front of the hub are the same as those of the first waypoint of the initial route reaching the front of the hub, the height of the second waypoint of the initial route reaching the front of the hub is h 1, the position of the second waypoint of the initial route reaching the front of the hub is Q, the position of the second waypoint reaching the Q cradle head is adjusted to be horizontally shot, and the direction of the machine head is adjusted to be the yaw angle of the fan to 180 degrees;
S5, acquiring a front view of a fan hub from a camera in a cradle head, generating a calibrated hub front route based on a hub identification algorithm, wherein the calibrated hub front route comprises two waypoints, a first waypoint of the calibrated hub front route is a position Q, the machine head direction and the shooting gesture are unchanged, a second waypoint of the calibrated hub front route is a picture center point of the hub, the center of the picture is shot by the camera, and acquiring the front view of the fan hub based on the second waypoint of the calibrated hub front route;
S6, calculating a fan blade phase angle beta and a blade pre-bending based on the front hub view obtained in the step S5;
S7, generating a routing inspection route by combining longitude and latitude (lng 3,lat3) of a fan tower, a fan yaw angle alpha, a fan blade phase angle beta, tower height, blade pre-bending and fan blade length l;
301 Inputting the fan top view into a fan yaw angle class model, obtaining the output class of the fan yaw angle and the corresponding confidence coefficient conf α1, converting the output class into [ -180 degrees, 180 degrees ] intervals according to the class, and obtaining the angle alpha 1 of the yaw angle estimated by classification, wherein
I is an output category of a yaw angle of the fan, i is a positive integer in a [0, M-1] interval, the top view correspondence of the fan is divided into M categories, and an angle interval corresponding to each category is k degrees;
302 Dividing the fan top view into a binary image only comprising a fan area by utilizing a dividing algorithm, and clustering all straight lines according to angles;
303 Straight line detection is carried out on the top view of the fan, a straight line with an intersection point with the edge of a picture is eliminated, two straight lines respectively representing the engine room and the fan blade are obtained, a hub area is taken as an origin of coordinates, the positive directions of an x axis and a y axis are taken as the lower left side, and the angle of an included angle between the x axis and the straight line where the engine room is positioned is calculated, so that the yaw angle alpha 2 of the fan on the top view of the fan is obtained;
304 Determining the position of the hub according to the intersection point of the two straight lines, calculating the yaw angle alpha' of the engine room at the moment based on the hub as an origin, calculating the comprehensive confidence coefficient of the yaw angle of the engine room to be conf α＝0.5*(confα1+confα2 based on alpha 1 and alpha 2, and letting x= |alpha 1-α2 |in the above steps If the integrated confidence coefficient is larger than the threshold value of the set cabin yaw angle, the integrated confidence coefficient is based on the cabin yaw angle alpha '=alpha 1 when the hub is the origin, and is smaller than the threshold value of the cabin yaw angle, and the integrated confidence coefficient of the cabin yaw angle given by the classification algorithm is based on the cabin yaw angle alpha' =alpha 2;confα1 when the hub is the origin;
305 According to the yaw angle alpha' of the engine room based on the wheel hub as the origin, adding the yaw angle rho of the cradle head to obtain a yaw angle cradle head correction output value alpha out of the fan, and converting the yaw angle output value of the fan into a fixed interval to obtain the yaw angle alpha of the fan.
2. The unmanned aerial vehicle-based fan routing generation method of claim 1, wherein,
The calculating of the longitude and latitude (lng 3,lat3) of the fan tower in the S1 specifically comprises the following steps:
101 At the longitude and latitude waypoint of the first fan, based on a tower identification algorithm, the fan tower is completely appeared in the picture acquired by the camera, a fan tower image I 1 of the longitude and latitude waypoint of the first fan is acquired, and at the moment, the position of the center point of the tower in the fan tower image I 1 is (mu 1,v1);
102 Based on the tower image I 1 of the fan, calculating the deflection angle c of the fan relative to the direction of the unmanned aerial vehicle head by combining with the internal parameters of the camera;
103 The flying direction is perpendicular to the machine head, the shooting gesture and the machine head direction are kept unchanged, the corresponding longitude and latitude navigation point of the second fan when the shooting picture of the camera is right opposite to the center of the tower barrel is obtained, the center image I 2 of the tower barrel is obtained, and the position of the center point of the tower barrel in the center image I 2 of the tower barrel is (mu 2,v2);
104 Based on the longitude and latitude (lng 1,lat1) of the position A of the unmanned aerial vehicle, the deflection angle c of the fan relative to the head direction of the unmanned aerial vehicle and the longitude and latitude (lng 2,lat2) of the position F of the unmanned aerial vehicle, the longitude and latitude (lng 3,lat3) corresponding to the position D of the fan tower is calculated.
