A fan three-dimensional information reconstruction method based on shadow geometry constraint

Abstract

The present application relates to the technical field of remote sensing image geometric inversion, in particular to a fan three-dimensional information reconstruction method based on shadow geometric constraint, which comprises the following steps: first, obtaining remote sensing images containing target fans, identifying the tower shadow and corresponding blade shadow of each fan and extracting shadow vectors; further, establishing a fan coordinate system and constructing the conversion relationship between the fan coordinate system and the remote sensing image coordinate system; under the condition that three blades are mutually 120 degrees and the solar elevation angle is missing, constructing a shadow geometric constraint model according to the projection relationship of spatial vectors along the sunlight direction to the ground plane; on this basis, establishing a nonlinear constraint equation group containing the fan tower height, blade radius, fan azimuth angle and solar projection direction parameters, obtaining the fan tower height and blade radius through optimization solution, and realizing the three-dimensional information reconstruction of the fan. The present application does not need to know the solar elevation angle, and can complete the fan structure parameter inversion only by relying on a single remote sensing image, and has the characteristics of high calculation precision and strong applicability.

Description

Technical Field

[0001] This invention relates to the field of remote sensing image geometric inversion technology, specifically to a method for reconstructing three-dimensional information of wind turbines based on shadow geometric constraints. Background Technology

[0002] Wind power generation, as an important component of clean energy, occupies a crucial position in the new energy power generation system. With the continuous expansion of wind farms, higher demands are placed on the monitoring of the operational status of wind turbine generators (hereinafter referred to as wind turbines), the evaluation of structural parameters, and the operation and maintenance management. Among these, the tower height and blade radius are important parameters describing the three-dimensional structural characteristics of wind turbines. These parameters not only relate to the power generation efficiency and structural safety of wind turbines but also directly affect applications such as wind farm layout optimization, wake effect analysis, and digital wind farm modeling. Therefore, how to quickly and accurately obtain the structural parameters of wind turbines has become an important research problem in the field of wind power monitoring and remote sensing applications.

[0003] In existing technologies, one approach involves using drones equipped with lidar or visual measurement devices to measure wind turbine structures. However, in deep-sea wind farm environments, the operation of drones is significantly limited because wind turbines are typically located far from the mainland. During hovering, drones usually rely on optical flow positioning modules to acquire surface feature information to maintain a stable position, but optical flow positioning requires stable and distinct ground texture features. However, sea surface texture is weak and constantly changing due to wave motion, making it difficult for drones to obtain stable visual positioning information. This hinders their ability to hover continuously in a fixed position, thus affecting the stability and measurement accuracy of data acquired by the drone-borne equipment (such as lidar or visual measurement devices). Therefore, the application of drone-based measurement methods in deep-sea wind farm environments is somewhat limited.

[0004] Another approach utilizes target projection information from remote sensing imagery for geometric measurements. Under remote sensing conditions, satellites or airborne platforms typically acquire ground images from fixed observation angles. By analyzing the projection relationships formed by the target on the ground, the spatial structural parameters of the target can be retrieved. For offshore wind turbines, due to the open sea environment and lack of tall obstacles, the shadows cast by the turbine towers and blades under sunlight usually have relatively clear and regular geometric shapes, and the shadow boundaries are easily identifiable. Therefore, it is suitable to retrieve structural parameters through shadow geometric relationships.

[0005] Therefore, in the context of offshore wind farms, it is necessary to study how to establish stable geometric constraints using only wind turbine shadow information from remote sensing imagery, without relying on UAV measurements and complex multi-source data, and to accurately invert structural parameters such as wind turbine tower height and blade radius. In view of this, this invention proposes a method for reconstructing three-dimensional information of wind turbines based on shadow geometric constraints. Summary of the Invention

[0006] The purpose of this invention is to provide a method for reconstructing three-dimensional information of wind turbines based on shadow geometric constraints, which solves the technical problem that existing shadow-based wind turbine structural parameter measurement methods rely on known solar altitude angles, making it difficult to accurately obtain tower height parameters and blade radius when the solar altitude angle corresponding to the image is missing or inaccurate.

