Systems and methods for inspecting wind turbines using unmanned autonomous technology

Abstract

A system for inspecting an offshore wind farm having one or more wind turbines includes an unmanned autonomous vessel. The unmanned autonomous vessel includes a positioning module for navigating the unmanned autonomous vessel to a target wind turbine in the offshore wind farm and positioning the unmanned autonomous vessel near the target wind turbine, an onboard data acquisition module with one or more sensors for collecting local data regarding the health of the target wind turbine, and a controller with at least one processor. The processor is configured to perform a number of operations, including, for example, receiving the local data from the one or more sensors and forwarding the local data to a remote command center via a satellite communication link.

Description

[Technical Field]

[0001] The present subject matter relates generally to wind turbines, and more particularly to systems and methods for inspecting wind turbines, such as offshore wind turbines, using unmanned autonomous technology. [Background technology]

[0002] Wind power is considered one of the cleanest and most environmentally friendly energy sources currently available, and wind turbines have been gaining increasing attention in this regard. Modern wind turbines typically include a tower, a generator, a gearbox, a nacelle, and one or more rotor blades. The rotor blades capture the kinetic energy of the wind using the well-known airfoil principle. For example, rotor blades typically have an airfoil cross-sectional profile such that during operation, air flows over the blade, creating a pressure difference between the sides. As a result, a lift force acts on the blade, directed from the pressure side to the suction side. The lift force generates torque on the main rotor shaft, which is geared to a generator for producing electricity.

[0003] Certain wind turbines are located in a common geographic location and may be commonly referred to as wind farms. Wind farms can be located on land or offshore. For offshore wind farms in particular, completing inspection and maintenance can be technically and economically challenging given their deployment environment (i.e., the ocean). Additionally, applying traditional inspection and detection techniques used for onshore wind turbines to offshore wind turbines can also pose significant challenges due to varying sea conditions.

[0004] SUMMARY Accordingly, the present disclosure is directed to systems and methods for providing improved inspection of wind power generation platforms, such as offshore wind farms, that address the above-mentioned problems. [Prior art documents] [Patent documents]

[0005] [Patent Document 1] Chinese Patent Application Publication No. 114721405 Summary of the Invention

[0006] Aspects and advantages of the present invention will be set forth in part in the description that follows, or may be obvious from the description, or may be learned by practice of the invention.

[0007] In one aspect, the present disclosure is directed to a system for inspecting an offshore wind farm having one or more wind turbines, the system including an unmanned autonomous vessel. The unmanned autonomous vessel includes: a positioning module for navigating the unmanned autonomous vessel to a target wind turbine in the offshore wind farm and positioning the unmanned autonomous vessel near the target wind turbine; an onboard data acquisition module including one or more sensors for collecting local data regarding the health of the target wind turbine; and a controller including at least one processor. The processor is configured to perform a number of operations, including, for example, receiving the local data from the one or more sensors and forwarding the local data to a remote command center via a satellite communication link.

[0008] In another aspect, the present disclosure is directed to a method for inspecting an offshore wind farm having one or more wind turbines. The method includes navigating an unmanned autonomous vessel to a target wind turbine at the offshore wind farm via a positioning module of the unmanned autonomous vessel. The method also includes positioning the unmanned autonomous vessel near the target wind turbine via the positioning module. Further, the method includes collecting local data regarding the health of the target wind turbine in the wind farm via an onboard data acquisition module having one or more sensors. Additionally, the method includes transmitting the local data to a remote command center via a satellite communication link.

[0009] These and other features, aspects, and advantages of the present invention will become better understood with reference to the following description and appended claims. The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and, together with the description, serve to explain the principles of the invention.

[0010] A full and enabling disclosure of this invention, including the best mode thereof, directed to one of ordinary skill in the art, is set forth in this specification, which makes reference to the accompanying drawings, in which: [Brief explanation of the drawings]

[0011] [Figure 1] 1 is a perspective view of an embodiment of a wind turbine according to the present disclosure; FIG. [Figure 2] FIG. 1 is a perspective interior view of an embodiment of a nacelle of a wind turbine according to the present disclosure. [Figure 3A] 1 is a schematic diagram of an embodiment of a system for inspecting one or more wind turbines in a wind farm, such as an offshore wind farm, according to the present disclosure. [Figure 3B] 1 is a schematic diagram of an embodiment of a system for inspecting one or more wind turbines in a wind farm, such as an offshore wind farm, according to the present disclosure. [Figure 4A] 1 is a schematic diagram of one embodiment of various components of a system for inspecting one or more wind turbines in a wind farm, such as an offshore wind farm, in accordance with the present disclosure. [Figure 4B] 1 is a schematic diagram of one embodiment of various components of a system for inspecting one or more wind turbines in a wind farm, such as an offshore wind farm, in accordance with the present disclosure. [Figure 4C] 1 is a schematic diagram of one embodiment of various components of a system for inspecting one or more wind turbines in a wind farm, such as an offshore wind farm, in accordance with the present disclosure. [Figure 5] 1 is a schematic diagram of an embodiment of a system for inspecting one or more wind turbines in an offshore wind farm according to the present disclosure. [Figure 6]1 is a schematic diagram of another embodiment of a system for inspecting one or more wind turbines in an offshore wind farm in accordance with the present disclosure. [Figure 7] FIG. 1 is a schematic diagram of one embodiment of operating a system for inspecting one or more wind turbines in an offshore wind farm according to the present disclosure, particularly illustrating a system having two cameras. [Figure 8] FIG. 10 is a schematic diagram of another embodiment of operating a system for inspecting one or more wind turbines in an offshore wind farm according to the present disclosure, particularly illustrating a system having two cameras. [Figure 9] FIG. 1 is a schematic diagram of one embodiment of operating a system for inspecting one or more wind turbines in an offshore wind farm according to the present disclosure, particularly illustrating a system having one camera. [Figure 10] FIG. 1 is a schematic diagram of an embodiment of a positioning module of a system for inspecting one or more wind turbines in an offshore wind farm in accordance with the present disclosure. [Figure 11] FIG. 1 is a schematic diagram of an embodiment of a dynamic positioning module of a positioning module of a system for inspecting one or more wind turbines in an offshore wind farm in accordance with the present disclosure. [Figure 12] FIG. 1 is a schematic diagram of an embodiment of a fault-tolerant positioning module of a positioning module of a system for inspecting one or more wind turbines in an offshore wind farm in accordance with the present disclosure. [Figure 13] 1 is a flow diagram of an embodiment of a method for inspecting one or more wind turbines in an offshore wind farm according to the present disclosure. [Figure 14] FIG. 2 is a block diagram of an embodiment of a controller for a wind turbine according to the present disclosure. DETAILED DESCRIPTION OF THE INVENTION

