Blade modeling apparatus and method

Abstract

The present invention relates to a blade modeling apparatus and method capable of supplementing insufficient sensing capability of a small drone equipped with a limited sensor by performing blade modeling using sensing data for at least one blade of a wind turbine. The blade modeling apparatus comprises: a data collection module for receiving sensing data of a drone with respect to a reference blade included in a wind turbine; and a modeling module for generating a blade model by performing modeling with respect to the wind turbine on the basis of the sensing data, wherein the modeling module comprises a reference blade model generation unit for generating a reference blade model by performing modeling with respect to the reference blade, and a different blade model generation unit for generating a different blade model for at least one different blade included in the wind turbine on the basis of the reference blade model.

Description

Blade modeling device and method

[0001] The present invention relates to a blade modeling device and method.

[0002] Specifically, the present invention relates to a blade modeling device and method that can complement the insufficient sensing capability of a small drone equipped with limited sensors by performing blade modeling using sensing data for at least one blade of a wind turbine.

[0003] The content described in this section merely provides background information for the present embodiment and does not constitute prior art.

[0004] Typically, when inspecting wind turbines using drones, the drone's position is controlled based on currently available sensor measurements.

[0005] However, due to spatial limitations, small drones often cannot accommodate sensors like lidar, which are used for distance measurement. Consequently, they can only accommodate a limited number of sensors, such as cameras. Insufficient sensing capabilities often prevent accurate determination of distances, such as between the drone and wind turbines.

[0006] In particular, the distance measurement accuracy of cameras mounted on small drones (e.g. stereo cameras) is significantly reduced when the plane is tilted or has no distinct features, such as the blades of a wind turbine.

[0007] Accordingly, there has been a significant need to improve the accuracy of mission control by accurately measuring the distance between the drone and the structure when using small drones to inspect structures such as wind turbines.

[0008] The purpose of the present invention is to provide a blade modeling device and method capable of inspecting all blades of a wind turbine at once through a blade modeling process even when using a small drone equipped with limited sensors.

[0009] Specifically, the purpose of the present invention is to provide a blade modeling device and method capable of supplementing the insufficient sensing capability of a small drone equipped with limited sensors by modeling a reference blade model (vertical blade model), predicting modeling results for other blades through the reference blade model, and correcting the predicted values ​​through sensing data for the other blades.

[0010] In addition, the purpose of the present invention is to provide a blade modeling device and method that can overcome limitations of the blades of a wind power generator, which are not easy to model due to the cone angle, tilt angle, etc., through modeling results for each surface of a reference blade (vertical blade).

[0011] The objectives of the present invention are not limited to those mentioned above. Other objectives and advantages of the present invention not mentioned above can be understood through the following description and will be more clearly understood through the embodiments of the present invention. Furthermore, it will be readily apparent that the objectives and advantages of the present invention can be realized by the means and combinations thereof set forth in the claims.

[0012] According to some embodiments of the present invention, a blade modeling device includes a data collection module that receives sensing data of a drone for a reference blade included in a wind power generator, and a modeling module that performs modeling of the wind power generator based on the sensing data to create a blade model, wherein the modeling module includes a reference blade model generation unit that performs modeling of the reference blade to create a reference blade model, and an other blade model generation unit that generates other blade models for at least one other blade included in the wind power generator based on the reference blade model, wherein the blade model may include at least one of at least one virtual straight line set along each of a plurality of surfaces included in the blade and a virtual coordinate system for each of the plurality of surfaces determined based on the virtual straight line.

[0013] In addition, the sensing data includes shooting data captured from a camera included in the drone, and the reference blade model generation unit can measure position data for a first measurement surface included in the reference blade using the shooting data, and set a virtual straight line for the first measurement surface based on the measured position data for the first measurement surface.

[0014] In addition, the reference blade model generation unit can recognize a blade box from the shooting data based on the first point in time of the shooting data, determine the center point of the recognized blade box, measure first position data which is position data of the determined center point, and set a center line which is a virtual straight line for the first measurement surface based on the first position data.

[0015] In addition, the reference blade model generation unit can recognize a blade box from the shooting data based on a second time point different from the first time point, determine a center point of the recognized blade box, measure second position data which is position data of the determined center point, and set the center line through regression analysis using the first position data and the second position data.

[0016] In addition, the reference blade model generation unit, when setting a virtual straight line for a second measurement plane different from the first measurement plane included in the reference blade, can measure position data for the second measurement plane using the photographed data, and set a virtual straight line for the second measurement plane based on the measured position data for the second measurement plane and a plurality of virtual straight lines for the first measurement plane including the center line.

[0017] Additionally, the plurality of virtual straight lines for the first measurement surface including the center line may include the center line, the left line which is a virtual straight line based on the left edge of the blade box, and the priority which is a virtual straight line based on the right edge of the blade box.

[0018] In addition, the reference blade model generation unit can derive a plurality of preliminary virtual straight lines for the second measurement surface based on the position data for the measured second measurement surface, and correct the plurality of preliminary virtual straight lines for the second measurement surface using at least one of a parallel translation technique and an orthogonal projection technique based on the plurality of virtual straight lines for the first measurement surface.

[0019] In addition, the reference blade model generation unit may set the virtual coordinate system for each of the plurality of surfaces included in the reference blade with the point where the nose of the wind turbine and the center line meet as the origin and the center line as one axis, and the other blade model generation unit may include a prediction unit that predicts a preliminary other blade model by rotating the virtual coordinate system for each of the plurality of surfaces by a predetermined angle.

[0020] In addition, the data collection module may further receive sensing data of the drone for the other blade, and the other blade model generation unit may further include a correction unit that corrects the predicted preliminary other blade model using the sensing data of the drone for the other blade to generate the other blade model.

[0021] Additionally, the above correction unit can correct the preliminary guitar blade model using the recursive least square method.

[0022] A blade modeling method according to some embodiments of the present invention may include a method for modeling a blade of a wind power generator, the method including: acquiring photographic data for a first surface of the blade at multiple points in time; modeling the first surface with a virtual straight line for the first surface; and modeling the second surface with a virtual straight line parallel to the virtual straight line for the first surface or a virtual straight line orthogonal to the virtual straight line for the first surface.

[0023] In addition, the virtual straight line is expressed as a reference point and a vector, and the step of modeling the first surface may be characterized by generating a plurality of position data from photographing data for the first surface, calculating the reference point as an average of the plurality of position data, and calculating the vector using a difference between the position data and the average.

[0024] In addition, the step of modeling the first side may be characterized by modeling the center line, right-hand line, and left-hand line for the first side, and the step of modeling the second side may be characterized by modeling the second side by projecting the center line, right-hand line, and left-hand line of the first side onto the second side based on the right-hand line of the second side when the second side is the left-hand side of the first side, and modeling the second side by projecting the center line, right-hand line, and left-hand line of the first side onto the second side based on the left-hand line of the second side when the second side is the right-hand side of the first side.

[0025] In addition, the step of modeling the first side may be characterized by modeling the center line, right and left lines for the first side, and the step of modeling the second side may be characterized by modeling the second side so that, when the second side is the rear side of the first side, the center line, right and left lines of the first side and the second side are parallel.

[0026] The blade modeling device and method according to some embodiments of the present invention have a novel effect of being able to inspect all blades of a wind turbine at once through a blade modeling process even when using a small drone equipped with limited sensors.

[0027] Specifically, the blade modeling device and method according to some embodiments of the present invention can supplement the insufficient sensing capability of a small drone equipped with a limited sensor (e.g., a stereo camera) by modeling a reference blade model (vertical blade model), then predicting modeling results for other blades through the reference blade model, and correcting the predicted values ​​through sensing data for the other blades.

[0028] At this time, the blade modeling device and method according to some embodiments of the present invention can express the three-dimensional shape of the blade by modeling the blade with a plurality of straight lines (e.g., eight straight lines) rather than a single straight line, thereby improving modeling accuracy.

[0029] In addition, the blade modeling device and method according to some embodiments of the present invention can overcome the difficulty of the blade modeling process due to the cone angle, tilt angle, etc. through the modeling results for each surface of the reference blade (vertical blade).

[0030] In addition, the blade modeling device and method according to some embodiments of the present invention have a novel effect of being able to obtain relative positional information between a drone and a blade using the blade modeling results after performing the blade modeling process. That is, since the blade modeling device and method according to some embodiments of the present invention performs blade modeling on the surface of the blade rather than the center, it is possible to calculate the relative position between the drone and the surface using the blade modeling results.