[0007] To achieve the above objectives, the present invention provides the following technical solution:

[0008] In a first aspect, the present invention provides a method for reconstructing three-dimensional information of a wind turbine based on shadow geometric constraints, comprising the following steps:

[0009] S101: Acquire a remote sensing image containing the target wind turbine and determine the spatial resolution of the image; identify the wind turbine tower shadow and the shadow of the three fan blades in the remote sensing image; and extract the tower shadow vector and the three fan blade shadow vector.

[0010] S102: Establish a wind turbine coordinate system with the wind turbine base as the origin, the z-axis perpendicular to the ground and upward, and the x-axis parallel to the rotation axis of the wind turbine blades. By the right-hand rule, the y-axis is located in the plane where the three blades are located. Based on the structural feature that the three blades of the wind turbine are evenly distributed in space at 120°, establish the spatial vector of the wind turbine tower and the three blades.

[0011] S103: Define the direction vector of sunlight. Based on the geometric relationship between the spatial vector projected along the direction of sunlight onto the ground plane to form the ground shadow vector, calculate the ground shadow vector of the wind turbine tower and the three fan blades on the ground plane.

[0012] S104: Establish the coordinate transformation relationship between the wind turbine coordinate system and the map image coordinate system, and convert the ground shadow vector representation in the wind turbine coordinate system into the map shadow vector in the map image coordinate system through a rotation matrix;

[0013] S105: Based on the map shadow vector, establish a set of nonlinear constraint equations including tower height parameters, blade radius parameters, wind turbine azimuth angle parameters, and solar projection direction parameters. Solve the set of equations using nonlinear optimization methods, and calculate the actual three-dimensional structural parameters of the wind turbine by combining the image spatial resolution.

[0014] As a preferred technical solution of the present invention, the shadows generated by the wind turbine tower and the fan blade in the remote sensing image are identified, and the shadow vector is calculated according to the endpoint coordinates of the shadow area: the shadow vector of the tower is obtained by taking the position of the wind turbine base as the starting point of the shadow vector and the position of the shadow of the fan blade shaft as the ending point; the shadow vector of the fan blade is obtained by taking the position of the shadow of the fan blade shaft as the starting point of the vector and the position of the end of the shadow of the fan blade as the ending point.

[0015] As a preferred technical solution of the present invention, since the three fan blades of the wind turbine are evenly distributed on the rotor hub and connected to the tower, the distance between their corresponding shadows is relatively close. After extracting the shadow vectors of the fan blades and the tower, the distance between each shadow vector is calculated, and the shadow combination that meets the preset error range is selected to determine that the tower shadow and the fan blade shadow belong to the same wind turbine structure.

[0016] As a preferred embodiment of the present invention, the relationship between the tower vector and the spatial vector of the three fan blades, representing the shadow vector on the ground plane, is calculated as follows:

[0017] Let any spatial vector be: ,in: This represents the component in the x-direction; Indicates the component in the y-direction; This represents the component in the z-direction;

[0018] The direction vector of sunlight is: ,in: and These represent the components of the sunlight direction vector along the x and y axes, respectively. This indicates that the direction vector is pointing towards the ground along the negative z-axis, meaning the z-axis component is -1;

[0019] The ground shadow vector, which is the spatial vector projected onto the ground plane along the direction of sunlight, is: .

[0020] As a preferred technical solution of the present invention, a unified projection geometric relationship is constructed based on the projection relationship between the spatial vectors of the wind turbine tower and the three blades under the same sunlight direction, so that all shadow vectors satisfy the same sunlight direction parameter constraint, and the x and y components of the shadow vectors are used as geometric constraint conditions for solving the wind turbine structural parameters.

[0021] As a preferred embodiment of the present invention, a wind turbine coordinate system O-xyz is established with the wind turbine base as the origin.

