CN110282143B - Inspection method for offshore wind farm unmanned aerial vehicle - Google Patents
Inspection method for offshore wind farm unmanned aerial vehicle Download PDFInfo
- Publication number
- CN110282143B CN110282143B CN201910514880.7A CN201910514880A CN110282143B CN 110282143 B CN110282143 B CN 110282143B CN 201910514880 A CN201910514880 A CN 201910514880A CN 110282143 B CN110282143 B CN 110282143B
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- blade
- fan
- offshore wind
- 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
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENTS OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D47/00—Equipment not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENTS OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D47/00—Equipment not otherwise provided for
- B64D47/08—Arrangements of cameras
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64F—GROUND OR AIRCRAFT-CARRIER-DECK INSTALLATIONS SPECIALLY ADAPTED FOR USE IN CONNECTION WITH AIRCRAFT; DESIGNING, MANUFACTURING, ASSEMBLING, CLEANING, MAINTAINING OR REPAIRING AIRCRAFT, NOT OTHERWISE PROVIDED FOR; HANDLING, TRANSPORTING, TESTING OR INSPECTING AIRCRAFT COMPONENTS, NOT OTHERWISE PROVIDED FOR
- B64F1/00—Ground or aircraft-carrier-deck installations
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2101/00—UAVs specially adapted for particular uses or applications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2101/00—UAVs specially adapted for particular uses or applications
- B64U2101/30—UAVs specially adapted for particular uses or applications for imaging, photography or videography
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64U—UNMANNED AERIAL VEHICLES [UAV]; EQUIPMENT THEREFOR
- B64U2201/00—UAVs characterised by their flight controls
- B64U2201/20—Remote controls
Abstract
The invention discloses an inspection method for an unmanned aerial vehicle in an offshore wind farm, which comprises the following steps: an automatic airport is deployed on the roof of the offshore booster station, and the unmanned aerial vehicle is remotely controlled through a network to take off and land, replace batteries and perform task operation in a full-automatic mode; controlling an unmanned aerial vehicle carrying a zoom camera and a laser radar to take off from the automatic airport, and carrying out full-autonomous path planning and image shooting on a fan and a sea area near a marine booster station; acquiring images of the fan blade and the sea area shot by the unmanned aerial vehicle, and performing fault analysis processing on the images through a deep learning algorithm to identify a fan crack and a marine vessel; according to the invention, the offshore wind farm unmanned aerial vehicle is used for polling, the offshore wind farm sea area and the draught fan are efficiently polled in time, the intellectualization of the offshore wind farm is improved, the operation and maintenance cost is effectively reduced, and the safe and reliable operation of the offshore wind farm is determined.
Description
Technical Field
The invention relates to the field of unmanned aerial vehicle inspection, in particular to an inspection method for an unmanned aerial vehicle in an offshore wind farm.
Background
Due to the wide distribution of the offshore wind power field and the severe offshore weather environment, the operation and routing inspection of the wind power field are very difficult, the cost is high, and the operation and management according to the operation and management mode of the onshore traditional wind power field are difficult. The offshore booster station in the wind power plant plays a role in transmission and distribution of electric energy of the whole power plant, and is an important part in operation management of the wind power plant. Meanwhile, the fans of the wind power plant are high in cost and bad in operating environment, and how to timely find and remove the fan faults and ensure safe and reliable operation of the fans is very important. At present, the main field for offshore wind power development in China is mainly arranged on the coastal areas facing wide mudflats and shallow water seabed. The operation and maintenance operation is obviously affected by tide, the severe working conditions such as typhoon and the like exist, more rivers, the cyclones, the strong wind, the cluster fog and the thunderstorm weather exist, the shoal is large in size, the tide in the intertidal zone is obviously affected, the access is difficult, the traffic equipment is difficult to select, the effective time of offshore maintenance operation is short, the safety risk is large, and large-scale maintenance equipment is lacked.
The offshore wind farm operation and maintenance needs to comprehensively consider factors such as offshore distance, meteorological sea conditions, unit fault rate, maintenance behaviors, power generation capacity and operation and maintenance economy to configure the operation and maintenance ship. Generally speaking, larger-scale wind power plants are in the form of fleet, and comprise different types of ships, such as traffic boats, professional operation and maintenance ships, professional operation and maintenance mother ships, rescue monitoring ships and other special engineering ships. The offshore booster station and the fan are only internally provided with corresponding cameras, and the inside of the offshore booster station and the inside of the fan are observed in real time. However, the AIS receiving device can only display real-time dynamic states of ships, specific behaviors of dangerous ships entering an offshore wind power plant cannot be determined, and the configured fan blade sensor cannot identify fine cracks of blades. Therefore, in the prior art, for the observation of the sea area and the fan blades in the offshore wind power plant, a corresponding operation and maintenance ship needs to be dispatched to the site for inspection, so that the offshore wind power operation and maintenance cost is very high.