[0012] Reference will now be made in detail to the embodiments of the invention, one or more examples of which are illustrated in the drawings. Each example is provided as an illustration of the invention, not as a limitation of the invention. Indeed, it will be apparent to those skilled in the art that various modifications and variations can be made in the present invention without departing from the scope or spirit of the invention. For example, features illustrated or described as part of one embodiment can be used with another embodiment to yield yet a further embodiment. It is therefore intended that the present invention cover such modifications and variations as come within the scope of the appended claims and their equivalents.

[0013] In general, the present disclosure is directed to systems and methods for inspecting one or more wind turbines in a wind farm, such as an offshore wind farm. For example, in one embodiment, the system may include an unmanned autonomous vessel equipped with a self-stabilizing data acquisition system having multiple sensors of various sensing modalities (e.g., visible range imaging, thermal imaging, LIDAR, etc.). Furthermore, the system includes a low-latency satellite communication link for remote control / command from an onshore command center, if necessary. Thus, the vessel can perform long-term, area-wide inspections and monitoring of a fleet of offshore wind turbines. Additionally, the onboard data acquisition system can perform data acquisition autonomously via pre-planned missions or semi-autonomously via low-latency triggering and tracking capabilities from a remote control center, such as an onshore control center. Furthermore, the onboard data acquisition system can self-stabilize to handle sea states and conditions. Furthermore, in one embodiment, data analysis can be performed onshore in real time, and depending on the results of the analysis, a more detailed inspection can be ordered as needed. For example, in one embodiment, the vessel can autonomously navigate to a target wind turbine for inspection (e.g., a safe distance ahead of the wind turbine), and the data acquisition system can automatically point the imaging sensor / device at a target (e.g., a portion of a blade) to acquire images / data. If necessary, the inspection can be performed semi-autonomously via a communications link. For example, in one embodiment, an operator can issue a command for an updated inspection target, such as a new portion of a blade or a new wind turbine, and the system can autonomously execute the updated mission. If an anomaly / damage is detected by the system, repair and / or maintenance orders can be issued to avoid catastrophic failure of the target wind turbine.

[0014] Referring now to the drawings, FIG. 1 illustrates a perspective view of one embodiment of a wind turbine 10 according to the present disclosure. As illustrated, the wind turbine 10 includes a tower 12 extending from a support surface 14, a nacelle 16 mounted to the tower 12, and a rotor 18 coupled to the nacelle 16. The rotor 18 includes a rotatable hub 20 and at least one rotor blade 22 coupled to and extending outward from the hub 20. For example, in the illustrated embodiment, the rotor 18 includes three rotor blades 22. However, in alternative embodiments, the rotor 18 may include more or fewer than three rotor blades 22. Each rotor blade 22 may be spaced about the hub 20 to facilitate rotation of the rotor 18 so that kinetic energy may be converted from the wind into usable mechanical energy and, subsequently, electrical energy. For example, the hub 20 may be rotatably coupled to a generator 24 ( FIG. 2 ) disposed within the nacelle 16 to enable the production of electrical energy.

[0015] As shown, the wind turbine 10 may also include a centralized turbine control system or turbine controller 26 within the nacelle 16. However, it should be understood that the turbine controller 26 may be disposed anywhere on or within the wind turbine 10, anywhere on the support surface 14, or generally at any other location. The turbine controller 26 may generally include any suitable processing unit configured to perform the functions described herein. Thus, in some embodiments, the turbine controller 26 may include suitable computer-readable instructions that, when implemented, configure the controller 26 to perform a variety of different operations, such as sending and executing wind turbine control signals, receiving and analyzing sensor signals, and / or generating message signals. By sending and executing wind turbine control signals, the turbine controller 26 may generally be configured to control various operational modes (e.g., start-up or shutdown sequences) and / or components of the wind turbine 10.

[0016] Referring now to FIG. 2 , a simplified internal view of one embodiment of the nacelle 16 of the wind turbine 10 is shown. As shown, a generator 24 may be disposed within the nacelle 16. In general, the generator 24 may be coupled to the rotor 18 of the wind turbine 10 to generate electrical power from the rotational energy generated by the rotor 18. For example, the rotor 18 may include a rotor shaft 34 that is coupled to the hub 20 and rotates therewith. The generator 24 may then be coupled to the rotor shaft 34 such that rotation of the rotor shaft 34 drives the generator 24. For example, in the illustrated embodiment, the generator 24 includes a generator shaft 36 that is rotatably coupled to the rotor shaft 34 through a gearbox 38. However, it should be understood that in other embodiments, the generator shaft 36 may be rotatably coupled directly to the rotor shaft 34. Alternatively, the generator 24 may be rotatably coupled directly to the rotor shaft 34 (often referred to as a “direct drive wind turbine”).

