Method, system and device for inverting material inventory distribution of offshore wind turbines based on satellite imagery

Abstract

The present invention discloses a method, system, and device for inverting the material inventory distribution of offshore wind turbines. The method includes: obtaining remote sensing image data and offshore wind turbine height and diameter data; determining wind turbine point distribution data and distinguishing different wind turbine farms; obtaining the wind turbine's residence effect point and wind turbine point, and determining the optimal threshold for calculating the wind turbine height and diameter; further calculating the binary image of the wind turbine's residence effect point and wind turbine point based on the optimal threshold, and measuring the wind turbine height, diameter, and width in areas without public wind turbine data; inferring the weight of the rotor, nacelle, and tower based on the wind turbine height and diameter; determining the percentage relationship of each material contained in the rotor, nacelle, and tower; and obtaining the spatial distribution of the wind turbine's material inventory. The present invention can efficiently obtain existing material inventory distribution data of offshore wind turbines using satellite remote sensing images, providing an effective quantitative monitoring solution for the material inventory distribution of offshore wind turbines and the subsequent waste treatment and recycling of wind turbine decommissioning.

Description

Technical Field

[0001] The present invention relates to the fields of remote sensing image processing, computer modeling and material circulation technology, and in particular to a method, system and device for inverting the material inventory distribution of offshore wind turbines using, for example, SAR satellite image data. Background Art

[0002] In recent years, the total amount of renewable energy in the world has increased dramatically, mainly driven by environmental and climate goals. Offshore wind energy is a highly anticipated and rapidly maturing renewable energy technology that is expected to have a significant impact on the energy transition. This large-scale technological transformation has the potential to reduce human greenhouse gas emissions. However, the transition to a low-carbon society requires a large amount of metals and minerals in areas where a large amount of renewable energy infrastructure is urgently needed. Energy transition and the subsequent supply security and environmental impacts are also becoming increasingly concerned. The wind energy sector also faces increasing challenges in managing the installation waste materials (such as glass fiber in blades) generated by decommissioning wind turbines. Therefore, obtaining the distribution of existing material stocks of offshore wind turbines is of great significance for the subsequent treatment and recycling of wind turbine decommissioning waste.

[0003] To obtain the material requirements of wind turbines, there are currently multiple methods for converting wind energy scenarios into material requirements. In existing technologies, if the annual installed capacity of wind turbines is given, the related material requirements are usually directly determined by the material intensity per capacity unit; if the annual installed capacity is not given, the related material requirements can be derived from the input-output method based on life cycle assessment (LCA), economic model or dynamic material flow analysis (MFA) model. However, the current material requirements for different wind energy technologies usually ignore the hierarchical characteristics of wind power systems. The materials embedded in the technical system are usually distributed in the subsystems or subcomponents of the wind turbine, with different compositions and recycling potentials. In addition, although existing methods can quantify material requirements to a certain extent, they cannot obtain intuitive spatial distribution information of the materials in the wind turbine.

[0004] The disclosure of the above background technology content is only used to assist in understanding the concept and technical solution of the present invention. It does not necessarily belong to the prior art of this patent application. In the absence of clear evidence that the above content has been disclosed on the filing date of this patent application, the above background technology should not be used to evaluate the novelty and creativity of this solution. Summary of the Invention

[0005] In view of this, the present invention proposes a method, system and equipment for inverting the material inventory distribution of offshore wind turbines using satellite imagery. This solution can effectively use satellite remote sensing imagery to obtain existing material inventory data and spatial distribution information of offshore wind turbines over a large area, providing an effective quantitative monitoring solution for the material inventory distribution of offshore wind turbines and the subsequent treatment and recycling of waste from wind turbine decommissioning.

[0006] Specifically, the present invention provides the following technical solutions:

[0007] In a first aspect, the present invention provides a method for inverting material inventory distribution of an offshore wind turbine, the method comprising:

[0008] S1. Obtain satellite image data, publicly available height data and publicly available diameter data of offshore wind turbines; pre-process the satellite image data to obtain synthetic image data;

[0009] S2. Determine wind turbine point distribution data based on the synthetic image data, the public height data, and the public diameter data, and distinguish wind turbine farms based on the wind turbine point distribution data;

[0010] S3. Based on the wind turbine point distribution data and synthetic image data, obtain the wind turbine's dwell effect point and wind turbine point, calculate the wind turbine point height and wind turbine point diameter, and determine the height threshold and diameter threshold by combining the public height data and public diameter data;

[0011] S4. Based on the height threshold and the diameter threshold, calculate the binary image of the fan's stop effect point and the binary image of the fan point, and measure the fan height data, fan diameter data, and fan width data in the area without public data;

[0012] S5. Based on the publicly available wind turbine dataset, model the relationship between the publicly available height data, publicly available diameter data, and the rotor weight, nacelle weight, and tower weight. Based on the established model, use the wind turbine height data and wind turbine diameter data to estimate the rotor weight, nacelle weight, and tower weight.