Disclosure of Invention
The invention provides an offshore wind farm unmanned aerial vehicle inspection method, which is used for solving the technical problems that the prior art cannot clearly determine the specific behavior of dangerous ships entering an offshore wind farm and cannot identify fine cracks of blades by inspection of an offshore wind farm unmanned aerial vehicle, so that the inspection of an offshore wind farm sea area and a fan can be timely and efficiently carried out, the intelligentization of the offshore wind farm is improved, the operation and maintenance cost is effectively reduced, and the safe and reliable operation of the offshore wind farm is determined.
In order to solve the technical problem, an embodiment of the invention provides an inspection method for an unmanned aerial vehicle in an offshore wind farm, which comprises the following steps:
an automatic airport is deployed on the roof of the offshore booster station, and the unmanned aerial vehicle is remotely controlled through a network to take off and land, replace batteries and perform task operation in a full-automatic mode;
controlling an unmanned aerial vehicle carrying a zoom camera and a laser radar to take off from the automatic airport, and carrying out full-autonomous path planning and image shooting on a fan and a sea area near a marine booster station;
and acquiring images of the fan blade and the sea area shot by the unmanned aerial vehicle, and performing fault analysis processing on the images through a deep learning algorithm to identify the fan crack and the marine vessel.
As a preferred scheme, the unmanned aerial vehicle performs fully autonomous path planning, including:
sequentially judging whether weather and wind conditions of the offshore booster station meet safe operation conditions, if so, simultaneously judging whether the unmanned aerial vehicle battery is electrified, and if not, controlling to change the battery and charging the battery;
starting an automatic inspection program and planning an inspection route;
the unmanned aerial vehicle flies above a designated fan or a designated ship, and when the unmanned aerial vehicle is automatically lifted to a designated height, the unmanned aerial vehicle automatically rises and calculates the central height of a fan hub;
the unmanned aerial vehicle automatically inspects each blade, and each blade inspects a plurality of paths;
after the flight of the air route is finished, the unmanned aerial vehicle returns to the automatic airport of the offshore booster station, namely, the flying spot is over, the cabin door of the automatic airport is controlled to be opened, the unmanned aerial vehicle automatically descends, and the inspection task is finished.
As the preferred scheme, when unmanned aerial vehicle rises to the wheel hub center automatically, confirm whether there is the deviation in wheel hub center and unmanned aerial vehicle position, if have, then finely tune unmanned aerial vehicle, with wheel hub center adjustment back, continue to patrol and examine the task.
Preferably, each blade inspects 4 paths, and a single blade shoots 4 areas of the front edge, the rear edge, the windward side and the leeward side.
As a preferred scheme, the processing of the image acquired by the unmanned aerial vehicle includes:
acquiring a target image with the resolution of 1mm x 3mm shot by an unmanned aerial vehicle;
splicing the single blade in the target image into 4 overall large images through data processing according to 4 areas of a front edge, a rear edge, a windward side and a leeward side;
and each path is independently spliced into a large graph, and any damage position on the blade is positioned by means of the large graph and the flight log.
Preferably, before the unmanned aerial vehicle captures images of the wind turbine and the sea area near the offshore booster station, positioning and navigation are carried out on the wind turbine blades or the ship.
Preferably, the positioning and navigating the fan blade or the ship comprises:
the cloud platform is used for increasing the stability of the load of the unmanned aerial vehicle;
a laser radar carried on the unmanned aerial vehicle measures the fan or the ship;
the camera locks a photographing target;
the distance between the unmanned aerial vehicle and the fan blade is 10m, and the unmanned aerial vehicle flies along two sides of the blade respectively; or the unmanned aerial vehicle flies along the ship body respectively with a clearance of 10m above the ship.
As a preferred scheme, the performing fault analysis processing on the image through a deep learning algorithm includes:
carrying out image recognition on the defect type of the fan blade;
capturing and identifying images of ship anchoring, impact wind turbine or offshore booster station foundation;
further comprising:
and controlling the unmanned aerial vehicle to carry out real-time video transmission and video recording, and issuing a fan blade fault and a dangerous ship tracking report after identifying the fault.
Preferably, the fan blade defect types include: the blade gel coat comes off, damages, transverse cracks and greasy dirt.