[0031] In addition to the above-described contents, the specific effects of the present invention are described together with the specific matters for carrying out the invention below.

[0032] FIG. 1 illustrates a blade modeling system according to some embodiments of the present invention.

[0033] FIG. 2 is a block diagram of a blade modeling device according to some embodiments of the present invention.

[0034] FIG. 3A is a drawing illustrating a reference blade and other blades according to some embodiments of the present invention.

[0035] FIG. 3b is a drawing illustrating a plurality of surfaces included in a blade according to some embodiments of the present invention.

[0036] FIG. 4 is a detailed block diagram of a modeling module according to some embodiments of the present invention.

[0037] FIG. 5 is a drawing for explaining a process of setting a virtual straight line for a first measurement surface included in a reference blade using sensing data for the reference blade.

[0038] Figure 6 illustrates an example of a virtual straight line set with respect to the first measurement surface of the reference blade.

[0039] FIG. 7a and FIG. 7b are drawings for explaining a process of correcting a virtual straight line of a second measurement surface of a reference blade using a virtual straight line of a first measurement surface of a reference blade.

[0040] Figure 8 illustrates an example of a virtual coordinate system set for the first surface (front surface) of the reference blade.

[0041] Figure 9 illustrates an example of a guitar blade model for the first side (front side) of a first guitar blade predicted based on the first side (front side) of a reference blade.

[0042] Figure 10 is a drawing for explaining the effect of the blade modeling process of the present invention.

[0043] FIG. 11 is a flowchart of a blade modeling method according to some embodiments of the present invention.

[0044] FIG. 12 is a flowchart of a blade modeling method according to some other embodiments of the present invention.

[0045] The terms and words used in this specification and claims should not be interpreted based on their general or dictionary meanings. In accordance with the principle that inventors can define the concepts of terms and words to best describe their inventions, they should be interpreted in a way that is consistent with the technical concept of the present invention. Furthermore, the embodiments described in this specification and the configurations depicted in the drawings are merely examples of how the present invention can be realized and do not fully represent the technical concept of the present invention. Therefore, it should be understood that various equivalents, modifications, and applicable examples may exist as of the time of filing.

[0046] The terms first, second, A, B, etc. used in this specification and claims may be used to describe various components, but the components should not be limited by these terms. These terms are used only for the purpose of distinguishing one component from another. For example, without departing from the scope of the present invention, the first component may be referred to as the second component, and similarly, the second component may also be referred to as the first component. The term "and / or" includes any combination of a plurality of related listed items or any item among a plurality of related listed items.

[0047] The terminology used in this specification and claims is for the purpose of describing specific embodiments only and is not intended to limit the present invention. Singular expressions include plural expressions unless the context clearly dictates otherwise. It should be understood that terms such as "comprise" or "have" in this application do not preclude the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof described in the specification.

[0048] Unless otherwise defined, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art to which the present invention belongs.

[0049] Terms defined in commonly used dictionaries should be interpreted to have a meaning consistent with their meaning in the context of the relevant technology, and will not be interpreted in an idealized or overly formal sense unless expressly defined in this application.

[0050] In addition, each configuration, process, procedure or method included in each embodiment of the present invention may be shared within a scope that is not technically inconsistent with each other.

[0051] Hereinafter, a blade modeling device and method according to some embodiments of the present invention will be described with reference to FIGS. 1 to 12.

[0052]

[0053] FIG. 1 illustrates a blade modeling system according to some embodiments of the present invention.

[0054] Referring to FIG. 1, a blade modeling system (1, hereinafter referred to as “blade modeling system”) for inspecting a wind power generator according to some embodiments of the present invention may include a drone (200) that photographs an industrial structure (100) and a blade modeling device (300).

[0055] Industrial structures (100) may refer to large facilities that require a large number of people and cost for inspection or are too dangerous for humans to perform inspection directly.

[0056] As examples, industrial structures (200) may include, but are not limited to, wind turbines, structures or facilities constructed for the operation of a business, such as factories or buildings, bridges, power lines, distribution lines, roads, etc. FIG. 1 illustrates a wind turbine as an example of an industrial structure (100).

[0057] For the convenience of the following explanation, the industrial structure (100) will be explained assuming that it is a wind power generator.

[0058] The drone (200) may include a device that flies around the wind power generator (100) and checks the status of the wind power generator (100). The drone (200) may also be referred to as an unmanned aerial vehicle (UAV). The drone (200) may be configured to automatically fly around the wind power generator (100) along a predetermined path, but embodiments of the present invention are not limited thereto. For example, the drone (200) may also be manually flown around the wind power generator (100) as needed. The drone (200) may be a flying drone that photographs the wind power generator (100) and / or the surrounding environment of the wind power generator (100), but embodiments are not limited thereto, and may be a ground drone, an underwater drone, etc.

[0059] The drone (200) flies according to a predetermined flight command and / or a control command for flight or operation received from a blade modeling device (300), and can obtain sensing data for the wind power generator (100).

[0060] As some examples, a drone (200) can fly around a wind turbine (100) to collect sensing data about the wind turbine (100) and transmit the collected sensing data to a blade modeling device (300).

[0061] The sensing data may include photographed data for each blade included in the wind power generator (100). In other words, the drone (200) may be equipped with mission equipment such as a camera (e.g., a stereo camera), and the drone (200) may transmit photographed data for each blade of the wind power generator (100) captured through the camera to the blade modeling device (300). At this time, the photographed data may include image data and / or video data for each blade of the wind power generator (100).

[0062] At this time, the drone (200) may include a small drone. For example, the drone (200) according to some embodiments of the present invention may be equipped with only an imaging device such as a camera as mission equipment. In other words, the mission equipment equipped on the drone (200) according to some embodiments of the present invention may include a stereo camera, but may not include a lidar sensor.

[0063] The blade modeling device (300) can generate a blade model based on sensing data received from the drone (200). In other words, the blade modeling device (300) can receive sensing data including shooting data from the drone (200) and generate a blade model based on the received sensing data.

[0064] The blade model may include a reference blade model and other blade models. The reference blade model may include modeling results regarding the reference blade, which is the blade whose angle with the ground is closest to vertical among the blades included in the wind generator (100), and the other blade model may include modeling results regarding other blades included in the wind generator (100) except the reference blade.

[0065] At this time, the blade model may include a virtual straight line and / or a virtual coordinate system set for each blade. In other words, the blade model may be in the form of a virtual straight line set for the blade or in the form of a virtual coordinate system. At this time, the virtual coordinate system may be created based on the virtual straight line. One virtual straight line may be a virtual straight line connecting a start point and an end point in space. The start point and the end point may be expressed as three-dimensional coordinates. The blade modeling device (300) may create a blade model with one or more virtual straight lines for one blade. In one example, the blade modeling device (300) may create a blade model including eight virtual straight lines representing the center lines of four surfaces and four edges for one blade.

[0066] In some examples, the blade model may include at least one virtual straight line set along each of a plurality of faces included in the blade and / or at least one virtual coordinate system for each of the plurality of faces determined based on the virtual straight lines. The virtual coordinate system may be a three-dimensional coordinate system expressed in x, y, and z axes. In one example, the reference blade model may include at least one virtual straight line set along each of a plurality of faces included in the reference blade and a virtual coordinate system for each of the plurality of faces determined based on the virtual straight lines. In another example, the other blade model may be in the form of at least one virtual straight line set along each of a plurality of faces included in the other blade and a virtual coordinate system for each of the plurality of faces determined based on the virtual straight lines.

[0067] The blade modeling device (300) can generate a reference blade model using sensing data for a reference blade, predict other blade models using the generated reference blade model, and then correct the prediction results of other blade models using sensing data for other blades.

[0068] At this time, the blade modeling device (300) can perform modeling for each of the plurality of faces included in the reference blade when creating a reference blade model. In other words, the blade modeling device (300) can perform modeling for each of the plurality of faces included in the reference blade, for example, the first face to the fourth face, and then synthesize the modeling results for each face to create a reference blade model. At this time, the blade modeling device (300) can use the modeling result for one face included in the reference blade to correct the modeling result for another face included in the reference blade.

[0069] The specific operation method of the blade modeling device (300) will be described later.