[0022] The spatial vector representation of the wind turbine tower is: ;

[0023] The spatial vector representation of the three fan blades is:

[0024] ;

[0025] ;

[0026] ;

[0027] Where: H is the height of the wind turbine tower, and L is the blade radius parameter. Let the angle between any fan blade and the y-axis be [angle]. Following a counter-clockwise order, the angles between the remaining two fan blades and the y-axis are as follows: ; .

[0028] As a preferred embodiment of the present invention, the transformation relationship between the wind turbine coordinate system and the map image coordinate system is realized through a rotation matrix, specifically as follows:

[0029] The wind turbine coordinate system is rotated around its z-axis by the wind turbine azimuth parameter φ, and then rotated 180° around its x-axis to coincide with the map image coordinate system. The ground shadow vector in the wind turbine coordinate system is converted into the map shadow vector in the map image coordinate system through the rotation matrix.

[0030] As a preferred embodiment of the present invention, the construction logic of the nonlinear constraint equation system is as follows:

[0031] After establishing the ground shadow vectors of the wind turbine tower and three blades and transforming them to the map image coordinate system, the theoretical shadow vectors are used to establish equality constraints with the tower shadow vectors and three blade shadow vectors extracted from the remote sensing image. Based on the equality constraints, a set of nonlinear constraint equations is constructed, including tower height parameters, blade radius parameters, wind turbine azimuth angle parameters, and solar projection direction parameters.

[0032] As a preferred technical solution of the present invention, the actual three-dimensional structural parameters include tower height parameters and fan blade radius parameters. The tower height parameters and fan blade radius parameters obtained by solving the nonlinear constraint equations are multiplied by the spatial resolution of the remote sensing image to obtain the tower height parameters and fan blade radius parameters.

[0033] Compared with the prior art, the beneficial effects of the present invention are:

[0034] This invention utilizes the structural feature of the three fan blades of a wind turbine being distributed at 120° intervals to correlate the three fan blades in a remote sensing image and establish a spatial geometric relationship between the wind turbine coordinate system and the image coordinate system. Simultaneously, it constructs a shadow geometric constraint model by combining the geometric law of spatial vectors projected onto the ground along the direction of sunlight. This allows for the unified incorporation of wind turbine tower height, fan blade radius, wind turbine azimuth angle, and solar projection direction parameters into a single set of nonlinear constraint equations for joint solution. Therefore, even with an unknown solar altitude angle, it can achieve the inversion calculation of tower height parameters and fan blade radius using only a single remote sensing image. Compared to measurement methods that rely on known solar altitude angles or multi-view images, this reduces data acquisition limitations and improves the applicability and stability of wind turbine three-dimensional structural parameter estimation. Attached Figure Description

[0035] Figure 1 This is a flowchart illustrating the physical model reasoning process of the present invention;

[0036] Figure 2 This is a schematic diagram of the wind turbine's own coordinate system according to the present invention;

[0037] Figure 3 This is a schematic diagram illustrating the relationship between the map coordinate system and the wind turbine coordinate system of this invention;

[0038] Figure 4 This is a flowchart illustrating the solution process for the tower height and blade radius parameters of this invention. Detailed Implementation

[0039] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0040] In the description of this invention, it should be noted that the terms "vertical," "upper," "lower," "horizontal," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this invention.

[0041] In the description of this invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0042] Example 1

[0043] Please see Figure 1 This invention provides a technical solution: a method for reconstructing three-dimensional information of wind turbines based on shadow geometric constraints, applied to high-resolution remote sensing image environments. By analyzing the shadow geometric relationship formed by the wind turbine tower and blades on the ground, the method realizes the inversion calculation of the wind turbine tower height and blade radius, including the following steps:

[0044] S101: Acquire a remote sensing image containing the target wind turbine and determine the image spatial resolution. Identify the wind turbine tower shadow and the shadows of the three fan blades in the remote sensing image, and extract the tower shadow vector and the three fan blade shadow vectors, respectively represented as... , , and ,like Figure 3 As shown;