Preferably, the size of the automatic airport is 1.55m by 1.55m, the airport is installed by using fixing bolts, and a 3.4m by 1.7m open area is arranged on site; setting 220V alternating current on site; a wired network with more than 10Mbps requires uplink and downlink equivalence in bandwidth; an automated weather station is located at a distance >2 meters from the automated airport.
Compared with the prior art, the embodiment of the invention has the following beneficial effects:
1, complete field automation, and the unmanned aerial vehicle can realize automatic taking off and landing, flying and energy source supplement; the problem that the multi-rotor unmanned aerial vehicle has insufficient endurance time and cannot reach field operation is solved, and the trouble that personnel go to the field operation is avoided;
2, the unmanned aerial vehicle intelligently and automatically plans a flight path, judges the state of a fan, and solves the problem that the unmanned aerial vehicle corresponds to the initial relative coordinate relationship of the fan and the fan blade, wherein the state comprises the course angle and the rotating position of the fan; meanwhile, sea ships near the offshore booster station can be patrolled and examined, and dangerous ships entering the offshore wind electric field area by mistake are identified.
3, the unmanned aerial vehicle can automatically plan a blade inspection flight strategy according to the position of the blade, so that the inspection shooting result of the unmanned aerial vehicle meets the requirements of standard and stability;
and 4, real-time detection can be performed through a deep learning method, a defect target is found and marked, a screenshot of a new defect target is stored, a manual auditing function is provided, and a fan and sea area patrol report can be automatically generated.
Drawings
FIG. 1: the schematic diagram of the frame of the inspection scheme of the unmanned aerial vehicle in the offshore wind farm in the embodiment of the invention;
FIG. 2 is a schematic diagram: the invention provides a topological schematic diagram of an inspection scheme system of an unmanned aerial vehicle of an offshore wind farm in an embodiment of the invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
Referring to fig. 1 and 2, a preferred embodiment of the present invention provides a method for inspecting an unmanned aerial vehicle in an offshore wind farm, including: an automatic airport is deployed on the roof of the offshore booster station, and the unmanned aerial vehicle is remotely controlled through a network to take off and land, replace batteries and perform task operation in a full-automatic mode; controlling an unmanned aerial vehicle carrying a zoom camera and a laser radar to take off from the automatic airport, and carrying out full-autonomous path planning and image shooting on a fan and a sea area near a marine booster station; and acquiring images of the fan blade and the sea area shot by the unmanned aerial vehicle, and performing fault analysis processing on the images through a deep learning algorithm to identify a fan crack and a marine vessel.
In this embodiment, the unmanned aerial vehicle performs fully autonomous path planning, including: sequentially judging whether weather and wind conditions of the offshore booster station meet safe operation conditions, if so, simultaneously judging whether the unmanned aerial vehicle battery is electrified, and if not, controlling to change the battery and charging the battery; starting an automatic inspection program and planning an inspection route; the unmanned aerial vehicle flies above a designated fan or a designated ship, and when the unmanned aerial vehicle is automatically lifted to a designated height, the unmanned aerial vehicle automatically rises and calculates the central height of a fan hub; the unmanned aerial vehicle automatically inspects each blade, and each blade inspects a plurality of paths; after the flight of the air route is finished, the unmanned aerial vehicle returns to the automatic airport of the offshore booster station, namely, the flying spot is over, the cabin door of the automatic airport is controlled to be opened, the unmanned aerial vehicle automatically descends, and the inspection task is finished.
In this embodiment, when unmanned aerial vehicle rises to the wheel hub center automatically, confirms whether there is the deviation in wheel hub center and unmanned aerial vehicle position, if there is, then finely tune unmanned aerial vehicle, with wheel hub center adjustment back, continue to patrol and examine the task.
In this embodiment, each blade patrols 4 paths, and a single blade is shot according to 4 areas of the front edge, the rear edge, the windward side and the leeward side.
In this embodiment, the processing of the image acquired by the unmanned aerial vehicle includes: acquiring a target image with the resolution of 1mm x 3mm shot by an unmanned aerial vehicle; splicing 4 regions of a single blade in the target image according to the front edge, the rear edge, the windward side and the leeward side into 4 overall large images through data processing; and each path is independently spliced into a large graph, and any damage position on the blade is positioned by means of the large graph and the flight log.
In this embodiment, before the unmanned aerial vehicle captures images of the sea area near the wind turbine and the offshore booster station, positioning and navigation are further performed on the wind turbine blade or the ship.