[0070] Meanwhile, the drone (200) and the blade modeling device (300) may be connected via a communication network. In other words, the communication network may serve to exchange data between the drone (200) and the blade modeling device (300). In this case, the communication network may serve to provide a connection path so that the drone (200) and the blade modeling device (300) can transmit and receive data between each other.

[0071] The communication network may include a communication network based on wired Internet technology, wireless Internet technology, and short-range communication technology. The wired Internet technology may include, for example, at least one of a local area network (LAN) and a wide area network (WAN). The wireless Internet technology may include, for example, at least one of wireless LAN (WLAN), Digital Living Network Alliance (DLNA), Wireless Broadband (Wibro), World Interoperability for Microwave Access (Wimax), High Speed ​​Downlink Packet Access (HSDPA), High Speed ​​Uplink Packet Access (HSUPA), IEEE 802.16, Long Term Evolution (LTE), Long Term Evolution-Advanced (LTE-A), Wireless Mobile Broadband Service (WMBS), and 5G NR (New Radio) technology. However, the present embodiment is not limited thereto. Short-range communication technologies may include, for example, at least one of Bluetooth, Radio Frequency Identification (RFID), Infrared Data Association (IrDA), Ultra-Wideband (UWB), ZigBee, Near Field Communication (NFC), Ultra Sound Communication (USC), Visible Light Communication (VLC), Wi-Fi, Wi-Fi Direct, and 5G NR (New Radio).However, the present embodiment is not limited thereto. The drone (200) and blade modeling device (300) communicating through a communication network may comply with technical standards and standard communication methods for mobile communication. For example, the standard communication method may include at least one of GSM (Global System for Mobile communication), CDMA (Code Division Multi Access), CDMA2000 (Code Division Multi Access 2000), EV-DO (Enhanced Voice-Data Optimized or Enhanced Voice-Data Only), WCDMA (Wideband CDMA), HSDPA (High Speed ​​Downlink Packet Access), HSUPA (High Speed ​​Uplink Packet Access), LTE (Long Term Evolution), LTEA (Long Term Evolution-Advanced), and 5G NR (New Radio). However, the present embodiment is not limited thereto.

[0072] In FIG. 1, the drone (200) and the blade modeling device (300) are illustrated as separate components. However, the present invention is not limited thereto, and the functions of the blade modeling device (300) may be integrated into the drone (200). In other words, each data processing process of the blade modeling device (300) may be performed by a processor included within the drone (200). The drone (200) may include one or more processors. The processor may include a CPU, a GPU, and / or an NPU.

[0073] However, for the convenience of the following explanation, the drone (200) and the blade modeling device (300) will be described as separate and distinct components.

[0074] Hereinafter, a blade modeling device (300) according to some embodiments of the present invention will be described in more detail with further reference to FIG. 2.

[0075]

[0076] FIG. 2 is a block diagram of a blade modeling device according to some embodiments of the present invention.

[0077] Referring to FIGS. 1 and 2, the blade modeling device (300) may include a data collection module (310), a modeling module (320), and a relative position calculation module (330). The blade modeling device (300) may include one or more processors, and the processors may perform the operations of the data collection module (310), the modeling module (320), and the relative position calculation module (330). The drone (200) may also include one or more processors, and the drone (200) may equally perform the operations of the data collection module (310), the modeling module (320), and the relative position calculation module (330).

[0078] The data collection module (310) can collect sensing data (hereinafter referred to as "SD"). In other words, the data collection module (310) can receive sensing data (SD) regarding a wind turbine (100) from a drone (200).

[0079] The sensing data (SD) may include data captured by the drone (200) of the wind turbine (100). That is, the drone (200) may be equipped with mission equipment such as a camera (e.g., a stereo camera), and the drone (200) may generate captured data of the wind turbine (100) through the camera and transmit it to the data collection module (310). At this time, the captured data included in the sensing data (SD) may include image data and / or video data for each blade of the wind turbine (100).

[0080] For example, the sensing data (SD) may include sensing data for a reference blade and sensing data for other blades.

[0081] The data collection module (310) can transmit the received shooting data (SD) to other components within the blade modeling device (300). For example, the data collection module (310) can transmit the shooting data (SD) to the modeling module (320), etc., but the present invention is not limited thereto.

[0082] The data collection module (310) can utilize various communication modules, and can perform data exchange between the drone (200) and the blade modeling device (300) through a communication network.

[0083] The modeling module (320) can generate a blade model (hereinafter referred to as "BM") based on sensing data (SD). In other words, the modeling module (320) can generate a blade model (BM) based on sensing data (SD) transmitted from the drone (200).

[0084] A blade model (BM) may include a reference blade model and other blade models. The reference blade model may include modeling results regarding a reference blade, which is the blade whose angle with the ground is closest to vertical among the blades included in the wind generator (100), and the other blade models may include modeling results regarding blades other than the reference blade among the blades included in the wind generator (100).

[0085] At this time, the blade model (BM) may include modeling results for each of the multiple faces of each corresponding blade. In other words, the blade model (BM) may include modeling results for each of the multiple faces included in the corresponding blade. Specifically, the reference blade model may include modeling results for each face included in the reference blade, and the other blade models may include modeling results for each face included in the other blades.

[0086] Hereinafter, with reference to FIGS. 3a and 3b, the reference blade and other blades included in the wind power generator (100) and the plurality of surfaces included in each blade will be described.

[0087]

[0088] FIG. 3A is a drawing illustrating a reference blade and other blades according to some embodiments of the present invention. FIG. 3B is a drawing illustrating a plurality of surfaces included in a blade according to some embodiments of the present invention.

[0089] Referring to FIGS. 3a and 3b, the wind turbine (100) may include a plurality of blades.

[0090] As some examples, the wind turbine generator (100) may include one reference blade (BD_ref) and at least one other blade (BD_else). FIG. 3A illustrates a first other blade (BD_else1) and a second other blade (BD_else2) as examples of other blades (BD_else), but the embodiments of the present invention are not limited thereto, and the number of other blades (BD_else) may be freely varied.

[0091] At this time, the reference blade (BD_ref) may include the blade whose angle with respect to the ground is closest to vertical among the blades included in the wind generator (100). In other words, the reference blade (BD_ref) in the present invention may be defined as the blade arranged at the most vertical angle with respect to the ground among the blades included in the wind generator (100).

[0092] Other blades (BD_else) may include blades other than the reference blade (BD_ref) among the blades included in the wind generator (100). In other words, other blades (BD_else) in the present invention may be defined as blades other than the reference blade (BD_ref) among the blades included in the wind generator (100).

[0093] At this time, the above-mentioned reference blade model may include modeling results regarding the reference blade (BD_ref) of FIG. 3a, and the other blade model may include modeling results regarding the other blade (BD_else) of FIG. 3a.

[0094] The blade (BD) of the present invention, which includes a reference blade (BD_ref) and other blades (BD_else), may include multiple surfaces.

[0095] As some examples, the blade (BD) in the present invention may include a first surface (BD_P1) to a fourth surface (BD_P4).

[0096] At this time, the first side (BD_P1) included in the blade (BD) may be a side (front side) located in front based on the direction in which the wind blows, i.e., the wind direction (hereinafter referred to as “WD”), the second side (BD_P2) may be a side (right side) located on the right side based on the wind direction (WD), the third side (BD_P3) may be a side (left side) located on the left side based on the wind direction (WD), and the fourth side (BD_P4) may be a side (rear side) located in the rear based on the wind direction (WD).

[0097] Hereinafter, for convenience of explanation, the surfaces located at the front, right, left, and rear of the blade (BD) with respect to the wind direction (WD) will be referred to as the first surface (BD_P1) to the fourth surface (BD_P4), respectively.

[0098] At this time, the blade model described above may include modeling results for each of the plurality of faces (BD_P1 to BD_P4) of the blade (BD). In other words, the blade model may include modeling results for each of the plurality of faces (BD_P1 to BD_P4) included in the blade (BD). Specifically, the reference blade model may include modeling results for each of the four faces included in the reference blade (BD_ref), and the other blade models may include modeling results for each of the four faces included in the other blade (BD_else).

[0099]

[0100] Referring again to FIGS. 1 and 2 , the blade model (BM) may include a virtual straight line and / or a virtual coordinate system established for each blade. In other words, the blade model (BM) may be in the form of a virtual straight line established for the blade or in the form of a virtual coordinate system. In this case, the virtual coordinate system may be generated based on the virtual straight line.