[0045] In this embodiment, the remote sensing image is first subjected to grayscale enhancement processing to increase the brightness difference between the shadow area and the background area. Then, an edge detection algorithm is used to calculate the gradient of the image to identify the shadow boundary region. Further, a region segmentation method is used to extract the shadow areas of the wind turbine tower and the fan blades. After extracting the shadow areas, the shadow vector is obtained by calculating the difference between the coordinates of the endpoints of the shadow areas. Specifically, the shadow vector starts at the bottom of the wind turbine and ends at the shadow position of the fan blade shaft, resulting in the wind turbine tower shadow vector. Taking the shadow position of the fan shaft as the starting point of the shadow vector and the end position of the shadow position as the ending point, following a counter-clockwise order, the shadow vector of the first fan blade is... The shadow vector of the second fan blade is The shadow vector of the third fan blade is In actual remote sensing imagery, due to the fixed angle of sunlight, the shadows cast on the ground by the wind turbine tower and blades exhibit a stable geometric relationship. Therefore, extracting the tower shadow vector and the shadow vectors of the three blades can provide fundamental data for subsequent establishment of a spatial vector projection model and construction of a system of nonlinear constraint equations.

[0046] S102: Establish a wind turbine coordinate system with the wind turbine base as the origin, the z-axis perpendicular to the ground and upward, the x-axis parallel to the rotation axis of the wind turbine blades, and the y-axis located in the plane containing the three blades. Based on the structural feature that the three blades of the wind turbine are evenly distributed in space at 120°, establish a spatial vector representation of the wind turbine tower and the three blades.

[0047] This can be understood as follows: a wind turbine generator typically consists of a tower and three blades, with the three blades evenly distributed at 120° intervals in space. For example... Figure 2 As shown, a shadow geometric constraint model is constructed using structural features. A wind turbine coordinate system O-xyz is established with the turbine base as the origin: where the z-axis is perpendicular to the ground and upwards, the x-axis is parallel to the wind turbine's rotation axis, and the y-axis lies in the plane containing the three turbine blades. The height of the wind turbine tower is H, and the blade radius parameter is L; one of the blades makes an angle of θ with the y-axis. Then, following a counter-clockwise order, the angles between the remaining two blades and the y-axis can be denoted as follows:

[0048] ;

[0049] .

[0050] In the wind turbine coordinate system, the spatial vector representation of the wind turbine tower is as follows: The spatial vector representations of the three fan blades are as follows:

[0051] ;

[0052] ;

[0053] ;

[0054] It should be noted that: here it is assumed that the included angle between any two of the three fan blades is 120°, which is true in reality;

[0055] S103: Define the direction vector of sunlight. Based on the geometric relationship of the spatial vector projected onto the ground plane along the direction of sunlight to form the ground shadow vector, calculate the ground shadow vector of the wind turbine tower and the ground shadow vector of the three fan blades on the ground plane.

[0056] For example, during the acquisition of remote sensing images, ground objects cast shadows on the ground under sunlight. A shadow projection model is established using the projection relationship of spatial vectors in the direction of sunlight. It is assumed that any spatial vector in space... : ;in: This represents the component in the x-direction; Indicates the component in the y-direction; This represents the component in the z-direction;

[0057] Sunlight direction vector: ;in: and These represent the components of the sunlight direction vector along the x and y axes, respectively. This indicates that the direction vector is pointing towards the ground along the negative z-axis, meaning the z-axis component is -1;

[0058] Definition: Spatial vector The starting point A is: The destination B is: Draw a direction vector through the starting point A. A straight line that is perpendicular to the ground plane. The intersection point is denoted as the ground shadow vector. That is, the projection point of point A on the ground. Similarly, the projection of point B onto the ground is denoted as... .

[0059] According to the equation of a straight line in space, we can obtain:

[0060] ;

[0061] ;

[0062] Therefore, spatial vectors In the direction of sunlight Ground shadow vector projected onto the ground for:

[0063] ; (1)

[0064] This expression describes the pattern of shadow formation of a spatial vector under sunlight conditions.