3. The method for generating a fan routing inspection route based on the unmanned aerial vehicle according to claim 1, wherein the step S2 specifically comprises the following steps:
201 The unmanned aerial vehicle continuously flies upwards, so that no obstacle exists above the unmanned aerial vehicle, and in the ascending process, the image transmission picture and the height of the unmanned aerial vehicle are used as parameters to identify the engine room and the hub;
202 When the nacelle and the hub recognize and detect the targets in the picture, the height of the unmanned aerial vehicle is corrected, the nacelle or the nacelle center point is positioned at the center of the picture, and the corresponding height of the unmanned aerial vehicle is the corrected height h' 1 of the center of the fan hub.
4. The unmanned aerial vehicle-based fan routing generation method of claim 1, wherein,
Step 305) specifically includes the steps of limiting and correcting the fan yaw angle holder correction output value alpha out to obtain a fan yaw angle when the north is 0 ° and the holder yaw angle is ρ, and the fan yaw angle holder correction output value alpha out =90° +α' +ρ The fan yaw angle α is limited to (-180, 180).
5. The unmanned aerial vehicle-based fan routing generation method of claim 1, wherein,
The step S5 of calibrating the center position of the hub specifically comprises the following steps:
501 The unmanned aerial vehicle flies to the front of the hub, and other obstacles are not generated in the flying process;
502 The camera shoots a picture and carries out hub identification to obtain a hub image I 3;
503 Acquiring the center point (x 1,y1) of the hub identification frame, and comparing the center point with the center position (x 2,y2) of the hub image I 3 to obtain the flight direction of the control unmanned aerial vehicle Distance fromAcquiring a front view I 4 of a fan hub;
504 Controlling the unmanned aerial vehicle to fly based on the flying direction and the distance in the step 503), and circularly executing 502), wherein the step 503) is that the distance between the position of the picture center point and the center point of the hub identification frame is smaller than a set threshold value, and the position of the unmanned aerial vehicle is the navigation point right in front of the center of the calibrated hub.
6. The unmanned aerial vehicle-based fan routing generation method of claim 1, wherein,
Step S6 of calculating the phase angle of the fan blade specifically comprises the following steps:
601a) After the front view of the fan hub is obtained, the front view of the fan hub is input into a blade phase angle classification model, the output category of the fan blade phase angle and the corresponding confidence level conf β1 are obtained, the front view of the fan hub is converted into an angle interval according to the category, and the obtained classified estimated blade phase angle beta 1 =i is the output category of the fan blade phase angle, i is a positive integer in the [0,U-1] interval;
602a) Inputting a current front view based on a blade phase angle classification model, acquiring an output class, and calculating a corresponding angle interval;
603a) Searching blades from the front view four sides of the fan hub to the center in sequence to obtain end points of 3 or 4 fan bodies extending to the image edges;
604a) Calculating an angle by taking the hub as an origin of coordinates, connecting the hub with an endpoint of an image edge, setting the position of the hub in a front view I 4 of the fan hub to be (mu 3,v3), setting the endpoint to be (mu 4,v4), and setting the angle to be
605A) Excluding the straight line of the tower barrel part, screening out an included angle beta 2 between the first blade in the anticlockwise direction and the tower barrel, wherein the confidence of the included angle beta 2 is conf β2;
606a) The phase angle beta of the fan blade is calculated,
Based on beta 1 and beta 2, calculating the comprehensive confidence level conf β＝0.5*(confβ1+confβ2 of the phase angle of the fan blade), and letting x= |beta 1-β2 |in the aboveWhen the values of beta 1 and beta 2 are the same, the comprehensive confidence is highest, when the values of beta 1 and beta 2 are 60 degrees different, the comprehensive confidence is lowest, if the comprehensive confidence is larger than the threshold value of the set fan blade phase angle, the algorithm output result is beta=beta 1, and when the comprehensive confidence is smaller than the threshold value of the fan blade phase angle, the algorithm output is beta=beta 2.