[0101] In some examples, the blade model (BM) may be in the form of at least one virtual straight line set along each of a plurality of faces included in the blade and / or at least one virtual coordinate system for each of the plurality of faces determined based on the virtual straight lines. As an example, the reference blade model may include at least one virtual straight line set along each of a plurality of faces included in the reference blade and a virtual coordinate system for each of the plurality of faces determined based on the virtual straight lines. As another example, the other blade model may include at least one virtual straight line set along each of a plurality of faces included in the other blade and a virtual coordinate system for each of the plurality of faces determined based on the virtual straight lines.

[0102] The modeling module (320) can generate a reference blade model using sensing data for a reference blade, predict other blade models using the generated reference blade model, and then correct the prediction results of other blade models using sensing data for other blades.

[0103] At this time, when creating a reference blade model, the modeling module (320) can use the modeling results for one surface included in the reference blade to correct the modeling results for another surface included in the reference blade. In other words, the modeling module (320) can use the blade model for the first surface included in the reference blade to correct the blade model for the second surface included in the reference blade.

[0104] Hereinafter, the operation of the modeling module (320) of the present invention will be described in more detail with reference to FIG. 4.

[0105]

[0106] FIG. 4 is a detailed block diagram of a modeling module according to some embodiments of the present invention.

[0107] Referring to FIGS. 1 and 4, a modeling module (320) according to some embodiments of the present invention may include a reference blade model generation unit (321) and other blade model generation unit (322). The other blade model generation unit (322) may include a prediction unit (322a) and a correction unit (322b).

[0108] The reference blade model generation unit (321) can generate a reference blade model (BM_ref) based on sensing data (SD) regarding the reference blade. At this time, the sensing data (SD) regarding the reference blade may include photographing data regarding the reference blade. In other words, the sensing data (SD) regarding the reference blade may include image data and / or video data regarding the reference blade.

[0109] As some examples, the reference blade model generation unit (321) can perform modeling for each of a plurality of surfaces included in the reference blade based on sensing data (SD) regarding the reference blade. In other words, the reference blade model generation unit (321) can perform modeling for each of the four surfaces included in the reference blade based on sensing data (SD) regarding the reference blade.

[0110] Below, the process of setting a virtual straight line for a reference blade will first be described, and then the process of setting a virtual coordinate system based on the virtual straight line will be described.

[0111] First, the reference blade model generation unit (321) can set a virtual straight line for any one surface included in the reference blade. In other words, the reference blade model generation unit (321) can set a virtual straight line for the first measurement surface of the reference blade. At this time, the first measurement surface can mean any one surface among a plurality of surfaces included in the reference blade (e.g., the first surface (BD_P1) to the fourth surface (BD_P4) of FIG. 3b).

[0112] As some examples, the reference blade model generation unit (321) can set a virtual straight line for the first measurement surface by measuring position data for the first measurement surface using sensing data for the first surface of the reference blade among the sensing data (SD) for the reference blade.

[0113] For example, the reference blade model generation unit (321) can generate position data measurement results for multiple points in time of sensing data (SD) regarding the reference blade, and set a virtual straight line for the first measurement surface of the reference blade by combining the generated multiple position data measurement results.

[0114]

[0115] Hereinafter, with reference to FIGS. 5 and 6, the process of the reference blade model generation unit (321) setting a virtual straight line for the first surface of the reference blade will be described. At this time, for convenience of explanation, it is assumed that the first measurement surface of the reference blade is the front surface (first surface) of the reference blade.

[0116]

[0117] FIG. 5 is a diagram illustrating a process of setting a virtual straight line for a first measurement surface included in a reference blade using sensing data for the reference blade. FIG. 6 illustrates an example of a virtual straight line set for the first measurement surface of the reference blade. In this case, as described above, in FIGS. 5 and 6, the first measurement surface of the reference blade is illustrated as being the front surface (first surface) of the reference blade for convenience of explanation.

[0118] Referring to FIGS. 5 and 6, the reference blade model generation unit (321) can set a virtual straight line (BM_ref_P1) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref) based on sensing data (SD_1, SD_2) at several points in time (T1, T2) regarding the reference blade (BD_ref).

[0119] At this time, the virtual straight line (BM_ref_P1) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref) may include multiple virtual straight lines. In other words, the virtual straight line (BM_ref_P1) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref) may include a left line (BM_ref_P1_left), a center line (BM_ref_P1_center), and a right line (BM_ref_P1_right) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref).

[0120] Below, the process of setting the center line (BM_ref_P1_center) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref) is described in detail.

[0121] First, the reference blade model generation unit (321) can recognize the first blade box (BB_1) from the first sensing data (SD_1) at the first time point (T1) for the reference blade (BD_ref). Thereafter, the reference blade model generation unit (321) can determine the center point (BB_1_center) of the first blade box (BB_1). Thereafter, the reference blade model generation unit (321) can calculate the pixel coordinates of the center point (BB_1_center). Thereafter, the reference blade model generation unit (321) can measure the position data of the center point (BB_1_center) using the distance between the drone (200) and the center point (BB_1_center) measured from the stereo camera included in the drone (200) and the pixel coordinates of the center point (BB_1_center). For convenience, the position data of the center point (BB_1_center) measured at the first time point (T1) is referred to as first position data.

[0122] Next, the reference blade model generation unit (321) can measure the second position data, which is the position data of the center point (BB_2_center) measured at the second time point (T2), through a process of recognizing the second blade box (BB_1) from the second sensing data (SD_2) at the second time point (T2) for the reference blade (BD_ref) in a similar manner to measuring the first position data of the center point (BB_1_center) described above.

[0123] Next, the reference blade model generation unit (321) can set the center line (BM_ref_P1_center) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref) by combining the first position data, which is the position data of the center line at the first time point (T1), and the second position data, which is the position data of the center line at the second time point (T2). For example, the reference blade model generation unit (321) can set the center line (BM_ref_P1_center) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref) by using regression analysis using the first position data and the second position data.

[0124] Meanwhile, the reference blade model generation unit (321) can set the left line (BM_ref_P1_left) and right line (BM_ref_P1_right) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref) in a similar manner to the process of setting the center line (BM_ref_P1_center) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref). That is, the reference blade model generation unit (321) can set the left line (BM_ref_P1_left) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref) by using the left center point (BB_1_left, BB_2_left) instead of the center point (BB_1_center, BB_2_center) in the blade box (BB_1, BB_2) recognized at each time point (T1, T2). In addition, the reference blade model generation unit (321) can set priority (BM_ref_P1_right) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref) by using the right center point (BB_1_right, BB_2_right) rather than the center point (BB_1_center, BB_2_center) of the blade box (BB_1, BB_2) recognized at each time point (T1, T2).

[0125]

[0126] Referring back to FIGS. 1 and 4, the reference blade model generation unit (321) can set a virtual straight line for the second measurement surface of the reference blade after a virtual straight line for the first measurement surface of the reference blade is set. At this time, the second measurement surface may mean any one of the surfaces excluding the first measurement surface among the plurality of surfaces included in the reference blade (e.g., the first surface (BD_P1) to the fourth surface (BD_P4) of FIG. 3b).

[0127] The reference blade model generation unit (321) can set a preliminary virtual straight line for the second measurement surface of the reference blade through a process similar to the process of setting a virtual straight line for the first measurement surface of the reference blade described above in FIG. 5. In other words, the reference blade model generation unit (321) can set a preliminary virtual straight line for the second measurement surface of the reference blade by performing the process of FIG. 5 described above on the sensing data for the second measurement surface of the reference blade, rather than the sensing data for the first measurement surface of the reference blade.

[0128] Next, the reference blade model generation unit (321) can set a virtual straight line for the second measurement surface of the reference blade by correcting a preliminary virtual straight line for the second measurement surface using the virtual straight line for the first measurement surface of the preset reference blade.

[0129] For example, the reference blade model generation unit (321) can correct a preliminary virtual straight line using a parallel translation technique and / or an orthogonal projection technique based on a virtual straight line for the first surface of a preset reference blade.