[0017] 3A-12 , various views of components of a system 100 for inspecting an offshore wind farm 101 having one or more wind turbines are shown, in accordance with the present disclosure. In particular, as shown in FIGS. 3A , 3B , and 4A , the system 100 includes an unmanned autonomous vessel 102 configured to navigate ocean across a body of water 150 to the offshore wind farm 101. Accordingly, as shown in FIG. 3B , the unmanned autonomous vessel 102 may have any suitable length L and / or any other suitable features (such as one or more stabilizers 152) to provide desired stability of the unmanned autonomous vessel 102 as the vessel 102 navigates in sea conditions.

[0018] 3B and 4A, system 100 includes a positioning module 104 for navigating unmanned autonomous vessel 102 to a target wind turbine 106 within offshore wind farm 101 and positioning unmanned autonomous vessel 102 near the target wind turbine. Additionally, as shown, system 100 may include an onboard data acquisition module 108 having one or more sensors 110 (such as imaging devices) for collecting local data regarding the health of target wind turbine 106, and a controller 114. Such components are configured to communicate with each other and with a remote command center 116 via a satellite communication link 118.

[0019] 10 , in certain embodiments, the positioning module 104 may include a dynamic positioning module 107 and a fault-tolerant positioning module 109. For example, in such an embodiment, the dynamic positioning module 107 is configured to transmit one or more planned routes to the fault-tolerant positioning module 109 (as indicated by arrow 125). Moreover, in one embodiment, as shown in FIGS. 10 and 11 , the dynamic positioning module 107 is configured to receive local data 111 (such as wind speed, data from sea and ship sensors) and global data 119 (such as weather forecasts from a satellite communication link 118). In addition, as shown in FIG. 11 , the dynamic positioning module 107 may also receive control center commands 127 and one or more ship detection data 129. Thus, the dynamic positioning module 107 may include a real-time dynamic path planner configured to generate an optimal path trajectory 121 for the unmanned autonomous vessel 102 over a future time period via a cost function 131, an optimizer 133, and / or a vessel system model prediction module 135, and to implement the optimal path trajectory 121 one step at a time.

[0020] In particular, as shown in FIG. 11 , the vessel system model prediction module 135 receives various inputs, such as weather forecasts, route maps, and vessel feedback information, and provides predicted results for a future time period (e.g., the next hour, or the next 10 minutes). Further, as shown, the cost function 131 and optimizer 133 generate an optimal route trajectory 121 within the future time period. However, in one embodiment, only the first few planned moves (or even only the first move) are executed. The system 100 then re-executes the plan following the same pattern, also known as receding horizon route planning. In such an embodiment, this approach is configured to dynamically detect and respond to changes in the environment and vessel conditions. In one embodiment, for example, control center commands 127 may override any parameters (e.g., parameters in the cost function, vessel system model, etc.) or outputs (e.g., nulling or adding bias) of the dynamic route planner.

[0021] In one example, the dynamic positioning module 107 may use a two-step vessel positioning approach to complete turbine inspection navigation. In such an embodiment, the first step is to navigate the unmanned autonomous vessel 102 close to the wind farm 101 (e.g., some distance from the unmanned autonomous vessel 102 to the target wind turbine 106, such as approximately 10 meters) using a coarse reference trajectory encoded in the cost function 131. The second step is to use refined coordination by adjusting the vessel position (e.g., blade angles including yaw and pitch angles) related to wind turbine conditions when the unmanned autonomous vessel 102 is sufficiently close to the target wind turbine 106 (e.g., some distance from the unmanned autonomous vessel 102 to the target wind turbine 106, such as less than approximately 10 meters). Both steps may be implemented by adjusting any parameters (e.g., parameters in the cost function 131, vessel system model prediction module 135, etc.) or outputs (nulling or adding bias) of the dynamic path planner in real time.

[0022] 11 , in one embodiment, a unique aspect of the present disclosure is the use of turbine health indicators to influence vessel path generation. For example, in one embodiment, blade leading edge erosion may be a health indicator, specifically the surface roughness (%) of the blade leading edge. In such an embodiment, the surface roughness (%) may be used to characterize the degree of erosion. This information from the remote command center 116 may become a priority constraint for the dynamic positioning optimization problem, which influences the vessel inspection path. Moreover, as particularly shown in FIG. 11 , the optimal path trajectory 121 may also be used by the sensor state estimator 137. For example, in one embodiment, the sensor state estimator 137 may use a Kalman filter (or any other suitable filter) and sensed inputs to the path planner (e.g., local data 111, global data 119, etc.) to estimate sensor states for future periods when the optimal path trajectory 121 is generated. Moreover, as shown, the estimated sensor states may then be used with the actual sensor states in future periods to calculate an error, which may then be transmitted to the dynamic positioning module 107 for optimization.