In this embodiment, the positioning and navigating the fan blade or the ship includes: the cloud platform is used for increasing the stability of the load of the unmanned aerial vehicle; a laser radar carried on the unmanned aerial vehicle measures the fan or the ship; the camera locks a photographing target; the distance between the unmanned aerial vehicle and the fan blade is 10m, and the unmanned aerial vehicle flies along two sides of the blade respectively; or the unmanned aerial vehicle flies along the ship body with a clearance of 10m above the ship.
In this embodiment, the performing fault analysis processing on the image through a deep learning algorithm includes: carrying out image recognition on the defect type of the fan blade; capturing and identifying images of ship anchoring, impact wind turbine or offshore booster station foundation; further comprising: and controlling the unmanned aerial vehicle to carry out real-time video transmission and video recording, and sending out a fan blade fault and a dangerous ship tracking report after identifying the fault.
In this embodiment, the fan blade defect type includes: the blade gel coat comes off, damages, transverse cracks and greasy dirt.
In the embodiment, the size of the automatic airport is 1.55m by 1.55m, the airport is installed by using fixing bolts, and a 3.4m by 1.7m open area is arranged on site; setting 220V alternating current on site; a wired network with more than 10Mbps requires uplink and downlink equivalence in bandwidth; an automated weather station is located at a distance >2 meters from the automated airport.
The present invention will be described in detail with reference to specific examples.
(1) Data acquisition
1, unmanned aerial vehicle inspection/deployment: and background personnel of the onshore centralized control center issue instructions to the unmanned aerial vehicle of the automatic airport. After receiving the command, the unmanned aerial vehicle can fly to a designated windmill position, check the equipment state of the unmanned aerial vehicle and select a proper flying starting point to unfold the unmanned aerial vehicle;
and 2, taking off: and the operator of the onshore centralized control center clicks the take-off button of the ground station operation interface, and the unmanned aerial vehicle takes off automatically.
And 3, operation: unmanned aerial vehicle will fly around the windmill and shoot blade outward appearance picture according to calculating the route under the assistance of visual calculation after taking off, and whole process personnel need not to operate the aircraft, only need observe supplementary unmanned aerial vehicle cloud platform and shoot the angle.
And 4, falling: after the operation is finished, the unmanned aerial vehicle automatically returns to the reachable automatic airport and automatically lands.
(2) Processing of images
1 st, the photographs taken can resolve to 1mm by 3mm targets. The clarity of the collected data can reach the data detail capable of distinguishing 1mm by 3 mm. Provide basis for the user to distinguish the damage of the leaf.
The blade is taken as an example 2. The single blade shoots according to 4 areas of the front edge, the rear edge, the windward side and the leeward side, and no obvious blind area exists. The shot pictures can be spliced into 4 integral large pictures through data processing. The acquisition system is designed to shoot according to four paths of each blade, so that the integrity of the shooting blades is ensured. Each path can be individually spliced into a large graph. And meanwhile, any damage position on the blade can be positioned by means of a large graph and a flight log.
An automatic airport laying and planning scheme for an offshore wind farm: (1) the requirement of the automatic airport is that the size of the airport is 1.55m by 1.55m, and the airport is installed by using a fixing bolt. An open area of 3.4m multiplied by 1.7m (the automatic airport door needs to occupy space after being opened) needs to be provided on site; providing 220V alternating current on site (which can be powered by photovoltaic); a wired network with more than 10Mbps requires uplink and downlink equivalence (recommendation) of bandwidth; setting an automatic weather station at a distance of more than 2 meters from an automatic airport; (2) the unmanned aerial vehicle flying operation time is 30 minutes, the single fan inspection time is 20 minutes, the unmanned aerial vehicle inspection has the breakpoint continuous shooting capability, in order to improve the inspection coverage range, the unmanned aerial vehicle operation can be divided into 4 steps, the single step is 5 minutes, the maximum coverage radius of the unmanned aerial vehicle is 5km, the operation period is considered to be shortened, and the optimal coverage radius is 2 km.
Automatic flight and shooting flow are patrolled and examined to offshore wind turbine electric field unmanned aerial vehicle:
(1) the wind machine is stopped or dangerous ships break into the offshore wind farm by mistake: a. the tip of a fan blade with the length of 40m in the running process of a fan is rotated at the speed of 80m/s, the performance of the existing unmanned aerial vehicle cannot follow shooting, and meanwhile, if the fan is in a high-speed rotation state, focusing is difficult, so that the imaging effect is poor, and the accuracy of video classification processing is influenced; b. when the unmanned aerial vehicle is in a shutdown state or the fan rotates at a low speed, the unmanned aerial vehicle can track and shoot. c. Dangerous ships break into the offshore wind power station by mistake, and when the unmanned aerial vehicle breaks down or catches fish, the unmanned aerial vehicle can track and shoot.