[0130] Hereinafter, the process of correcting the preliminary virtual straight line will be described in more detail with reference to FIGS. 7a and 7b. At this time, as in FIGS. 5 and 6, for convenience of explanation, it is assumed that the first measurement surface of the reference blade is the front surface (first surface) of the reference blade.

[0131]

[0132] FIG. 7a and FIG. 7b are drawings for explaining a process of correcting a virtual straight line of a second measurement surface of a reference blade using a virtual straight line of a first measurement surface of a reference blade.

[0133] In more detail, FIG. 7a illustrates a process of correcting a preliminary virtual straight line for a fourth side (rear side, BD_ref_P4) corresponding to the opposite side based on the first side (front side, BD_ref_P1) of the reference blade (BD_ref), and FIG. 7b illustrates a process of correcting a preliminary virtual straight line for a second side (right side, BD_ref_P2) corresponding to the side based on the first side (front side, BD_ref_P1) of the reference blade (BD_ref). Specifically, FIG. 7a illustrates a process of setting a virtual straight line for the fourth side (rear side, BD_ref_P4) by correcting a preliminary virtual straight line for the fourth side (rear side, BD_ref_P4) using a virtual straight line for the first side (front side, BD_ref_P1) of the reference blade (BD_ref), and FIG. 7b illustrates a process of setting a virtual straight line for the second side (right side, BD_ref_P2) by correcting a preliminary virtual straight line for the second side (right side, BD_ref_P2) using a virtual straight line for the first side (front side, BD_ref_P1) of the reference blade (BD_ref).

[0134] At this time, in FIGS. 7A and 7B, for convenience of explanation as described above, the first measurement surface of the reference blade is illustrated as the front surface (first surface) of the reference blade. At this time, in the case of FIG. 7A, the second measurement surface is illustrated as the fourth surface (rear surface, BD_ref_P4), and in the case of FIG. 7B, the second measurement surface is illustrated as the second surface (right surface, BD_ref_P2).

[0135] Referring to FIG. 7a, FIG. 7a illustrates a center line (BD_ref_P1_center), a left line (BD_ref_P1_left), and a right line (BD_ref_P1_right) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref) set through the process described above in FIG. 5, and similarly, preliminary virtual straight lines (BD_ref_P4_center_pre, BD_ref_P4_left_pre, BD_ref_P4_right_pre) for the fourth side (rear side, BD_ref_P4) of the reference blade (BD_ref) set through the process described above in FIG. 5 are illustrated.

[0136] The reference blade model generation unit (321) can correct preliminary virtual straight lines (BD_ref_P4_center_pre, BD_ref_P4_left_pre, BD_ref_P4_right_pre) for the fourth side (rear side, BD_ref_P4) of the reference blade (BD_ref).

[0137] As some examples, the reference blade model generation unit (321) can generate virtual straight lines (BM_ref_P4_center, BM_ref_P4_left, BM_ref_P4_right) for the fourth side (rear side, BD_ref_P4) of the reference blade (BD_ref) by correcting the preliminary virtual straight lines (BD_ref_P4_center_pre, BD_ref_P4_left_pre, BD_ref_P4_right_pre) for the fourth side (rear side, BD_ref_P4) using the virtual straight lines (BD_ref_P1_center, BD_ref_P1_left, BD_ref_P1_right) for the first side (front side, BD_ref_P1) of the preset reference blade (BD_ref).

[0138] For example, the reference blade model generation unit (321) can generate preliminary virtual straight lines (BM_ref_P4_center, BM_ref_P4_left, BM_ref_P4_right) using a parallel movement technique based on the virtual straight lines (BD_ref_P1_center, BD_ref_P1_left, BD_ref_P1_right) for the first surface (front surface, BD_ref_P1) of the reference blade (BD_ref).

[0139] Specifically, the reference blade model generation unit (321) can set the priority (BD_ref_P4_right) for the fourth side (rear side, BD_ref_P4) by correcting the position of the preliminary priority (BD_ref_P4_right_pre) for the fourth side (rear side, BD_ref_P4) to be parallel to the left line (BD_ref_P1_left) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref), as illustrated in FIG. 7a.

[0140] Similarly, the reference blade model generation unit (321) can set the center line (BD_ref_P4_center) for the fourth side (rear side, BD_ref_P4) by correcting the position of the preliminary center line (BD_ref_P4_center_pre) for the fourth side (rear side, BD_ref_P4) to be parallel to the center line (BD_ref_P1_center) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref), as illustrated in FIG. 7a.

[0141] In addition, the reference blade model generation unit (321) can set the left-hand side (BD_ref_P4_left) for the fourth side (rear side, BD_ref_P4) by correcting the position of the preliminary left-hand side (BD_ref_P4_left_pre) for the fourth side (rear side, BD_ref_P4) to be parallel to the priority (BD_ref_P1_right) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref), as illustrated in FIG. 7a.

[0142] Referring to FIG. 7b, FIG. 7b illustrates a center line (BD_ref_P1_center), a left line (BD_ref_P1_left), and a right line (BD_ref_P1_right) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref) set through the process described above in FIG. 5, and similarly, preliminary virtual straight lines (BD_ref_P2_center_pre, BD_ref_P2_left_pre, BD_ref_P2_right_pre) for the second side (right side, BD_ref_P2) of the reference blade (BD_ref) set through the process described above in FIG. 5 are illustrated.

[0143] The reference blade model generation unit (321) can correct preliminary virtual straight lines (BD_ref_P2_center_pre, BD_ref_P2_left_pre, BD_ref_P2_right_pre) for the second side (right side, BD_ref_P2) of the reference blade (BD_ref).

[0144] As some examples, the reference blade model generation unit (321) can generate virtual straight lines (BM_ref_P2_center, BM_ref_P2_left, BM_ref_P2_right) for the second side (right side, BD_ref_P2) of the reference blade (BD_ref) by correcting the preliminary virtual straight lines (BD_ref_P2_center_pre, BD_ref_P2_left_pre, BD_ref_P2_right_pre) for the second side (right side, BD_ref_P2) using the virtual straight lines (BD_ref_P1_center, BD_ref_P1_left, BD_ref_P1_right) for the first side (front side, BD_ref_P1) of the preset reference blade (BD_ref).

[0145] For example, the reference blade model generation unit (321) can generate a preliminary virtual straight line (BM_ref_P2_center, BM_ref_P2_left, BM_ref_P2_right) using an orthogonal projection technique based on one of the virtual straight lines (BD_ref_P1_center, BD_ref_P1_left, BD_ref_P1_right) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref).

[0146] Specifically, as illustrated in FIG. 7b, the reference blade model generation unit (321) can set the virtual straight lines (BD_ref_P2_center, BD_ref_P2_left, BD_ref_P2_right) for the second side (right side, BD_ref_P2) by projecting the positions of the preliminary virtual straight lines (BD_ref_P2_center_pre, BD_ref_P2_left_pre, BD_ref_P2_right_pre) for the second side (right side, BD_ref_P2) onto a plane corresponding to the priority (BD_ref_P1_right) for the first side (front side, BD_ref_P1) of the reference blade (BD_ref).

[0147]

[0148] Referring again to FIGS. 1 and 4, the reference blade model generation unit (321) can set a preliminary virtual straight line for other surfaces (third measurement surface, fourth measurement surface) of the reference blade in a manner similar to the aforementioned manner, and then correct the preliminary virtual straight line to set a virtual straight line for the corresponding surfaces (third measurement surface, fourth measurement surface).

[0149] Through this process, the reference blade model generation unit (321) can generate eight virtual straight lines for the reference blade as the reference blade model (BM_ref). In other words, the reference blade model (BM_ref) generated by the reference blade model generation unit (321) can include eight virtual straight lines. Specifically, the reference blade model generation unit (321) can set three virtual straight lines for each side of the reference blade, and since some of these overlap (e.g., the right line of the first side (front side) and the left line of the second side (right side) overlap), when the number of these overlapping parts is deducted, the reference blade model (BM_ref) generated by the reference blade model generation unit (321) includes eight virtual straight lines.

[0150]

[0151] Meanwhile, when a virtual straight line for the reference blade is set through the aforementioned process, the reference blade model generation unit (321) can set a virtual coordinate system for the reference blade based on the virtual straight line. At this time, similar to the virtual straight line, the virtual coordinate system can be set for each of the multiple surfaces included in the reference blade (e.g., each of the first surface (front surface) to the fourth surface (rear surface)).