7. The unmanned aerial vehicle-based fan routing generation method of claim 1, wherein the calculating of the blade pre-bending in S6 specifically comprises the following steps:
601b) Blade segmentation is carried out on a front view of a fan hub, the hub center is taken as an origin, the phase angle direction is taken as an x-axis positive direction, the x-axis anticlockwise 90 degrees is taken as a y-axis positive direction, and a two-dimensional rectangular coordinate system is established
602B) Taking points along the positive direction of the x axis according to the set interval, calculating y values corresponding to the blade areas, and generating a plurality of data points;
603b) Fitting all data points by curves, and obtaining a curve analysis function from a two-dimensional rectangular coordinate system Conversion to hub rectangular coordinatesTwo-dimensional rectangular coordinate systemIs a coordinate system rotated according to the phase angle;
604b) Four parameter equation is selected And (3) carrying out curve fitting, wherein d represents a baseline of the blade pre-bending, a represents a maximum value of the blade pre-bending, c represents a position parameter of an inflection point, b represents a slope parameter of the curve, carrying data points in, setting an error expected threshold epsilon, counting error mean epsilon 1 between the true values and the estimated values of all points in an iterative process, and adjusting parameters according to the error mean epsilon 1 until the error mean is controlled within the expected threshold epsilon 1 < epsilon, wherein a corresponding analytical formula is an equation of curve fitting, and the blade pre-bending is represented by the curve equation due to the bending of the blade.
8. The method for generating a fan routing inspection route based on the unmanned aerial vehicle according to claim 1, wherein the step S7 specifically comprises the following steps:
701 Based on fan yaw angle α, fan blade phase angle β, inherent parameters impeller elevation angle θ and blade cone angle of the fan Calculating the routing inspection route in the rectangular coordinates of the hubThe angle of the first blade is changed to beta' =270-beta, and the angle of elevation of the impeller is set in the rectangular coordinate of the hubThe next corresponding rotation matrix is: Obtaining a first blade direction vector The angle between the other two blades and the first blade is known, the pre-bending of the blades is the same, the direction vectors of the second blade and the third blade are obtained by replacing the angle of the blades, and the coordinate mapping expression before and after conversion is brought into the curve equation of the pre-bending of the blades to obtain the rectangular coordinates of each blade at the hubThe lower curve fitting analytic expression;
702 Known blade length/in coordinate system In the process of inspecting the front edge, the blade pre-bending curve equation z=f (x) obtained through coordinate system conversion,The x variable takes value according to n equal division in the interval of [0, l x v β ] to generate n coordinate systemsIs the waypoint of (2) Wherein epsilon g is the distance between the unmanned aerial vehicle and the blade when the unmanned aerial vehicle patrols and examines the front edge of the blade, the unmanned aerial vehicle obtains a blade patrol route through waypoints in sequence, n represents that the x variable takes values in the interval of [0, l x v β ] according to n equal division, and the generated coordinate system is based onThe number of waypoints;
when the trailing edge is inspected, the waypoint is Epsilon h is the distance from the blade when the trailing edge of the blade is inspected, and for the leeward side, the waypoint is The windward waypoint is Epsilon m is the distance between the inspection blade and the blade when the inspection blade faces the wind;
703 Generating a route from the initial position of the unmanned aerial vehicle by combining the longitude and latitude (lng 3,lat3) of a wind turbine tower, knowing a yaw angle a of the wind turbine and a corrected hub height h' 1, and knowing that the pre-bending of the blades is based on a hub rectangular coordinate system Is characterized by that the rectangular coordinate system of the wheel hubConversion to a tower rectangular coordinate system based on the bottom of a fan towerThe corresponding conversion matrix is: Rectangular coordinate system of tower Then converting the longitude and latitude and the altitude;
704 In the inspection of the fan blade, the front edge, the rear edge, the windward side and the leeward side of the blade are inspected respectively.