(2) Planning a flight path; a. background personnel of a land centralized control center enter unmanned aerial vehicle inspection operation software; b. sequentially confirming whether the weather and the wind power condition of the offshore booster station meet safe operation conditions or not according to software prompt; meanwhile, whether the battery of the unmanned aerial vehicle of the automatic airport is electrified or not is confirmed, and if not, the battery can be automatically changed in the automatic airport. The automatic airport can charge the battery; c. after safety is confirmed, an automatic inspection program is started, and the back-end processing software plans an inspection route; d. the unmanned aerial vehicle flies above a designated fan or above a designated ship. After the unmanned aerial vehicle is automatically lifted to a specified height, the unmanned aerial vehicle automatically rises and calculates the central height of the hub of the fan; e. when unmanned aerial vehicle rises to the wheel hub center automatically, system operator will need to confirm on patrolling and examining unmanned aerial vehicle ground control software patrolling and examining. If the hub center seen in the software deviates from the prompt box, an operator needs to finely adjust the unmanned aerial vehicle through the software, and after the hub center is adjusted into the prompt box, the routing inspection task is continued; f. the unmanned aerial vehicle automatically inspects each blade according to the mode that the blade root of the front edge is changed to the blade tip, the blade tip of the rear edge is changed to the blade root, the windward side is changed to the leeward side, the blade root of the rear edge is changed to the blade tip, and the blade tip of the front edge is changed to the blade root; each blade has 4 paths, and each windmill has 12 paths; g. at the starting point of each path, an operator of a land centralized control center is required to confirm whether the blades can be seen in the picture, and if so, the detection is continued; if not, the operator needs to finely adjust the unmanned aerial vehicle through the software button and then continues the routing inspection task; and h.after the 12 flight routes finish flying, the unmanned aerial vehicle automatically returns to the automatic airport of the offshore booster station, namely, the flying starting point is overhead. And opening the cabin door of the automatic airport, automatically descending the unmanned aerial vehicle, and finishing the inspection task. And finally, closing the cabin door of the automatic airport, and replacing the battery of the unmanned aerial vehicle.
(3) Fan blade or vessel positioning navigation: a. the cloud platform is used for increasing the stability of the load of the unmanned aerial vehicle; b. the laser radar measures the fan or the ship; c. the camera locks a photographing target; d. the distance between the unmanned aerial vehicle and the fan blade is 10m, and the unmanned aerial vehicle flies along two sides of the blade respectively; or the unmanned aerial vehicle flies along the ship body respectively with a clearance of 10m above the ship.
(4) Fault identification and processing: a. under the condition of self-learning of the system, the defect types of the fan blade are supported to carry out image recognition, such as gel coat falling, damage, transverse crack, oil stain and the like; the clarity of the collected data can reach the data detail capable of distinguishing 1mm by 3 mm. Providing basis for identifying damage of the leaves; taking the blade as an example, a single blade shoots 4 areas according to the front edge, the rear edge, the windward side and the leeward side, and no obvious blind area exists. The shot pictures can be spliced into 4 integral large pictures through data processing; the acquisition system is designed to shoot according to four paths of each blade so as to ensure the integrity of the shot blades; each path can be spliced into a large graph independently, and any damage position on the blade can be positioned by means of the large graph and the flight log; b. supporting image capture and identification of ship anchoring, impact wind turbine or offshore booster station foundation; c. the system supports real-time video transmission and recording, and can provide tracking reports of fan blade faults and dangerous ships.
The inspection of the offshore wind farm unmanned aerial vehicle comprises three automation of field automation, inspection flight automation and image analysis automation. Automatic airports are arranged on the roofs of the offshore booster stations and on partial fan foundation platforms, so that the unmanned aerial vehicle can fully cover the whole offshore wind power field sea area. The automation of the whole flow of fan inspection can be realized by the automatic airport and the unmanned aerial vehicle. Through this set of unmanned aerial vehicle system of patrolling and examining of collocation, not only can realize that whole offshore wind farm sea area is automatic to be patrol, but also realize the fault identification of offshore wind turbine blade.
The above-mentioned embodiments are provided to further explain the objects, technical solutions and advantages of the present invention in detail, and it should be understood that the above-mentioned embodiments are only examples of the present invention and are not intended to limit the scope of the present invention. It should be understood that any modifications, equivalents, improvements and the like, which come within the spirit and principle of the invention, may occur to those skilled in the art and are intended to be included within the scope of the invention.