[0152] As some examples, the reference blade model generation unit (321) can set a virtual coordinate system with the point where one of a plurality of virtual straight lines for the nose of the wind turbine (100) and one surface of the reference blade intersects as the origin and the virtual straight line as one axis (e.g., the Z axis).

[0153] For example, the reference blade model generation unit (321) can set a virtual coordinate system with the point where the center line of the nose of the wind turbine (100) and the first surface (front surface) of the reference blade intersecting as the origin and the center line as one axis (e.g., Z axis).

[0154] Accordingly, the reference blade model (BM_ref) generated by the reference blade model generation unit (321) may include four virtual coordinate systems. In other words, the virtual coordinate system is generated based on the center line among the virtual straight lines, and since one center line is set for each of the first side (front side) to the fourth side (rear side) of the reference blade, the reference blade model (BM_ref) includes four virtual coordinate systems.

[0155] Hereinafter, a virtual coordinate system set for the first surface (front surface) of the reference blade will be described with reference to FIG. 8.

[0156]

[0157] Figure 8 illustrates an example of a virtual coordinate system set for the first surface (front surface) of the reference blade.

[0158] Referring to Fig. 8, Fig. 8 illustrates a virtual coordinate system (BM_ref_P1_cs) set for the first side (front side) of the reference blade (BD_ref). At this time, the first side of the reference blade (BD_ref) illustrated in Fig. 8 may be the front side of the reference blade (BD_ref) based on the wind direction (WD of Fig. 3b) as described above.

[0159] As some examples, the reference blade model generation unit (321) can set a virtual coordinate system (BM_ref_P1_cs) with the point where the center line (BM_ref_P1_center) of the nose of the wind turbine (100) and the first surface (front surface) of the reference blade (BD_ref) intersect as the origin and the center line (BM_ref_P1_center) as one axis (Z-axis).

[0160] In other words, the virtual coordinate system (BM_ref_P1_cs) set by the reference blade model generation unit (321) for the first surface (front surface) of the reference blade (BM_ref) may be a coordinate system with the point where the nose of the wind turbine (100) and the center line (BM_ref_P1_center) for the first surface (front surface) of the reference blade (BM_ref) intersect as the origin and the center line (BM_ref_P1_center) as one axis (Z-axis).

[0161] In Fig. 8, only the virtual coordinate system for the first side (front side) of the reference blade (BD_ref) is shown, but this is only for convenience of explanation, and as described above, the reference blade model (BM_ref) may include multiple virtual coordinate systems each set for the first side (front side) to the fourth side (rear side).

[0162]

[0163] Referring back to FIGS. 1 and 4, the other blade model generation unit (322) can generate the other blade model (BM_else) based on the sensing data (SD) regarding the other blade and the reference blade model (BM_ref). At this time, the sensing data (SD) regarding the other blade may include photographing data regarding the other blade. In other words, the sensing data (SD) regarding the other blade may include image data and / or video data regarding the other blade.

[0164] Specifically, the other blade model generation unit (322) may include a prediction unit (322a) and a correction unit (322b).

[0165] The prediction unit (322a) can generate a preliminary other blade model (BM_else_pre) based on the reference blade model (BM_ref). At this time, the reference blade model (BM_ref) that the prediction unit (322a) receives and uses from the reference blade model generation unit (321) may be in the form of a virtual coordinate system.

[0166] As some examples, the prediction unit (322a) can generate a preliminary other blade model (BM_else_pre) by rotating a virtual coordinate system, which is a reference blade model (BM_ref), by a predetermined angle.

[0167] For example, the prediction unit (322a) can generate a preliminary guitar blade model (BM_else_pre) through a formula for a rotation matrix such as <Mathematical Formula 1> below, but the embodiment of the present invention is not limited thereto.

[0168] <Mathematical Formula 1>

[0169]

[0170] In <Mathematical Formula 1> is a position vector expressed in a virtual coordinate system with respect to the first side (front side) of the first guitar blade (BD_else1 in Fig. 3a) among the guitar blades, is a position vector expressed in a virtual coordinate system with respect to the first surface (front surface) of the reference blade, is a rotation matrix that transforms the virtual coordinate system with respect to the first face (front face) of the reference blade into the virtual coordinate system with respect to the first face (front face) of the first other blade (BD_else1 in Fig. 3a). is centered on the x-axis in the virtual coordinate system. The x-axis rotation matrix that rotates by an angle, is centered around the y-axis in the virtual coordinate system. Y-axis rotation matrix that rotates by an angle, is centered around the z-axis in the virtual coordinate system. It refers to the z-axis rotation matrix that rotates by the angle. At this time, , , represent the x-axis rotation angle, y-axis rotation angle, and z-axis rotation angle, respectively.

[0171] For example, the prediction unit (322a) can generate a preliminary other blade model (BM_else_pre) by rotating the reference blade model (BM_ref) by 120° around the x-axis, which is one axis constituting the reference blade model (BM_ref).

[0172] In other words, the prediction unit (322a) can generate a first other blade model (BD_else1 in FIG. 3a) by rotating the reference blade model (BM_ref) by -120° around the x-axis, and can generate a second other blade model (BD_else2 in FIG. 3a) by rotating the reference blade model (BM_ref) by 120° or -240° around the x-axis. That is, at this time, the x-axis rotation angle ( ) can include 120°, -120°, 240°, etc.

[0173] The correction unit (322b) can generate a guitar blade model (BM_else) by correcting a preliminary guitar blade model (BM_else_pre) using sensing data (SD) about the guitar blade.

[0174] For example, the correction unit (322b) uses the sensing data (SD) about the other blade to calculate the rotation matrix (in the above-described <Mathematical Formula 1>) ) of each rotation angle ( , , ) can be corrected.

[0175] At this time, the correction unit (322b) can generate a guitar blade model (BM_else) by correcting the preliminary guitar blade model (BM_else_pre) using a predetermined correction algorithm. For example, the correction algorithm may be an algorithm based on the recursive least squares method, but the embodiments of the present invention are not limited thereto.

[0176] Specifically, the correction unit (322b) determines a measurement error, which means the difference between the position data measurement result generated using sensing data (SD) about other blades and the model corresponding point (having the same z value as the position data measurement result) corresponding to the position data measurement result, and can generate a correction model related to the determined measurement error. At this time, the state variable of the correction model is the x-axis rotation angle ( ) and y-axis rotation angle ( ) can be defined (since the difference in the z position is not large depending on the change in slope). Then, the correction unit (322b) differentiates the correction model each time the position data measurement result generated using the sensing data (SD) on the other blade is measured, and uses a predefined algorithm in relation to the differential matrix and Kalman gain (K) produced by differentiating the correction model to determine the state variable (x-axis rotation angle ( ) and the change in y-axis rotation angle ( ) can be estimated. At this time, the predefined algorithm may be an algorithm related to a Kalman filter, but the embodiment of the present invention is not limited thereto. Next, the correction unit (322b) estimates the estimated state variable (x-axis rotation angle ( ) and the rotation angle of the y-axis ( ) can be used to generate a guitar blade model (BM_else) by correcting the preliminary guitar blade model (BM_else_pre).

[0177] Referring to FIG. 9 below, an example of a other blade model (BM_else) generated by the other blade model generation unit (322) will be described.

[0178]

[0179] Figure 9 illustrates an example of a guitar blade model for the first side (front side) of a first guitar blade predicted based on the first side (front side) of a reference blade.

[0180] Referring to FIG. 4 and FIG. 9, FIG. 9 illustrates a blade model (BM_else1_P1_cs) in the form of a virtual coordinate system for the first side (front side) of the first guitar blade (BD_else1) generated by the guitar blade model generation unit (322) through the process described above.

[0181] At this time, the other blade model (BM_else1_P1_cs) illustrated in FIG. 9 may be a other blade model generated based on the first surface (front surface) of the reference blade as described above.

[0182] For convenience of explanation, only the blade model (BM_else1_P1_cs) for the first side of the first guitar blade (BD_else1) is shown in FIG. 9. However, as described above, it is natural that the guitar blade model for the first guitar blade (BD_else1) includes blade models for the second side (right side) to the fourth side (rear side) of the first guitar blade (BD_else1).

[0183]

[0184] Referring again to FIGS. 1 and 4, the modeling module (320) can output a blade model (BM) including a generated reference blade model (BM_ref) and other blade models (BM_else).