[0013] S6. Determine the percentage relationship of each substance contained in the rotor, nacelle, and tower;

[0014] S7. Based on the rotor weight, nacelle weight, tower weight estimated in S5 and the percentage relationship of each material in S6, obtain the spatial distribution of the wind turbine material inventory.

[0015] Preferably, in S1, the satellite image data is time series data, and the median of the time series data for the entire year is calculated as the synthetic image data.

[0016] Preferably, in S2, the method for determining the wind turbine point distribution data is:

[0017] S21, performing erosion and expansion operations on the synthetic image data to enhance the distribution range information of the wind turbine points;

[0018] S22, based on the fan point screening threshold, processing the synthetic image data into a binary image, and converting the fan point pixels into vector points;

[0019] S23, setting a first buffer zone for fan points and eliminating unreasonable fan points;

[0020] S24. Perform spatial clustering on the wind turbine points retained after the elimination to form a wind farm, and use the wind turbine point data retained after the elimination as wind turbine point distribution data.

[0021] Preferably, the corrosion and expansion operation mode is:

[0022] AB={x,y|(B) xy ∈A}

[0023]

[0024] Where A represents the synthetic image data, B represents the convolution kernel, and x and y represent the coordinate positions of the synthetic image data pixels.

[0025] Preferably, the S23 further includes:

[0026] Set the radius of the first buffer zone and remove points with less than 3 fan points in the first buffer zone. The specific method is:

[0027] WTPointsOut=Filter(buffer WTPointsIn (3km)>3)

[0028] Among them, WTPointsIn represents the fan point data before elimination, WTPointsOut represents the fan point data after elimination, buffer represents the buffer operation, and Filter represents the elimination operation.

[0029] Preferably, the radius of the first buffer zone is 3 km.

[0030] Preferably, in said S24, in the spatial clustering method, the wind turbine point sample set, the neighborhood parameters, and the distance measurement method are used as inputs, and the clusters are used as outputs.

[0031] Preferably, the S3 further includes:

[0032] S31. Based on the wind turbine point distribution data, establish a second buffer zone for each wind turbine point, and use the second buffer zone as a candidate area for a stay effect point and a wind turbine point.

[0033] S32. For each candidate area, obtain a binary image of the stay effect point and a binary image of the fan point in the fan point distribution data, convert the binary image of the stay effect point into a vector point, and then calculate the distance Dist in combination with the fan point in the fan point distribution data;

[0034] Obtain the satellite image angle data Angle according to the wind turbine point position in the wind turbine point distribution data, and calculate the height of the wind turbine point Height:

[0035] Heightt =Dist t *tan(Angle*π / 180),t∈[Thesh start ,Thesh end ];

[0036] Among them, t represents the image automatic threshold, t∈[Thesh start ,Thesh end ], Thesh start and Thesh end is the value of the synthetic image data, which is determined by the distribution range of the numerical values ​​of the wind turbine points in the synthetic image;

[0037] S33. Generate a rectangular bounding box based on the binary image of the wind turbine point in the wind turbine point distribution data, wherein the bounding box has the wind turbine point diameter and the nacelle width as sides; the wind turbine point diameter is obtained from the bounding box area and the bounding box perimeter, and the bounding box area and the bounding box perimeter are obtained from statistical data;

[0038] S34. Calculate the sum of the squares of the distances between the wind turbine point height and the public height data using the wind turbine point distribution data and the SAR median synthetic image data, and use the value of the synthetic image data with the minimum sum of the squares as the height threshold; calculate the sum of the squares of the distances between the wind turbine point diameter and the public diameter data, and use the value of the synthetic image data with the minimum sum of the squares as the diameter threshold.