[0023] 12 , a schematic diagram of one embodiment of a fault-tolerant positioning module 109 according to the present disclosure is shown. In particular, as shown, whenever one or more of the following abnormal conditions occur, the edge controller of the unmanned autonomous vessel 102 may lose input signals critical to achieving real-time path planning. Therefore, a pre-stored planned path may be utilized with information prior to the abnormal condition. Such operation may occur when communication loss occurs with either the remote command center 116 and / or the satellite communication link 118, and / or when a partial failure of the unmanned autonomous vessel 102 or vessel sensors occurs:

[0024] In particular embodiments, for example, the fault-tolerant positioning module 109 is configured to generate, via the positioning digital twin 139, top three (or more) paths (e.g., A, B, and C) for the unmanned autonomous vessel 102 at any time prior to an event (e.g., an abnormal situation), given weather profiles / forecasts, wind farm SCADA data, vessel information, the vessel 102's current status (e.g., map location, range, etc.), historical data sets, etc. Additionally, as shown, the positioning digital twin 139 may include a scenario generation module 145, a cost function 147, and / or a system model 149. Thus, in one embodiment, based on the cost function 147 and potential future scenarios 145, and the vessel system model predictions 149 (e.g., energy / material balances for the vessel systems), the fault-tolerant positioning module 109 can generate the top paths A, B, and C. In such embodiments, the top paths may be the result of a Pareto front or a multi-objective optimization problem and may be associated with one or more corresponding abnormal situations (e.g., partial failures of input information, etc.).

[0025] After an event (e.g., an abnormal situation), partial information or functionality may be compromised. When input information is limited, the fault-tolerant positioning module 109 may include a pattern matching module 141 for selecting the best route, as shown at 143, to navigate the system 100 according to the selected route. Once the system 100 recovers and becomes normal, the system 100 may switch back to utilizing the dynamic positioning module 107.

[0026] Additionally, as shown in FIGS. 3A-5 , the on-board data acquisition module 108 has one or more sensors 110 (e.g., imaging devices) for collecting local data 105 related to the health of the target wind turbine 106. In certain embodiments, as shown in FIG. 4A , the on-board data acquisition module 108 may be housed within a watertight vessel 154 for safely transporting the sensor 110 out to sea. Moreover, in certain embodiments, the on-board data acquisition module 108 may be self-stabilizing, as further described in more detail herein below. Moreover, in certain embodiments, for example, the sensor 110 may include multiple sensors having multiple different sensor modalities. More specifically, in one embodiment, the multiple sensor modalities may include visible range imaging, thermal imaging, or light detection and ranging (LIDAR) imaging. Thus, the collected local data 105 may include data regarding the health status of the target wind turbine 106, the operating status of the target wind turbine 106, vessel detection, and / or global information about the offshore wind farm 101 (such as weather forecasts for the wind farm 101 from satellite communication link 118 and / or environmental conditions near the target wind turbine 106). Additionally, the health status of the target wind turbine 106 may include health indicators (such as erosion, deflection, deformation, or defects) of the target wind turbine 106, electrical component health (such as overheating, underheating, moisture content, or offline detection), and / or switching device health status.

[0027] In further embodiments, for example, the dynamic positioning module 107 is configured to set the health indicator as a priority constraint and influence the output of the optimal path trajectory 121 based on the health indicator. In certain embodiments, the dynamic positioning module 107 is also configured to generate multiple candidate paths for the unmanned autonomous vessel 102 based on different failure modes. In such embodiments, for example, the different failure modes may include loss of communication with the satellite communication link 118, partial failure of the unmanned autonomous vessel 102, and / or the onboard data acquisition module 108. Furthermore, the multiple candidate paths may be continuously generated and stored in the fault-tolerant positioning module 109. In additional embodiments, the fault-tolerant positioning module 109 is configured to select an optimal path from the multiple stored candidate paths based on the actual failure mode. Thus, as shown in FIG. 10 , the outputs of the dynamic positioning module 107 and the fault-tolerant positioning module 109 are received by a vessel health monitoring and decision module (also referred to herein simply as controller 114), which outputs the optimal path trajectory 121 and / or one or more warning indicators 123, such as early warning outputs.

[0028] More specifically, in certain embodiments, vessel detection described herein may include one or more camera images of the target wind turbine 106. In such embodiments, as shown in FIGS. 4A-4C and 6, the camera images may be captured by one or more self-stabilizing cameras 112, 115. For example, as shown, the system 100 may include a positioning camera 112 and a tracking camera 115 mounted on or otherwise secured to a gimbal 120. In one embodiment, for example, the cameras 112, 115 may be secured atop one or more platforms of the gimbal 120. As used herein, a gimbal generally refers to a pivoting support that allows for rotation of an object about an axis. Thus, in the present disclosure, the gimbal 120 enables the cameras 112, 115 to self-stabilize, even in unstable situations (such as an ocean or sea with constantly moving waves). In further embodiments, system 100 may include any suitable stabilizing device, such as a vertical stabilizer, a horizontal stabilizer, a vertical windscreen, a horizontal windscreen, a gyroscope, a tether, and / or any other suitable device for stabilizing components of system 100.

[0029] 4B, the self-stabilizing cameras 112, 115 (and / or any of the sensors described herein) may be remotely controlled, for example, via a remote trigger / controller 122. In such an embodiment, for example, the remote trigger / controller 122 may be an antenna or receiver capable of receiving signals from the remote command center 116. Such signals may use radio frequency signals, Wi-Fi signals, Bluetooth signals, or any other protocol for communication.

[0030] 3A , the sensors 110 may be configured to use, for example, burst photography to detect defects on the surfaces of the rotor blades 22, LIDAR to monitor the aeroelastic behavior of the blades, and / or infrared (IR) / thermal imaging to monitor aerodynamic performance and / or detect defects on one or more surfaces (e.g., rotor blade surfaces) of the target wind turbine 106. Additionally, as shown in FIG. 3A , the sensors 110 described herein may include one or more deployable sensors 113 that may be launched from the unmanned autonomous vessel 102 to collect local data. Such deployable sensors 113 may be fixed to the underwater vessel 148, for example, to collect underwater data about the target wind turbine 106 (e.g., data related to a portion of the tower 12 or foundation (not shown) that is underwater). In a further embodiment, the deployable sensors 113 may be fixed to one or more unmanned aerial vehicles (UAVs) or drones to collect local data 105.