[0065] Therefore, the spatial vector representation of the wind turbine tower (H) and the spatial vector representation of the fan blades (L1, L2, L3) are ground shadow vectors. It can be represented as:

[0066] ;

[0067] S104: Establish the coordinate transformation relationship between the wind turbine coordinate system and the map image coordinate system. Use a rotation matrix to convert the ground shadow vector of the tower and the ground shadow vector of the three fan blades in the wind turbine coordinate system into the map shadow vector of the tower and the map shadow vector of the three fan blades in the map image coordinate system.

[0068] Specifically, in remote sensing imagery, the shadow distribution of wind turbines is typically represented using the map image coordinate system, while the structural parameters of the wind turbines are defined in the wind turbine coordinate system. Therefore, it is necessary to establish a geometric transformation relationship between the wind turbine coordinate system and the map image coordinate system to achieve a unified expression between the shadow geometric model and the image measurement data, such as... Figure 3 As shown, O-xyz is the windmill coordinate system, O I -xyz represents the map's own coordinate system (without loss of generality, the x-axis is defined as rightward, the y-axis as downward, and the z-axis as perpendicular to the image and inward). Therefore, O-xyz, after rotating φ around its z-axis and then 180° around its x-axis, can be converted to O. I -xyz coordinate system. This converts the windmill coordinate system O-xyz to the map's own coordinate system O. I The rotation matrix R corresponding to -xyz O2OI ,writing:

[0069] ;

[0070] Then the ground shadow vector in the O-xyz wind turbine coordinate system Convert to O I Map shadow vector in the -xyz map image coordinate system Can be written as:

[0071] (2)

[0072] Through this coordinate transformation, the ground shadow vectors of the wind turbine tower and the three blades can be uniformly represented as two-dimensional map shadow vectors in the map image coordinate system, thereby enabling a direct correspondence between the theoretical shadow model and the shadow vectors extracted from the remote sensing image.

[0073] S105: Based on the shadow vector of the tower map and the shadow vector of the three blade maps, establish a set of nonlinear constraint equations including tower height parameters, blade radius parameters, wind turbine azimuth angle parameters, and solar projection direction parameters. Solve the set of equations using a nonlinear optimization method to obtain the wind turbine tower height and blade radius. Combined with the image spatial resolution, calculate the actual three-dimensional structural parameters of the wind turbine, including tower height parameters and blade radius parameters.

[0074] Specifically, after obtaining the transformation relationship between the wind turbine coordinate system and the map image coordinate system, the shadow projection expression of the wind turbine tower and blades under sunlight is established, thereby realizing the correspondence between the wind turbine structural parameters and the image shadow features.

[0075] In the wind turbine coordinate system O-xyz, the tower and three blades of the wind turbine are all affected by the same direction of sunlight. Therefore, their shadow vectors satisfy a unified geometric constraint: all shadow vectors are determined by the same solar projection direction, and the shadow vectors in the direction of sunlight are all within the same direction. The ground shadow vector of the downward projection is The projection in the wind turbine coordinate system is transformed to the map coordinate system according to formula (2) to obtain the tower map shadow vector. and the shadow vectors of the three fan-shaped maps :

[0076] (3)

[0077] At this point, we have obtained the tower height parameter H, and the vector representations of the first blade L1, the second blade L2, and the third blade L3 in the map coordinate system. By identifying the wind turbine's tower and blades, we can obtain their corresponding shadow vectors. , , and According to formula (3), the following equation is obtained:

[0078] (4)

[0079] The above system of equations includes unknowns such as tower height parameter H, fan blade radius parameter L, fan azimuth angle parameter φ, and the angle between any fan blade and the y-axis. The components t1 and t2 of the sunlight projection direction vector can be solved using nonlinear optimization to obtain the tower height parameter H, the fan blade radius parameter L, and the sunlight projection direction vector (i.e., the solar altitude angle). Here, H and L are in image pixels. Multiplying them by the spatial resolution of the map yields the actual length parameters, enabling the measurement of the tower height parameter and fan blade radius based on ground shadows.