Claims (6)
1. An inspection method for an unmanned aerial vehicle in an offshore wind plant is characterized by comprising the following steps:
an automatic airport is deployed on the roof of the offshore booster station, and the unmanned aerial vehicle is remotely controlled through a network to take off and land, replace batteries and perform task operation in a full-automatic mode;
controlling an unmanned aerial vehicle carrying a zoom camera and a laser radar to take off from the automatic airport, and carrying out full-autonomous path planning and image shooting on a fan and a sea area near a marine booster station;
acquiring images of the fan blade and the sea area shot by the unmanned aerial vehicle, and performing fault analysis processing on the images through a deep learning algorithm to identify a fan crack and a marine vessel; the image of the sea area comprises a ship anchoring image and a ship impact fan image;
wherein, unmanned aerial vehicle carries out full autonomic path planning, includes:
sequentially judging whether weather and wind conditions of the offshore booster station meet safe operation conditions, if so, simultaneously judging whether the unmanned aerial vehicle battery is electrified, and if not, controlling to change the battery and charging the battery;
starting an automatic inspection program and planning an inspection route;
the unmanned aerial vehicle flies above a designated fan or a designated ship, and when the unmanned aerial vehicle is automatically lifted to a designated height, the unmanned aerial vehicle automatically rises and calculates the central height of a fan hub;
the unmanned aerial vehicle automatically inspects each blade, and each blade inspects a plurality of paths;
after the flight of the flight path is finished, the unmanned aerial vehicle returns to an automatic airport of the offshore booster station, namely, the upper part of a flying starting point, the cabin door of the automatic airport is controlled to be opened, the unmanned aerial vehicle automatically lands, and the inspection task is finished;
when the unmanned aerial vehicle automatically rises to the hub center, whether the hub center and the unmanned aerial vehicle are deviated or not is confirmed, if yes, the unmanned aerial vehicle is finely adjusted, and after the hub center is adjusted, the routing inspection task is continued;
4 routes are patrolled and examined to every blade, and single blade is shot according to 4 regions of leading edge, trailing edge, windward side, leeward side, specifically includes: the unmanned aerial vehicle automatically inspects each blade according to the mode that the blade root of the front edge is changed to the blade tip, the blade tip of the rear edge is changed to the blade root, the windward side is changed to the leeward side, the blade root of the rear edge is changed to the blade tip, and the blade tip of the front edge is changed to the blade root; each windmill patrols 12 paths, at the starting point of each path, an operator of a land centralized control center is required to confirm whether the blades can be seen in the picture, and if so, the detection is continued; if not, the operator needs to finely adjust the unmanned aerial vehicle through the software button and then continues the routing inspection task;
the image to unmanned aerial vehicle acquirement is handled, include:
acquiring a target image with the resolution of 1mm x 3mm shot by an unmanned aerial vehicle;
splicing the single blade in the target image into 4 overall large images through data processing according to 4 areas of a front edge, a rear edge, a windward side and a leeward side;
and each path is independently spliced into a large graph, and any damage position on the blade is positioned by means of the large graph and the flight log.
2. The offshore wind farm unmanned aerial vehicle inspection method according to claim 1, wherein before the unmanned aerial vehicle captures images of the wind turbine and the sea area near the offshore booster station, positioning and navigation are performed on the wind turbine blades or the ship.
3. The offshore wind farm unmanned aerial vehicle inspection method according to claim 2, wherein the positioning and navigation of the fan blades or the ship comprises:
the cloud platform is used for increasing the stability of the load of the unmanned aerial vehicle;
a laser radar carried on the unmanned aerial vehicle measures the fan or the ship;
the camera locks a photographing target;
the distance between the unmanned aerial vehicle and the fan blade is 10m, and the unmanned aerial vehicle flies along two sides of the blade respectively; or the unmanned aerial vehicle flies along the ship body respectively with a clearance of 10m above the ship.
4. The offshore wind farm unmanned aerial vehicle inspection method according to claim 1, wherein the fault analysis processing of the image through a deep learning algorithm comprises:
carrying out image recognition on the defect type of the fan blade;
capturing and identifying images of ship anchoring, impact wind turbine or offshore booster station foundation;
further comprising:
and controlling the unmanned aerial vehicle to carry out real-time video transmission and video recording, and issuing a fan blade fault and a dangerous ship tracking report after identifying the fault.
5. The offshore wind farm unmanned aerial vehicle inspection method of claim 4, wherein the fan blade defect types comprise: the blade gel coat comes off, is damaged, has transverse cracks and is greasy.