[0031] Moreover, in one embodiment, the on-board data acquisition module 108 may be configured to use artificial intelligence (AI) and / or one or more computer vision (CV) based algorithms to target and track one or more moving components (e.g., rotor blades 22) or non-moving components (e.g., tower 12, etc.) of the target wind turbine 106 for data collection. Thus, in one embodiment, the target wind turbine 106 may remain operational during inspection.

[0032] 7-9, various embodiments of operating a system 100 for inspecting an offshore wind farm 101 having one or more wind turbines according to the present disclosure are shown. In particular, as shown in FIG. 7, the system 100 may include two cameras: a positioning camera 112 and a tracking camera 115. In particular, the positioning camera 112 may be used to position the platform on a gimbal 120. Thus, in one embodiment, the positioning camera 112 may be a low-resolution, wide-angle spotting camera, while the tracking camera 115 may be a high-resolution camera with zoom and tracking capabilities. Thus, as shown, the tracking camera 115 may track a rotor blade 22, for example, from root 136 to tip 138 and midpoint 140 while the target wind turbine 106 is in operation or stationary (as indicated by the spiral motion path 134). In such an embodiment, the system 100 may require visual servoing (also known as vision-based robotic control).

[0033] In another embodiment, as shown in FIG. 8 , the system 100 may also include two cameras 112, 115: a positioning camera 112 and a tracking camera 115. In particular, the positioning camera 112 may be used to position the gimbal 120 platform. Thus, in one embodiment, the positioning camera 112 may be a low-resolution, wide-angle spotting camera, and the tracking camera 115 may be a high-resolution camera with zoom and tracking capabilities. Thus, as shown, the tracking camera 115 may track one of the rotor blades 22 to locate the root 136, midsection 140, and tip 138 and perform burst captures in a straight line or fixed-point path motion, as indicated by arrow 142. In such an embodiment, the system 100 may not require visual servoing.

[0034] 9, system 100 may include a single camera 110. Thus, in such an embodiment, camera 110 may be a high-resolution, wide-angle camera for tracking the entire wind turbine 106 of interest, thereby eliminating the need for a tracking camera for finer targets. In such an embodiment, system 100 may have a motion path with a fixed point (e.g., no more than one).

[0035] Additionally, as shown in FIGS. 5 and 6 and as described above, system 100 may also include a controller 114 having at least one processor and local storage 117 (FIG. 6). Accordingly, controller 114 is configured to perform a number of operations. For example, in one embodiment, the number of operations may include receiving, by controller 114, local data 105 from sensors 110, e.g., via network 130 and / or any processor. In one embodiment, network 130, for example, may be a low-latency network. As used herein, a low-latency network generally refers to a computer network optimized to process very large amounts of data signals with minimal delay (latency). Thus, a low-latency network is designed to support operations requiring near-real-time access to rapidly changing data.

[0036] 5 and 6, the on-board data acquisition module 108 (and / or the controller 114) may include image segmentation and recognition functionality 124, target tracking 126 (e.g., for the entire wind turbine and / or rotor blades 22), and / or model-based image capture 128 for processing the local data 105. For example, in one embodiment, the image segmentation and recognition functionality 124 may include machine learning (ML) segmentation, bounding boxes, and / or blade segmentation. Furthermore, as particularly shown in FIG. 6, the controller 114 may include image processing capabilities 132 for processing the collected data (e.g., images) before applying one or more of the features described herein (e.g., tracking, image recognition, modeling, etc.).

[0037] 5 and 6, the controller 114 is configured to forward the local data 105 to the remote command center 116 via a satellite communication link 118 (FIGS. 3A and 5). More specifically, in one embodiment, the controller 114 may identify one or more anomalies or defects in the local data related to the health of the wind turbine of interest and may forward the local data along with the identified defects / anomalies to the remote command center 116.

[0038] In certain embodiments, the remote command center 116 may be an onshore remote control center. Further, in one embodiment, the controller 114 may be configured to transmit one or more warning indicators 123 ( FIG. 10 ) of damage or wear related to the target wind turbine 106. More specifically, in one embodiment, the warning indicators may include a number of different levels or categories for classifying damage and / or wear on the target wind turbine 106. For example, in one embodiment, the warning indicators may include a color, such as green, yellow, or red. Thus, in one embodiment, the warning indicators may include internal health status alerts (e.g., vessel and detection system health levels, 0-100, green / yellow / red, etc.), external condition alerts (e.g., extreme environment, high waves, strong winds, vessel capsizing, unsuitable for inspection, etc.), and / or alerts of unexpected / server failures of the wind turbine (e.g., resulting in redundancy for turbine internal systems).

[0039] Thus, in one embodiment, when the local data 105 is transferred via satellite communication link 118 to the remote command center 116, if one or more anomalies are identified in the local data 105, the remote command center 116 can generate repair and / or maintenance orders and dispatch such orders to the wind farm 101.

[0040] In further embodiments, the system 100 may also receive one or more inspection commands for the target wind turbine 106 from the remote command center 116 via the satellite communication link 118. Accordingly, in such embodiments, the system 100 is configured to implement the inspection commands. In such embodiments, for example, as described above, the unmanned autonomous vessel 102 may be equipped with an antenna or receiver capable of receiving signals from the remote command center 116. Such signals may use radio frequency signals, Wi-Fi signals, Bluetooth signals, or any other protocol for communication.