[0080] In actual remote sensing images, there are cases where the shadow of a certain fan blade overlaps with the shadow of the tower. In this case, it is impossible to extract the shadow vector of that fan blade. In this case, the number of effective equations in the equation set is reduced to 6, and the number of unknown parameters is also 6. The equation set still maintains full rank, so the wind turbine structural parameters can still be solved by the above nonlinear optimization method.

[0081] Example 2

[0082] like Figure 4 As shown, this embodiment establishes geometric constraints using the wind turbine shadow vector extracted from remote sensing imagery and calculates the three-dimensional structural parameters of the wind turbine using a spatial projection model. The steps include:

[0083] Step 1: Determine the spatial resolution S of the map, acquire remote sensing image data containing the target wind turbine, and read the spatial resolution parameter S of the image. The spatial resolution S represents the actual ground length corresponding to a single pixel in the remote sensing image, and is used to realize the conversion between the image pixel scale and the real geographic scale.

[0084] Step 2: Obtain the wind turbine shadow vector. Identify the shadows of the wind turbine tower and the three fan blades in the remote sensing image, and extract the corresponding shadow vectors. Specifically, by determining the bottom position of the wind turbine as the starting point of the shadow vector and the position of the fan blade shaft shadow as the ending point, the tower shadow vector is obtained. Using the shadow position of the fan shaft as the starting point of the shadow vector and the end position of the shadow of the fan blade as the ending point, the shadow vectors of the three fan blades are obtained in a counterclockwise order. , and .

[0085] Step 3: Solve for the wind turbine structural parameters. Based on the aforementioned spatial projection model, establish the spatial vector representation of the wind turbine tower and the three blades to represent the shadow relationship formed under sunlight. Then, construct a set of nonlinear constraint equations containing the tower height parameter H, the blade radius parameter L, and the sunlight projection direction parameter according to formula (4). Solve the set of equations using a nonlinear optimization method to obtain the tower height parameter H and the blade radius parameter L.

[0086] Step 4: Calculate the actual structural dimensions of the wind turbine. The obtained parameters H and L are expressed in pixels. Therefore, multiply H and L by the image spatial resolution S to obtain the actual height of the wind turbine tower and the actual radius of the wind turbine blades. This realizes the calculation of the three-dimensional structural parameters of the wind turbine. The inversion calculation of tower height parameters and blade radius parameters can be completed by relying only on the shadow information of a single remote sensing image, thereby realizing the automatic acquisition of the three-dimensional structural parameters of the wind turbine.

[0087] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed in this invention can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0088] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0089] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A method for reconstructing three-dimensional information of a wind turbine based on shadow geometric constraints, characterized in that: Includes the following steps: S101: Acquire a remote sensing image containing the target wind turbine and determine the spatial resolution of the image; identify the wind turbine tower shadow and the shadow of the three fan blades in the remote sensing image; and extract the tower shadow vector and the three fan blade shadow vector. S102: Establish a wind turbine coordinate system with the wind turbine base as the origin, the z-axis perpendicular to the ground and upward, and the x-axis parallel to the rotation axis of the wind turbine blades. By the right-hand rule, the y-axis is located in the plane where the three blades are located. Based on the structural feature that the three blades of the wind turbine are evenly distributed in space at 120°, establish the spatial vector of the wind turbine tower and the three blades. S103: Define the direction vector of sunlight. Based on the geometric relationship between the spatial vector projected along the direction of sunlight onto the ground plane to form the ground shadow vector, calculate the ground shadow vector of the wind turbine tower and the three fan blades on the ground plane. S104: Establish the coordinate transformation relationship between the wind turbine coordinate system and the map image coordinate system, and convert the ground shadow vector in the wind turbine coordinate system into the map shadow vector in the map image coordinate system through a rotation matrix; S105: Based on the map shadow vector, establish a set of nonlinear constraint equations including tower height parameters, blade radius parameters, wind turbine azimuth angle parameters, and solar projection direction parameters. Solve the set of equations using nonlinear optimization methods, and calculate the actual three-dimensional structural parameters of the wind turbine by combining the image spatial resolution.