6. The offshore wind farm unmanned aerial vehicle inspection method according to claim 1, wherein the size of the automatic airport is 1.55m by 1.55m, the airport is installed by using fixing bolts, and an open area of 3.4m by 1.7m is arranged on site; setting 220V alternating current on site; in a wired network with more than 10Mbps, the bandwidth requires uplink and downlink equivalence; an automated weather station is located at a distance >2 meters from the automated airport.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910514880.7A CN110282143B (en) | 2019-06-14 | 2019-06-14 | Inspection method for offshore wind farm unmanned aerial vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910514880.7A CN110282143B (en) | 2019-06-14 | 2019-06-14 | Inspection method for offshore wind farm unmanned aerial vehicle |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110282143A CN110282143A (en) | 2019-09-27 |
| CN110282143B true CN110282143B (en) | 2022-09-27 |
Family
ID=68003999
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910514880.7A Active CN110282143B (en) | 2019-06-14 | 2019-06-14 | Inspection method for offshore wind farm unmanned aerial vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110282143B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112801432A (en) * | 2019-10-25 | 2021-05-14 | 北京国电思达科技有限公司 | Fan unit blade intelligent inspection system and fan unit blade inspection method |
| CN111026156A (en) * | 2019-12-17 | 2020-04-17 | 北京京东乾石科技有限公司 | Inspection system, method, control device, equipment and storage medium |
| JP2023501187A (en) * | 2019-10-28 | 2023-01-18 | ベイジン・ジンドン・チアンシ・テクノロジー・カンパニー・リミテッド | Unmanned Aerial Airports, Unmanned Aerial Systems, and Unmanned Aerial Cruise Systems |
| CN110879601B (en) * | 2019-12-06 | 2021-05-18 | 电子科技大学 | Unmanned aerial vehicle inspection method for unknown fan structure |
| CN112360699A (en) * | 2020-10-22 | 2021-02-12 | 华能大理风力发电有限公司 | Intelligent inspection and diagnosis analysis method for blades of full-automatic wind generating set |
| CN112346476B (en) * | 2020-11-06 | 2021-12-28 | 南方电网电力科技股份有限公司 | Automatic unmanned aerial vehicle inspection system and method |
| CN112506214B (en) * | 2020-11-16 | 2022-12-30 | 天津航天中为数据系统科技有限公司 | Operation flow of unmanned aerial vehicle autonomous fan inspection system |
| CN112947511A (en) * | 2021-01-25 | 2021-06-11 | 北京京能能源技术研究有限责任公司 | Method for inspecting fan blade by unmanned aerial vehicle |
| CN113077561A (en) * | 2021-03-29 | 2021-07-06 | 北京智盟信通科技有限公司 | Intelligent inspection system for unmanned aerial vehicle |
| CN113759960A (en) * | 2021-07-26 | 2021-12-07 | 青海黄河风力发电有限责任公司 | Unmanned aerial vehicle-based fan blade and tower barrel inspection identification system and method |
| CN113485453A (en) * | 2021-08-20 | 2021-10-08 | 中国华能集团清洁能源技术研究院有限公司 | Method and device for generating inspection flight path of offshore unmanned aerial vehicle and unmanned aerial vehicle |
| CN113942616B (en) * | 2021-09-30 | 2023-04-18 | 华能盐城大丰新能源发电有限责任公司 | Inspection mechanism and method for offshore wind farm |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102628425A (en) * | 2011-02-04 | 2012-08-08 | 通用电气公司 | Method and system for wind turbine inspection |
| CN203845022U (en) * | 2014-04-28 | 2014-09-24 | 赵子滨 | Automation platform for providing service for routing inspection unmanned plane |
| CN106762451A (en) * | 2016-12-05 | 2017-05-31 | 北京金风科创风电设备有限公司 | Fan blade damage detection method, device and system based on unmanned aerial vehicle |
| CN107656537A (en) * | 2016-07-25 | 2018-02-02 | 新疆金风科技股份有限公司 | Unmanned plane route planning method and device, fan blade inspection method and system based on unmanned plane |
| CN207600967U (en) * | 2017-11-29 | 2018-07-10 | 华北电力大学（保定） | A kind of device for wind power plant blade surface defects detection |
| CN109409283A (en) * | 2018-10-24 | 2019-03-01 | 深圳市锦润防务科技有限公司 | A kind of method, system and the storage medium of surface vessel tracking and monitoring |
| WO2019048721A1 (en) * | 2017-09-06 | 2019-03-14 | Alerion Technologies, S.L. | Method and device of autonomous navigation |
| CN109720593A (en) * | 2018-12-28 | 2019-05-07 | 上海扩博智能技术有限公司 | Blade tracing detection carry device, unmanned plane and method based on laser facula |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102011017564B4 (en) * | 2011-04-26 | 2017-02-16 | Airbus Defence and Space GmbH | Method and system for inspecting a surface for material defects |