[0041] Referring now to FIG. 13 , a flow diagram of one embodiment of a method 200 for inspecting an offshore wind farm having one or more wind turbines according to the present disclosure is shown. Generally, the method 200 is described herein as relating to an offshore wind farm having one or more wind turbines, such as the wind farm shown in FIG. 3 . However, it should be understood that the disclosed method 200 may be implemented using any other suitable wind farm, both onshore and offshore. Additionally, while FIG. 13 depicts steps performed in a particular order for purposes of illustration and explanation, the methods described herein are not limited to any particular order or arrangement. Those skilled in the art will understand, using the disclosure provided herein, that various steps of the method can be omitted, rearranged, combined, and / or adapted in various ways.

[0042] As shown at (202), method 200 includes navigating an unmanned autonomous vessel to a target wind turbine at an offshore wind farm via a positioning module of the unmanned autonomous vessel. As shown at (204), method 200 includes positioning the unmanned autonomous vessel near the target wind turbine via the positioning module. As shown at (206), method 200 includes collecting local data related to the health of a target wind turbine in the wind farm via an onboard data acquisition module having one or more sensors. For example, in one embodiment, collecting local data related to the health of the target wind turbine via the onboard data acquisition module may include targeting and tracking one or more moving components of the target wind turbine for data collection using at least one of artificial intelligence (AI) or one or more computer vision (CV)-based algorithms. As shown at (208), method 200 includes transmitting the local data to a remote command center via a satellite communication link.

[0043] In additional embodiments, method 200 may also include receiving, via a controller of the unmanned autonomous vessel, one or more inspection commands (e.g., new or updated commands, etc.) for the target wind turbine from a remote command center via a satellite communication link, and implementing the one or more inspection commands via the system.

[0044] 14 , a block diagram of one embodiment of suitable components that may be included within a controller 300 (e.g., turbine controller 26 or controller 114) in accordance with the present disclosure is shown. As shown, controller 300 may include one or more processors 302 and associated memory devices 304 configured to perform various computer-implemented functions (e.g., executing methods, steps, calculations, etc., and storing associated data as disclosed herein). Additionally, controller 300 may also include a communications module 306 to facilitate communication between controller 300 and various components of wind turbine 10. Further, communications module 306 may include a sensor interface 308 (e.g., one or more analog-to-digital converters) to enable signals transmitted from sensors (e.g., sensor 110) to be converted into signals that can be understood and processed by processor 302. It should be understood that sensor 110 may be communicatively coupled to communications module 306 using any suitable means. For example, as shown, sensor 110 is coupled to sensor interface 308 via a wired connection. However, in other embodiments, the sensor 110 may be coupled to the sensor interface 308 via a wireless connection, such as by using any suitable wireless communication protocol known in the art.

[0045] As used herein, the term "processor" refers not only to integrated circuits referred to in the art as being included in a computer, but also to controllers, microcontrollers, microcomputers, programmable logic controllers (PLCs), application-specific integrated circuits, and other programmable circuits. Additionally, memory device 304 may generally comprise memory elements including, but not limited to, computer-readable media (e.g., random access memory (RAM)), computer-readable non-volatile media (e.g., flash memory), floppy disks, compact disc read-only memories (CD-ROMs), magneto-optical disks (MODs), digital versatile disks (DVDs), and / or other suitable memory elements. Such memory device 304 may generally be configured to store suitable computer-readable instructions that, when executed by processor 302, configure controller 300 to perform various functions, including, but not limited to, sending appropriate control signals to perform control operations, as described herein, as well as various other suitable computer-implemented functions.

[0046] Further aspects of the invention are provided by the subject matter of the following clauses.

[0047] 1. A system for inspecting an offshore wind farm having one or more wind turbines, the system comprising: an unmanned autonomous vessel configured to navigate the unmanned autonomous vessel to a target wind turbine in the offshore wind farm; a positioning module for positioning the unmanned autonomous vessel near the target wind turbine; an onboard data acquisition module comprising one or more sensors for collecting local data regarding the health of the target wind turbine; and a controller comprising at least one processor configured to perform a plurality of operations, the plurality of operations including receiving local data from the one or more sensors and forwarding the local data to a remote command center via a satellite communication link.

[0048] 10. The system of any preceding clause, wherein the on-board data acquisition module is configured to use at least one of artificial intelligence (AI) or one or more computer vision (CV) based algorithms to target and track one or more moving components of the target wind turbine for data collection.

[0049] 10. The system of any preceding clause, wherein the one or more sensors comprise a plurality of sensors with a plurality of sensor modalities, the plurality of sensor modalities including at least one of visible range imaging, thermal imaging, or light detection and ranging (LIDAR) imaging.

[0050] 10. The system of any preceding clause, wherein the local data includes at least one of a health status of the target wind turbine, an operational status of the target wind turbine, vessel detection, or global information regarding the offshore wind farm, and wherein the method further includes identifying one or more defects in the local data regarding the health of the target wind turbine, and forwarding the local data together with the identified one or more defects to a remote command center.

[0051] 10. The system of any preceding clause, wherein vessel detection includes at least one camera image of the target wind turbine, the camera image being captured by a self-stabilizing gimbal camera.

[0052] The system of any preceding clause, wherein the global information includes at least one of a weather forecast for the offshore wind farm from a satellite communications link, or environmental conditions near the wind turbine of interest.

[0053] 10. The system of any preceding clause, wherein the health status of the target wind turbine includes at least one of a health indicator of the target wind turbine, an electrical component health, or a switching device health status.