[0185] Through this process, the blade model (BM) generated by the modeling module (320) can comprehensively include 24 virtual straight lines and 12 virtual coordinate systems. That is, as described above, the wind power generator (100) can include 3 blades, and 8 virtual straight lines and 4 virtual coordinate systems can be set for each blade, so the blade model (BM) can comprehensively include 24 virtual straight lines and 12 virtual coordinate systems. However, this is only for the convenience of explanation, and either the virtual straight lines or the virtual coordinate systems included in the blade model (BM) can be omitted, and the number of virtual straight lines and virtual coordinate systems can also be freely reduced and / or modified.

[0186] In this way, the modeling module (320) according to some embodiments of the present invention has a new effect of being able to inspect all blades of a wind power generator (100) at once through a blade modeling process even when using a small drone (200) equipped with limited sensors.

[0187] Specifically, the modeling module (320) models a reference blade model, then predicts modeling results for other blades through the reference blade model, and corrects the predictions through sensing data for the other blades, thereby supplementing the insufficient sensing capability of a small drone (200) equipped with limited sensors (e.g., a stereo camera).

[0188] At this time, the modeling module (320) can express the three-dimensional shape of the blade by modeling the blade as multiple straight lines (e.g., eight straight lines) rather than one straight line, thereby improving modeling accuracy.

[0189] In addition, the modeling module (320) can overcome the difficulty of the blade modeling process due to the cone angle, tilt angle, etc. through the modeling results for each face of the reference blade.

[0190] Hereinafter, the effect of the modeling process of the modeling module (320) of the present invention will be described with reference to FIG. 10.

[0191]

[0192] Figure 10 is a drawing for explaining the effect of the blade modeling process of the present invention.

[0193] Referring to FIGS. 1, 4 and 10, a blade modeling device (300) including a modeling module (320) according to some embodiments of the present invention is capable of performing blade modeling in which various parameters of each blade (BD_ref, BD_else) are reflected.

[0194] That is, in the case of a general blade modeling method, only the roll direction rotation angle of the blade (BD_ref, BD_else) (blade angle, angle between the blade and the ground when the wind power generator (100) is observed from the front) can be reflected.

[0195] However, in the case of the modeling module (320) according to some embodiments of the present invention, it is possible to perform blade modeling that reflects various parameters such as not only the roll direction rotation angle, but also the cone angle related to the rotor plane of each blade (BD_ref, BD_else), and the tilt angle related to the shaft.

[0196] Accordingly, the blade modeling device (300) including the modeling module (320) according to some embodiments of the present invention can further improve accuracy in the blade modeling process.

[0197]

[0198] Referring back to FIGS. 1 and 2, the relative position calculation module (330) can calculate the relative position (Reference Location, hereinafter referred to as “RL”) between the drone (200) and the wind turbine (100) based on the generated blade model (BM). At this time, the relative position (RL) can mean the position of the drone (200) based on a specific surface included in one blade of the wind turbine (100).

[0199] Hereinafter, for the convenience of explanation, the process of determining the relative position between the first surface (front surface) of the first guitar blade and the drone (200) will be described using an example.

[0200] As some examples, the relative position calculation module (330) can calculate the relative position (RL) based on a blade model (BM) expressed in the form of a virtual coordinate system for the first surface (front surface) of the first guitar blade and an inertial coordinate system in which a GPS position measured by a GPS sensor of the drone (200) is defined.

[0201] Specifically, first, the relative position calculation module (330) can calculate the position of the drone (200) in a virtual coordinate system with respect to the first surface (front surface) of the first guitar blade. In other words, the relative position calculation module (330) can determine the virtual position of the drone (200) by converting the position (GPS position) of the drone (200) defined in the inertial coordinate system based on the virtual coordinate system.

[0202] Next, the relative position calculation module (330) can determine the relative position in the virtual coordinate system based on a point having the same z-coordinate as the determined virtual position of the drone (200). In other words, the relative position calculation module (330) can search for a point having the same z-value as the virtual position in the virtual coordinate system of the first side (front) of the first guitar blade, and determine the relative position in the virtual coordinate system based on the point. Accordingly, the relative position in the virtual coordinate system can be expressed in the form of (x1, y1, 0), etc. In other words, the z-value of the relative position in the virtual coordinate system can be 0.

[0203] Next, the relative position calculation module (330) can convert the relative position (x1, y1, 0) in the determined virtual coordinate system into an inertial coordinate system to calculate the final relative position (RL).

[0204]

[0205] FIG. 11 is a flowchart of a blade modeling method according to some embodiments of the present invention. Each step (S100 to S400) of FIG. 11 can be performed by the blade modeling device (300) of FIGS. 1 and 2 . The following descriptions are provided briefly, excluding any overlapping details.

[0206] Referring to FIGS. 1, 2, 4, and 11, first, sensing data of the drone can be received (S100).

[0207] As some examples, the data collection module (310) can collect sensing data (SD) of the drone (200) regarding the wind power generator (100). In other words, the data collection module (310) can receive sensing data (SD) regarding the wind power generator (100) from the drone (200).

[0208] The sensing data (SD) may include photographed data for the wind power generator (100). In other words, the sensing data (SD) may include data taken by the drone (200) of the wind power generator (100). That is, the drone (200) may be equipped with mission equipment such as a camera (e.g., a stereo camera), and the drone (200) may generate photographed data for the wind power generator (100) through the camera and transmit the generated data to the data collection module (310). At this time, the photographed data included in the sensing data (SD) may include image data and / or video data for each blade of the wind power generator (100).

[0209] For example, the sensing data (SD) may include sensing data for a reference blade and sensing data for other blades.

[0210] Next, a reference blade model can be created (S200).

[0211] As some examples, the reference blade model generation unit (321) can generate a reference blade model (BM_ref) based on sensing data (SD) regarding the reference blade.

[0212] As some examples, the reference blade model generation unit (321) can perform modeling for each of a plurality of surfaces included in the reference blade based on sensing data (SD) regarding the reference blade. In other words, the reference blade model generation unit (321) can perform modeling for each of the four surfaces included in the reference blade based on sensing data (SD) regarding the reference blade.

[0213] At this time, as described above, the reference blade model (BM_ref) may include a virtual straight line with respect to the reference blade and / or a virtual coordinate system with respect to the reference blade, and at this time, the virtual coordinate system may be generated based on the virtual straight line.

[0214] For example, the reference blade model generation unit (321) can generate eight virtual straight lines for the reference blade as the reference blade model (BM_ref). In other words, the reference blade model (BM_ref) generated by the reference blade model generation unit (321) can include eight virtual straight lines. Specifically, the reference blade model generation unit (321) can set three virtual straight lines for each side of the reference blade, and since some of these overlap (e.g., the right line of the first side (front side) and the left line of the second side (right side) overlap), when the number of such overlapping parts is deducted, the reference blade model (BM_ref) generated by the reference blade model generation unit (321) includes eight virtual straight lines.

[0215] As another example, the reference blade model generation unit (321) can generate four virtual coordinate systems for the reference blade as the reference blade model (BM_ref). That is, the reference blade model (BM_ref) generated by the reference blade model generation unit (321) can include four virtual coordinate systems. In other words, the virtual coordinate system is generated based on the center line among the virtual straight lines, and since one center line is set for each of the first side (front side) to the fourth side (rear side) of the reference blade, the reference blade model (BM_ref) includes four virtual coordinate systems.

[0216] Next, other blade models can be created (S300).

[0217] As some examples, the guitar blade model generation unit (322) can generate a guitar blade model (BM_else) based on sensing data (SD) about the guitar blade and a reference blade model (BM_ref).

[0218] For example, the guitar blade model generation unit (322) can generate a preliminary guitar blade model (BM_else_pre) by predicting the guitar blade model using the generated reference blade model (BM_ref), and generate a guitar blade model (BM_else) by correcting the preliminary guitar blade model (BM_else_pre) based on sensing data (SD) regarding the guitar blade.

[0219] At this time, the guitar blade model generation unit (322) can generate a preliminary guitar blade model (BM_else_pre) using a rotation matrix such as the aforementioned <Mathematical Formula 1>, and can generate a guitar blade model (BM_else) by correcting the preliminary guitar blade model (BM_else_pre) using a correction algorithm based on the recursive least square method, etc.