2. The method for reconstructing three-dimensional information of a wind turbine based on shadow geometric constraints according to claim 1, characterized in that: The shadows cast by wind turbine towers and blades in remote sensing images are identified, and shadow vectors are calculated based on the endpoint coordinates of the shadow areas: the shadow vector of the tower is obtained by taking the position of the wind turbine base as the starting point of the shadow vector and the position of the shadow of the blade shaft as the ending point; the shadow vector of the blade is obtained by taking the position of the shadow of the blade shaft as the starting point of the vector and the position of the end of the shadow of the blade as the ending point.

3. The method for reconstructing three-dimensional information of a wind turbine based on shadow geometric constraints according to claim 1, characterized in that: Since the three blades of the wind turbine are evenly distributed on the rotor hub and connected to the tower, the distance between their corresponding shadows is relatively close. After extracting the shadow vectors of the blades and the tower, the distance between each shadow vector is calculated, and the shadow combination that meets the preset error range is selected to determine that the tower shadow and the blade shadow belong to the same wind turbine structure.

4. The method for reconstructing three-dimensional information of a wind turbine based on shadow geometric constraints according to claim 1, characterized in that: Establish a wind turbine coordinate system O-xyz with the wind turbine base as the origin. The spatial vector representation of the wind turbine tower is: ; The spatial vector representation of the three fan blades is: ； ； ； Where: H is the height of the wind turbine tower, and L is the blade radius parameter. Let the angle between any fan blade and the y-axis be [angle]. Following a counter-clockwise order, the angles between the remaining two fan blades and the y-axis are as follows: ; .

5. The method for reconstructing three-dimensional information of a wind turbine based on shadow geometric constraints according to claim 1, characterized in that: The relationship between the spatial vector of the tower and the shadow vector of the three fan blades projected onto the ground plane is calculated as follows: Let any spatial vector be: ,in: This represents the component in the x-direction; Indicates the component in the y-direction; This represents the component in the z-direction; The direction vector of sunlight is: ,in: and These represent the components of the sunlight direction vector along the x and y axes, respectively. This indicates that the direction vector is pointing towards the ground along the negative z-axis, meaning the z-axis component is -1; The ground shadow vector, which is the spatial vector projected onto the ground plane along the direction of sunlight, is: .

6. The method for reconstructing three-dimensional information of a wind turbine based on shadow geometric constraints according to claim 5, characterized in that: Based on the projection relationship between the spatial vectors of the wind turbine tower and the three fan blades under the same sunlight direction, a unified projection geometry relationship is constructed so that all shadow vectors satisfy the same sunlight direction parameter constraint.

7. The method for reconstructing three-dimensional information of a wind turbine based on shadow geometric constraints according to claim 1, characterized in that: The transformation between the wind turbine coordinate system and the map image coordinate system is achieved through a rotation matrix, specifically as follows: The wind turbine coordinate system is rotated around its z-axis by the wind turbine azimuth parameter φ, and then rotated 180° around its x-axis to coincide with the map image coordinate system. The ground shadow vector in the wind turbine coordinate system is converted into the map shadow vector in the map image coordinate system through the rotation matrix.

8. The method for reconstructing three-dimensional information of a wind turbine based on shadow geometric constraints according to claim 1, characterized in that: The construction logic of the nonlinear constraint equation system: After establishing the ground shadow vectors of the wind turbine tower and three blades and transforming them to the map image coordinate system, the theoretical shadow vectors are used to establish equality constraints with the tower shadow vectors and three blade shadow vectors extracted from the remote sensing image. Based on the equality constraints, a set of nonlinear constraint equations is constructed, including tower height parameters, blade radius parameters, wind turbine azimuth angle parameters, and solar projection direction parameters.

9. The method for reconstructing three-dimensional information of a wind turbine based on shadow geometric constraints according to claim 8, characterized in that: The actual three-dimensional structural parameters include the tower height parameter and the fan blade radius parameter. The tower height parameter and the fan blade radius parameter obtained by solving the nonlinear constraint equations are multiplied by the spatial resolution of the remote sensing image to obtain the tower height parameter and the fan blade radius parameter.

Images