| DE102013113326A1 (en) * | 2013-12-02 | 2015-06-03 | Hgz Patentvermarktungs Gmbh | Method for optical detection of a wind turbine for testing purposes with the aid of an aircraft |
-
2019
- 2019-06-14 CN CN201910514880.7A patent/CN110282143B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102628425A (en) * | 2011-02-04 | 2012-08-08 | 通用电气公司 | Method and system for wind turbine inspection |
| CN203845022U (en) * | 2014-04-28 | 2014-09-24 | 赵子滨 | Automation platform for providing service for routing inspection unmanned plane |
| CN107656537A (en) * | 2016-07-25 | 2018-02-02 | 新疆金风科技股份有限公司 | Unmanned plane route planning method and device, fan blade inspection method and system based on unmanned plane |
| CN106762451A (en) * | 2016-12-05 | 2017-05-31 | 北京金风科创风电设备有限公司 | Fan blade damage detection method, device and system based on unmanned aerial vehicle |
| WO2019048721A1 (en) * | 2017-09-06 | 2019-03-14 | Alerion Technologies, S.L. | Method and device of autonomous navigation |
| CN207600967U (en) * | 2017-11-29 | 2018-07-10 | 华北电力大学（保定） | A kind of device for wind power plant blade surface defects detection |
| CN109409283A (en) * | 2018-10-24 | 2019-03-01 | 深圳市锦润防务科技有限公司 | A kind of method, system and the storage medium of surface vessel tracking and monitoring |
| CN109720593A (en) * | 2018-12-28 | 2019-05-07 | 上海扩博智能技术有限公司 | Blade tracing detection carry device, unmanned plane and method based on laser facula |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110282143A (en) | 2019-09-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110282143B (en) | Inspection method for offshore wind farm unmanned aerial vehicle | |
| US11549492B2 (en) | Method of condition monitoring one or more wind turbines and parts thereof and performing instant alarm when needed | |
| CN207600967U (en) | A kind of device for wind power plant blade surface defects detection | |
| CN110603379B (en) | Inspection tool control device for wind power equipment inspection tool | |
| CN106762451A (en) | Fan blade damage detection method, device and system based on unmanned aerial vehicle | |
| CN111459189A (en) | Offshore resident offshore wind power unmanned aerial vehicle full-automatic inspection system based on automatic nest | |
| CN205620817U (en) | Independently unmanned aerial vehicle patrols and examines fan blade system | |
| CN112506214B (en) | Operation flow of unmanned aerial vehicle autonomous fan inspection system | |
| WO2019158171A1 (en) | Systems and vehicles for managing wind turbine systems | |
| CN112925337B (en) | Automatic inspection method for multi-rotor unmanned aerial vehicle with metal structure of large crane | |
| CN112684806A (en) | Electric power inspection unmanned aerial vehicle system based on dual obstacle avoidance and intelligent identification | |
| CN115586789A (en) | Vision-based method for confirming and inspecting suspension point of wind driven generator inspection unmanned aerial vehicle | |
| CN212060982U (en) | Offshore resident offshore wind power unmanned aerial vehicle full-autonomous inspection system | |
| CN112960132A (en) | Distributed shared nest and unmanned aerial vehicle inspection method for power line of distributed shared nest | |
| CN114757454B (en) | Unmanned aerial vehicle inspection route generation method, device and equipment of wind driven generator | |
| CN115326075A (en) | Path planning method for realizing wind field global automatic inspection based on unmanned aerial vehicle | |
| LU504712B1 (en) | Intelligent inspection method for fan blade | |
| CN106218910A (en) | Gather the system of high-voltage electric power circuit screen of trees defect, method and control terminal | |
| CN115421503B (en) | Unmanned aerial vehicle inspection system for bridge | |
| CN217515351U (en) | Unmanned ship inspection system suitable for offshore wind power plant | |
| CN111045452A (en) | Power line inspection method based on deep learning | |
| KR102541382B1 (en) | Apparatus for controlling wind power generator and method for inspecting the blades of wind power generator | |
| CN112758323B (en) | Unmanned aerial vehicle with follow-up illumination function for bridge detection | |
| Su et al. | Research on automatic route planning algorithm for wind turbine inspection | |
| Su et al. | A Path Planning Method for UAV Inspection of Wind Turbines |
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 |