[0054] The system of any preceding clause, wherein the health indicator includes at least one of erosion, deflection, deformation, or defects, and the electrical component health includes at least one of overheating, underheating, moisture content, or offline detection.

[0055] 10. The system of any preceding clause, wherein the on-board data acquisition module is self-stabilizing.

[0056] 10. The system of any preceding clause, wherein the positioning module comprises a dynamic positioning module and a fault-tolerant positioning module, the dynamic positioning module configured to send the one or more planned paths to the fault-tolerant positioning module.

[0057] 10. The system of any preceding clause, wherein the dynamic positioning module is configured to receive local and global information regarding the unmanned autonomous vessel, generate an optimal path trajectory for the unmanned autonomous vessel over a future period via a cost function and an optimizer, and implement the optimal path trajectory one step at a time.

[0058] The system of any preceding clause, wherein the dynamic positioning module is configured to set the health indicator as a priority constraint and influence output of the optimal path trajectory based on the health indicator.

[0059] 10. The system of any preceding clause, wherein the dynamic positioning module is configured to generate a plurality of candidate paths for the unmanned autonomous vessel based on different failure modes, the different failure modes including at least one of loss of communication with a satellite communication link of a remote command center, partial failure of the unmanned autonomous vessel or the onboard data acquisition module, and the plurality of candidate paths are continuously generated and stored in the fault-tolerant positioning module.

[0060] 10. The system of any preceding clause, wherein the fault-tolerant positioning module is configured to select an optimal path from a plurality of candidate paths based on an observed failure mode.

[0061] 10. The system of any preceding clause, wherein transferring the local data to a remote command center via a satellite communications link further includes transmitting one or more warning indicators of damage related to the target wind turbine.

[0062] 10. The system of any preceding clause, wherein transmitting the local data via a satellite communications link to a remote command center causes one or more repair or maintenance orders to be generated by the remote command center if one or more anomalies are identified in the local data.

[0063] 10. The system of any preceding clause, wherein the operations further include receiving one or more inspection commands for the target wind turbine from a remote command center via a satellite communication link; and implementing the one or more inspection commands via the system.

[0064] 1. A method for inspecting an offshore wind farm having one or more wind turbines, the method including: navigating an unmanned autonomous vessel to a target wind turbine at the offshore wind farm via a positioning module of the unmanned autonomous vessel; positioning the unmanned autonomous vessel near the target wind turbine via the positioning module; collecting local data regarding the health of the target wind turbine in the offshore wind farm via an onboard data acquisition module having one or more sensors; and transferring the local data to a remote command center via a satellite communications link.

[0065] 10. The method of any preceding clause, further comprising: identifying, via a controller of the unmanned autonomous vessel, one or more defects in local data relating to the health of the target wind turbine; and transmitting the local data together with the identified one or more defects to a remote command center.

[0066] 10. The method of any preceding clause, further comprising receiving, via a controller of the unmanned autonomous vessel, one or more inspection commands for the target wind turbine from a remote command center via a satellite communications link; and implementing the one or more inspection commands.

[0067] Examples are used herein to disclose the invention, including the best mode, and to enable any person skilled in the art to practice the invention, including making and using any devices or systems, and performing any methods incorporated therein. The patentable scope of the invention is defined by the claims, and may include other examples that occur to those skilled in the art. Such other examples are intended to be within the scope of the claims if they contain structural elements that do not deviate from the literal language of the claims, or contain equivalent structural elements that do not deviate substantially from the literal language of the claims. [Explanation of symbols]

[0068] 10. Wind Turbines 12. Tower 14 Support surface 16 Nacelle 18 rotors 20 Hub 22 rotor blades 24 Generator 26 Turbine controller, controller 34 rotor shaft 36 Generator shaft 38 Gearbox 100 systems 101 Offshore wind power plants, wind power plants 102 Unmanned autonomous vessels, ships 104 Positioning Module 105 Local Data 106 Target Wind Turbines 107 Dynamic Positioning Module 108 Onboard Data Acquisition Module 109 Fault-tolerant positioning module, fault-tolerant module 110 one or more sensors, sensors, cameras 111 Local Data 112 Self-stabilizing camera, positioning camera, camera 113 One or more deployable sensors, deployable sensors 114 Controller 115 Self-stabilizing cameras, tracking cameras, cameras 116 Remote Command Center 117 Local Storage 118 Satellite Communication Links 119 Global Data 120 Gimbal 121 Optimal Route Trajectory 122 Remote Trigger / Control Device 123 One or more warning indicators 124 Image Segmentation and Recognition Functions 125 Arrow 126 Target Tracking 127 Control Center Command 128 Model-Based Image Capture 129 One or more vessel detection data 130 Network 131 Cost Function 132 Image Processing Capability 133 Optimizer 134 Spiral Motion Path 135 Ship System Model Prediction Module 136 Base 137 Sensor State Estimator 138 Tip 139 Positioning Digital Twin 140 Middle, Middle Section 141 Pattern Matching Module 142 Arrow 145 Scenario Generation Module, Potential Future Scenarios 147 Cost Function 148 Underwater Vessel 149 System Model, Ship System Model Prediction 150 Water area 152 One or more stabilizers 154 Waterproof Ship 200 ways 202 Navigating an unmanned autonomous vessel to a target wind turbine in an offshore wind farm via a positioning module of the unmanned autonomous vessel. 204 Positioning the unmanned autonomous vessel near the target wind turbine via the positioning module. 206 collecting local data regarding the health of a target wind turbine within a wind farm via an on-board data acquisition module having one or more sensors; 208 Transferring local data to a remote command center via a satellite communication link 300 Controller 302 one or more processors, processors 304 Memory Devices 306 Communication Module 308 Sensor Interface