9. A computing system, comprising:
One or more processors, memory, and one or more programs, wherein one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs comprising instructions for performing any of the methods of claims 1-8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410518436.3A CN118444693B (en) | 2024-04-26 | 2024-04-26 | A method and system for generating wind turbine inspection routes based on drones |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410518436.3A CN118444693B (en) | 2024-04-26 | 2024-04-26 | A method and system for generating wind turbine inspection routes based on drones |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118444693A CN118444693A (en) | 2024-08-06 |
| CN118444693B true CN118444693B (en) | 2025-02-25 |
Family
ID=92313195
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410518436.3A Active CN118444693B (en) | 2024-04-26 | 2024-04-26 | A method and system for generating wind turbine inspection routes based on drones |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118444693B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119007053B (en) * | 2024-10-24 | 2025-07-01 | 南通火眼智能科技有限公司 | Method for identifying blade tips of fan blades by using unmanned aerial vehicle-mounted edge computing platform |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112506214A (en) * | 2020-11-16 | 2021-03-16 | 天津航天中为数据系统科技有限公司 | Operation flow of autonomous fan inspection system of unmanned aerial vehicle |
| CN113723192A (en) * | 2021-07-30 | 2021-11-30 | 鹏城实验室 | Blade image acquisition method in running state of fan |
| CN115480589A (en) * | 2022-09-06 | 2022-12-16 | 中科云尚(南京)智能技术有限公司 | Method and system for generating fan inspection route based on unmanned aerial vehicle |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111708380B (en) * | 2020-06-29 | 2023-11-10 | 北京御航智能科技有限公司 | Wind turbine generator appearance defect detection method, platform, unmanned aerial vehicle and system |
| CN114296483B (en) * | 2022-03-09 | 2022-06-28 | 北京图知天下科技有限责任公司 | Intelligent inspection method and electronic equipment for wind driven generator in non-stop state |
-
2024
- 2024-04-26 CN CN202410518436.3A patent/CN118444693B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112506214A (en) * | 2020-11-16 | 2021-03-16 | 天津航天中为数据系统科技有限公司 | Operation flow of autonomous fan inspection system of unmanned aerial vehicle |
| CN113723192A (en) * | 2021-07-30 | 2021-11-30 | 鹏城实验室 | Blade image acquisition method in running state of fan |
| CN115480589A (en) * | 2022-09-06 | 2022-12-16 | 中科云尚(南京)智能技术有限公司 | Method and system for generating fan inspection route based on unmanned aerial vehicle |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118444693A (en) | 2024-08-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110580717B (en) | A method for generating autonomous inspection routes of unmanned aerial vehicles for power towers | |
| CN110554704B (en) | Unmanned aerial vehicle-based fan blade autonomous inspection method | |
| CN110879601B (en) | A UAV inspection method for unknown wind turbine structure | |
| CN108894933B (en) | Method and system for tracking, losing and re-capturing fan blade tips during tracking detection of fan blade tips through unmanned aerial vehicle | |
| CN112904877A (en) | Automatic fan blade inspection system and method based on unmanned aerial vehicle | |
| US20230105991A1 (en) | Method of imaging a wind turbine rotor blade | |
| CN108915959B (en) | Method and system for detecting bypassing of fan blade tip area through unmanned aerial vehicle | |
| CN110189315B (en) | Unmanned aerial vehicle automatic positioning method for blades of wind turbine generator | |
| CN109739254B (en) | Unmanned aerial vehicle adopting visual image positioning in power inspection and positioning method thereof | |
| CN114004977B (en) | Method and system for positioning aerial data target based on deep learning | |
| EP3679439A1 (en) | Method and unmanned aerial vehicle for acquiring sensor data related to a wind turbine | |
| CN115480589B (en) | Unmanned aerial vehicle-based fan routing inspection route generation method and system | |
| CN118444693B (en) | A method and system for generating wind turbine inspection routes based on drones | |
| CN113610749A (en) | Fan blade defect detection method based on neural network | |
| CN114397900B (en) | Unmanned aerial vehicle aerial photo center point longitude and latitude error optimization method | |
| CN115328181A (en) | Method for positioning key target space in unmanned aerial vehicle power transmission line inspection | |
| CN108869196B (en) | Method and system for detecting rear side blade root area of fan through unmanned aerial vehicle | |
| CN109764864B (en) | A method and system for indoor UAV pose acquisition based on color recognition | |
| CN112700498A (en) | Wind driven generator blade tip positioning method and system based on deep learning | |
| CN111815560A (en) | Photovoltaic power station fault detection method and device, portable detection equipment and storage medium | |
| CN112947526A (en) | Unmanned aerial vehicle autonomous landing method and system | |
| CN114723184B (en) | Wind driven generator measuring method, device and equipment based on visual perception | |
| CN115933730B (en) | Unmanned aerial vehicle inspection and fault positioning method for photovoltaic power station | |
| Zhou et al. | Three dimensional fully autonomous inspection method for wind power employing unmanned aerial vehicle based on 5G wireless communication and artificial intelligence | |
| CN116893685A (en) | Unmanned aerial vehicle route planning 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |