Unmanned aerial vehicle wind turbine inspection systems and methods
Methods, systems and apparatus, including computer programs encoded on computer storage media for an unmanned aerial vehicle (UAV) wind turbine inspection system. One of the methods includes obtaining first sensor information by an unmanned aerial vehicle (UAV), the first sensor information describing physical aspects of a wind turbine, including one or more blades of the wind turbine. An orientation of the blades of the wind turbine are determined based on the obtained first sensor information. A flight pattern for the UAV to inspect the blades of the wind turbine is determined, the flight pattern being based on the determined orientation of the blades. Each of the blades of the wind turbine is inspected by the UAV according to the determined flight pattern, the inspection including obtaining second sensor information describing the blades of the wind turbine.
1. A system, comprising:
an unmanned aerial vehicle including one or more computer readable storage media storing instructions and one or more processors configured to execute the instructions to:
determine an orientation of multiple blades of a wind turbine based on indications of one or more aspects of the wind turbine, wherein the orientation comprises an angle associated with an offset from a particular position;
determine a flight plan for inspecting the multiple blades based on the orientation of the multiple blades; and
inspect, subsequent to determining the flight plan, the multiple blades according to the flight plan without moving any of the multiple blades by, for each blade of the multiple blades, obtaining sensor information while navigating along the blade from one or more angles relative to an edge of the blade.
2. The system of claim 1 , further comprising:
a user device in communication with the unmanned aerial vehicle and configured to:
determine the indications of the one or more aspects of the wind turbine based on input received at the user device; and
transmit the indications of the one or more aspects of the wind turbine to the unmanned aerial vehicle.
3. The system of claim 2 , wherein the input received at the user device corresponds to one or more of a selection of a type of the wind turbine, geometry information associated with the wind turbine, or a stand-off distance for the wind turbine.
4. The system of claim 2 , wherein the sensor information includes one or more images, wherein the one or more processors are configured to execute the instructions to:
transmit the one or more images for display at the user device.
5. The system of claim 1 , wherein, to determine the orientation of the multiple blades of the wind turbine, the one or more processors are configured to execute the instructions to:
generate a point cloud representing the wind turbine based on output of a distance sensor that measures a distance from the unmanned aerial vehicle to the wind turbine; and
determine the orientation of the multiple blades of the wind turbine based on the point cloud.
6. The system of claim 1 , wherein, to determine the orientation of the multiple blades of the wind turbine, the one or more processors are configured to execute the instructions to:
determine a pose of a camera of the unmanned aerial vehicle for each of one or more images of the wind turbine captured using the camera; and
determine the orientation of the multiple blades of the wind turbine based on the pose determined for each of the one or more images.
7. The system of claim 1 , wherein, to determine the orientation of the multiple blades of the wind turbine, the one or more processors are configured to execute the instructions to:
generate a point cloud representing the wind turbine based on one or more images of a rotor hub of the wind turbine; and
determine the orientation of the multiple blades of the wind turbine based on the point cloud.
8. A non-transitory computer storage medium storing instructions operable to cause one or more processors to perform operations comprising:
determining an orientation of multiple blades of a wind turbine, wherein the orientation comprises an angle associated with an offset from a particular position; and
determining a flight plan for inspecting the multiple blades based on the orientation of the multiple blades, wherein the flight plan configures an unmanned aerial vehicle to inspect the multiple blades without moving any of the multiple blades by, for each blade of the multiple blades, causing the unmanned aerial vehicle to navigate along the blade from one or more angles relative to a leading edge of the blade.
9. The non-transitory computer storage medium of claim 8 , wherein the orientation of the multiple blades of the wind turbine are determined based on geometry information associated with the wind turbine.
10. The non-transitory computer storage medium of claim 8 , wherein, for each blade of the multiple blades, the flight plan configures the unmanned aerial vehicle to navigate along the blade for a fixed distance between a proximal end of the blade to a distal end of the blade.
11. The non-transitory computer storage medium of claim 8 , wherein, for each blade of the multiple blades, the flight plan configures the unmanned aerial vehicle to remain at one or more distances from the blade while navigating along the blade.
12. A method, comprising:
determining a flight plan for an unmanned aerial vehicle to inspect multiple blades of a wind turbine; and
inspecting the multiple blades according to the flight plan without moving any of the multiple blades by, for each blade of the multiple blades, the unmanned aerial vehicle obtaining sensor information while navigating along the blade from one or more angles relative to a leading edge of the blade.
13. The method of claim 12 , wherein the flight plan is determined based on orientations of the multiple blades.
14. The method of claim 13 , wherein the orientations of the multiple blades are determined based on output of a planar distance sensor of the unmanned aerial vehicle activated while the unmanned aerial vehicle ascends vertically from a take-off location.
15. The method of claim 13 , wherein the orientations of the multiple blades are determined based on pose information associated with one or more images captured using a camera of the unmanned aerial vehicle.
16. The method of claim 13 , wherein the orientations of the multiple blades are determined based on images of a rotor hub of the wind turbine.
17. The method of claim 13 , wherein the orientations of the multiple blades are determined based on an initial altitude of the multiple blades and a set distance between each of the multiple blades.
18. The method of claim 13 , wherein information indicating the orientations of the multiple blades is obtained at the unmanned aerial vehicle from a user device in communication with the unmanned aerial vehicle.
19. The method of claim 12 , wherein the unmanned aerial vehicle inspects the multiple blades based on a stand-off distance determined based on one or both of wind conditions or a speed of the multiple blades.
20. The method of claim 12 , the method comprising:
assigning an identifier associated with the sensor information to a blade of the multiple blades; and
monitoring the blade for degradation based on the identifier and second sensor information later obtained for the wind turbine.