Claims

1. A system (100) for inspecting an offshore wind farm (101) having one or more wind turbines (10), said system (100) comprising: Unmanned autonomous ship (102) The unmanned autonomous vessel (102) comprises: a positioning module (104) for navigating the unmanned autonomous marine vessel (102) to a target wind turbine (106) in the offshore wind farm (101) and positioning the unmanned autonomous marine vessel (102) near the target wind turbine (106); an on-board data acquisition module (108) comprising one or more sensors (110) for collecting local data (105) relating to the health of the target wind turbine (106); A controller (114) comprising at least one processor configured to perform a plurality of operations, the plurality of operations comprising: receiving the local data (105) from the one or more sensors (110); transferring said local data (105) to a remote command center (116) via a satellite communication link (118); a controller (114) including: A system (100) comprising:

2. 2. The system (100) of claim 1, wherein the on-board data acquisition module (108) is configured to use at least one of artificial intelligence (AI) or one or more computer vision (CV) based algorithms to target and track one or more moving components of the target wind turbine (106) for data collection.

3. 10. The system of claim 1, wherein the one or more sensors comprise a plurality of sensors with a plurality of sensor modalities, the plurality of sensor modalities including at least one of visible range imaging, thermal imaging, or light detection and ranging (LIDAR) imaging.

4. 2. The system (100) of claim 1, wherein the local data (105) includes at least one of a health status of the target wind turbine (106), an operational status of the target wind turbine (106), vessel detection, or global information about the offshore wind farm (101), and the method further includes identifying one or more defects in the local data (105) related to the health of the target wind turbine (106) and transferring the local data (105) together with the identified one or more defects to the remote command center (116).

5. The system (100) of claim 4, wherein the vessel detection includes at least one camera image of the target wind turbine (106), the camera image being captured by a self-stabilizing gimbal camera.

6. 5. The system (100) of claim 4, wherein the global information includes at least one of a weather forecast for the offshore wind farm (101) from the satellite communication link (118) or environmental conditions near the target wind turbine (106).

7. 5. The system of claim 4, wherein the health status of the target wind turbine includes at least one of a health indicator, an electrical component health, or a switching device health status of the target wind turbine.

8. 8. The system (100) of claim 7, wherein the health indicator comprises at least one of erosion, deflection, deformation, or defects, and the electrical component health comprises at least one of overheating, underheating, moisture content, or offline detection.

9. The system (100) of claim 1, wherein the on-board data acquisition module (108) is self-stabilizing.

10. 2. The system (100) of claim 1, wherein the positioning module (104) comprises a dynamic positioning module (107) and a fault-tolerant positioning module (109), and the dynamic positioning module (107) is configured to transmit one or more planned paths to the fault-tolerant positioning module (109).

11. The dynamic positioning module (107) receiving local and global information regarding the unmanned autonomous vessel (102); generating an optimal path trajectory (121) for the unmanned autonomous vessel (102) over a future period via a cost function (131) and an optimizer (133); implementing said optimal path trajectory (121) one step at a time; The system (100) of claim 10, configured to:

12. 12. The system (100) of claim 11, wherein the dynamic positioning module (107) is configured to set the health indicator as a priority constraint and influence the output of the optimal path trajectory (121) based on the health indicator.

13. 12. The system of claim 11, wherein the dynamic positioning module is configured to generate a plurality of candidate paths for the unmanned autonomous vessel based on different failure modes, the different failure modes including at least one of a loss of communication with the satellite communication link of the remote command center, a partial failure of the unmanned autonomous vessel or the onboard data acquisition module, and the plurality of candidate paths are continuously generated and stored in the fault-tolerant positioning module.

14. The system (100) of claim 10, wherein the fault-tolerant location module (109) is configured to select an optimal path from the plurality of candidate paths based on an observed failure mode.

15. 2. The system (100) of claim 1, wherein transferring the local data (105) to the remote command center (116) via the satellite communication link (118) further comprises transmitting one or more warning indicators (123) of damage related to the target wind turbine (106).

16. 2. The system of claim 1, wherein upon transmitting the local data to the remote command center via the satellite communication link, one or more repair or maintenance orders are generated by the remote command center if one or more anomalies are identified in the local data.

17. 2. The system (100) of claim 1, wherein the plurality of operations further comprises receiving one or more inspection commands for the target wind turbine (106) from the remote command center (116) via the satellite communication link (118) and implementing the one or more inspection commands via the system (100).

18. A method (200) for inspecting an offshore wind farm (101) having one or more wind turbines (10), said method (200) comprising: Navigating (202) an unmanned autonomous vessel (102) to a target wind turbine (106) at the offshore wind farm (101) via a positioning module (104) of the unmanned autonomous vessel (102); positioning (204) the unmanned autonomous vessel (102) near the target wind turbine (106) via the positioning module (104); collecting (206) local data (105) regarding the health of the target wind turbine (106) in the offshore wind farm (101) via an on-board data acquisition module (108) having one or more sensors (110); transmitting (208) said local data (105) to a remote command center (116) via a satellite communication link (118); A method (200) comprising:

19. Identifying, via a controller of the unmanned autonomous vessel (102), one or more defects in the local data (105) relating to the health of the target wind turbine (106); transferring said local data (105) along with said one or more identified defects to said remote command center (116); 20. The method (200) of claim 18, further comprising:

20. 20. The method (200) of claim 18, further comprising receiving, via a controller of the unmanned autonomous vessel (102), one or more inspection commands for the target wind turbine (106) from the remote command center (116) via the satellite communications link (118), and implementing the one or more inspection commands.

Images