[0220] Next, the relative position can be calculated using the blade model (S400).

[0221] As some examples, the relative position calculation module (330) can calculate the relative position (RL) based on a blade model (BM) expressed in the form of a virtual coordinate system for the first surface (front surface) of the first guitar blade and an inertial coordinate system in which a GPS position measured by a GPS sensor of the drone (200) is defined.

[0222] Detailed explanation is omitted.

[0223]

[0224] Figure 12 is a flowchart of a blade modeling method according to several other embodiments of the present invention. Each step of Figure 12 may be performed by a drone (200) or a blade modeling device (300). For convenience, Figure 12 depicts the drone (200) performing each step. Below, overlapping content is omitted and briefly described.

[0225] A drone (200) can model the blades of a wind turbine. A wind turbine includes at least one blade. The drone (200) can model the entire blade by applying the modeling results of one blade to other blades.

[0226] Specifically, referring to FIG. 1, FIG. 2 and FIG. 12, first, shooting data for the first surface of the blade can be acquired at multiple points in time (S500).

[0227] As an example, the drone (200) can acquire photographic data for the first side of the blade at multiple points in time.

[0228] For example, the drone (200) can acquire image data taken of the first surface while flying along the first surface of the blade.

[0229] The drone (200) can model the first surface as a virtual straight line. In other words, the result of the drone (200) modeling the first surface of the blade may be in the form of a virtual straight line. In this case, the virtual straight line can be expressed by the following <Mathematical Formula 2>.

[0230] <Mathematical Formula 2>

[0231]

[0232] At this time, in <Mathematical Formula 2>, p0=(x0, y0, z0) is a reference point, and u is a unit vector representing the slope of the virtual straight line. t is a scalar parameter. The reference point is the average of multiple position data acquired from the shooting data. u can be determined as the left singular vector corresponding to the largest singular value by performing SVD (Singular Value Decomposition) on the matrix representing the difference between the position data and p0.

[0233] Next, the first side of the blade can be modeled (S600).

[0234] In some examples, the drone (200) may generate at least one virtual straight line for the first surface of the blade. For example, the drone (200) may model the first surface by generating a centerline, a left line, and a right line for the first surface of the blade.

[0235] At this time, the drone (200) can create a virtual straight line representing the center line using the center points of the blade box recognized in the image data, can create a virtual straight line representing the left line using the center points of the left corner of the blade box, and can create a virtual straight line representing the priority using the center points of the right corner of the blade box. The blade box represents the blade recognized in the image data.

[0236] Next, the drone (200) can model the second side of the blade (S700).

[0237] As some examples, the drone (200) may model the second surface as a virtual straight line parallel to the virtual straight line for the first surface or as a virtual straight line orthogonal to the virtual straight line for the first surface.

[0238] When the second side is the left side of the first side, the drone (200) can model the second side by projecting the center line, right line, and left line of the first side onto the second side based on the right line of the second side. When the second side is the right side of the first side, the drone (200) can model the second side by projecting the center line, right line, and left line of the first side onto the second side based on the left line of the second side. When the second side is the rear side of the first side, the drone (200) can model the second side so that the center lines, right line, and left lines of the first and second sides are parallel.

[0239] The above description is merely an example of the technical idea of ​​the present embodiment, and those skilled in the art will appreciate that various modifications and variations can be made without departing from the essential characteristics of the present embodiment. Therefore, the present embodiments are not intended to limit the technical idea of ​​the present embodiment, but rather to explain it, and the scope of the technical idea of ​​the present embodiment is not limited by these embodiments. The scope of protection of the present embodiment should be interpreted by the claims below, and all technical ideas within a scope equivalent thereto should be interpreted as being included in the scope of rights of the present embodiment.

Claims

1. A data collection module that receives sensing data from a drone for a reference blade included in a wind turbine; and A modeling module for generating a blade model by performing modeling on the wind turbine based on the sensing data, The above modeling module, A reference blade model generation unit that generates a reference blade model by performing modeling on the above reference blade, A blade model generation unit for generating a blade model for at least one other blade included in the wind turbine based on the reference blade model, The blade model includes at least one virtual straight line set along each of the plurality of faces included in the blade and at least one virtual coordinate system for each of the plurality of faces determined based on the virtual straight line. Blade modeling device.

2. In paragraph 1, The above sensing data is, Contains shooting data captured from a camera included in the above drone, The above reference blade model generation unit, Using the above shooting data, position data for the first measurement surface included in the reference blade is measured, Based on the position data for the first measurement surface measured above, a virtual straight line for the first measurement surface is set. Blade modeling device.

3. In paragraph 2, The above reference blade model generation unit, Based on the first point in time of the above shooting data, Recognize the Blade Box from the above shooting data, Determine the center point of the above recognized blade box, Measure the first location data, which is the location data of the above-determined central point, Based on the first location data, a center line, which is a virtual straight line for the first measurement surface, is set. Blade modeling device.

4. In paragraph 3, The above reference blade model generation unit, Based on a second point in time that is different from the first point in time above, Recognize the blade box from the above shooting data, Determine the center point of the above recognized blade box, Measure the second location data, which is the location data of the above-determined central point, Setting the center line through regression analysis using the first location data and the second location data Blade modeling device.

5. In paragraph 4, The above reference blade model generation unit, When setting a virtual straight line for a second measurement plane different from the first measurement plane included in the above reference blade, Using the above shooting data, position data for the second measurement surface is measured, Setting a virtual straight line for the second measurement surface based on position data for the second measurement surface measured above and a plurality of virtual straight lines for the first measurement surface including the center line Blade modeling device.

6. In paragraph 5, A plurality of virtual straight lines for the first measurement surface including the center line are, The center line includes a left line, which is a virtual straight line based on the left edge of the blade box, and a priority line, which is a virtual straight line based on the right edge of the blade box. Blade modeling device.

7. In paragraph 5, The above reference blade model generation unit, A plurality of preliminary virtual straight lines for the second measurement surface are derived based on the position data for the second measurement surface measured above, Correcting a plurality of preliminary virtual straight lines for the second measurement plane using at least one of a parallel translation technique and an orthogonal projection technique based on a plurality of virtual straight lines for the first measurement plane. Blade modeling device.

8. In paragraph 3, The above reference blade model generation unit, The point where the nose of the wind turbine and the center line meet is set as the origin, and the virtual coordinate system is set for each of the plurality of surfaces included in the reference blade with the center line as one axis, The above guitar blade model generation unit, A prediction unit that predicts a preliminary guitar blade model by rotating the virtual coordinate system for each of the plurality of surfaces by a predetermined angle. Blade modeling device.

9. In paragraph 8, The above data collection module, Receive more drone sensing data for the above-mentioned other blades, The above guitar blade model generation unit, Further comprising a correction unit that corrects the predicted preliminary guitar blade model using the drone's sensing data for the guitar blade to generate the guitar blade model. Blade modeling device.

10. In paragraph 9, The above correction part, Correcting the preliminary guitar blade model using the recursive least square method. Blade modeling device.

11. A method for modeling one blade of a wind turbine, A step of acquiring photographing data for a first surface of the blade at multiple points in time; A step of modeling the first surface with a virtual straight line for the first surface; and A step of modeling a second surface as a virtual straight line parallel to a virtual straight line for the first surface or a virtual straight line orthogonal to the virtual straight line for the first surface. How to model a blade.

12. In paragraph 11, The above virtual straight line is expressed by a reference point and a vector, The step of modeling the first surface is: Generate multiple location data from the shooting data for the first surface, Calculate the reference point as an average of the above multiple location data, Characterized in that the vector is calculated using the difference between the above location data and the above average. How to model a blade.

13. In paragraph 11, The step of modeling the first surface is: Model the center line, priority line and left line for the first surface above, The step of modeling the second surface is: If the second surface is the left surface of the first surface, the center line, right line, and left line of the first surface are projected onto the second surface based on the right line of the second surface to model the second surface. When the second surface is the right surface of the first surface, the second surface is modeled by projecting the center line, right line, and left line of the first surface onto the second surface based on the left line of the second surface. How to model a blade.

14. In paragraph 11, The step of modeling the first surface is: Model the center line, priority line and left line for the first surface above, The step of modeling the second surface is: When the second surface is the rear surface of the first surface, the second surface is modeled so that the center line, right and left lines of the first surface and the second surface are parallel. How to model a blade.

Images