[0039] Preferably, in S33, the fan point diameter Diameter is calculated as follows:

[0040]

[0041] The calculation method of cabin width is:

[0042]

[0043] Among them, area represents the area of ​​the bounding box, and perimeter represents the perimeter of the bounding box.

[0044] Preferably, the S4 further comprises:

[0045] S41. Based on the height threshold and the diameter threshold, recalculate the binary image of the dwell effect point and the binary image of the wind turbine point. For areas without public wind turbine data, repeat steps S33 and S34 to calculate the wind turbine height data, wind turbine diameter data, and wind turbine width data for which no public data is available.

[0046] S42. Calculate the median of the wind turbine height data, wind turbine diameter data, and wind turbine width data of all wind turbine points in each wind turbine farm, and use this median as the wind turbine height data, wind turbine diameter data, and wind turbine width data of each wind turbine point in the wind turbine farm, thereby ultimately obtaining the wind turbine height data, wind turbine diameter data, and wind turbine width data in areas without public data.

[0047] Preferably, in S5, the model is:

[0048] q=ap b

[0049] Where q represents the rotor weight, nacelle weight, or tower weight, p represents the height or diameter of the wind turbine, and a and b represent the parameters to be solved.

[0050] In a second aspect, the present invention further provides a system for inverting material inventory distribution of offshore wind turbines, the system comprising:

[0051] A data acquisition module is used to acquire satellite image data, publicly available height data and publicly available diameter data of offshore wind turbines, and to pre-process the satellite image data to obtain synthetic image data;

[0052] a wind turbine point determination module, configured to determine wind turbine point distribution data based on synthetic image data, public height data, and public diameter data, and to distinguish wind turbine farms based on the wind turbine point distribution data;

[0053] A threshold determination module is used to obtain the fan's dwell effect point and fan point based on the fan point distribution data and synthetic image data, calculate the fan point height and fan point diameter, and determine the height threshold and diameter threshold by combining the public height data and the public diameter data;

[0054] A module for determining wind turbines with no public data is used to calculate the binary image of the wind turbine's stop effect point and the binary image of the wind turbine point based on the height threshold and the diameter threshold, and to measure the wind turbine height data, wind turbine diameter data, and wind turbine width data in areas with no public data.

[0055] The weight calculation module is used to model the relationship between public height data, public diameter data and rotor weight, nacelle weight, and tower weight based on the public wind turbine data set. Based on the established model, the rotor weight, nacelle weight, and tower weight are calculated using the wind turbine height data and wind turbine diameter data.

[0056] The material inventory calculation module is used to obtain the spatial distribution of the wind turbine material inventory based on the percentage relationship of each material contained in the rotor, nacelle and tower, as well as the estimated rotor weight, nacelle weight and tower weight.

[0057] In a third aspect, the present invention further provides a device for inverting the material inventory distribution of an offshore wind turbine, the device comprising a memory and a processor, the processor calling computer instructions in the memory to execute the method for inverting the material inventory distribution of an offshore wind turbine as described above.

[0058] Compared with the existing technology, this technical solution has at least the following beneficial effects:

[0059] 1. The present invention proposes a method for inverting the material stock distribution of offshore wind turbines using SAR satellite imagery. First, based on SAR satellite imagery data and digital image processing methods, it can quickly obtain the distribution point data of offshore wind turbines over a large area, and automatically calculate the height, diameter, and width values ​​of the wind turbine points in each wind farm, which can provide more comprehensive and intuitive size attribute information of the wind turbine points.

[0060] 2. In a further solution, the present invention models the functional relationship between the height and diameter of the wind turbine and the weight of the rotor, nacelle, and tower. At the same time, by determining the percentage relationship of various materials contained in the rotor, nacelle, and tower, such as copper, iron, and aluminum, the inventory of each material is calculated, thereby realizing fast and effective quantitative monitoring of the material inventory at a wide range of wind turbine points.

[0061] 3. Due to the close integration of wind turbine material inventory and geographic spatial data, the present invention can provide thematic maps of the spatial distribution of various material inventories of wind turbines, which can provide a certain reference value for wind energy departments in managing installation scrap materials generated by retired wind turbines. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0063] Figure 1 This is a flow chart of a method for inverting the material inventory distribution of offshore wind turbines using SAR satellite images according to a preferred embodiment of the present invention;

[0064] Figure 2 The original SAR image of the wind turbine point and the wind turbine binary image obtained by thresholding are shown in the preferred embodiment of the present invention;

[0065] Figure 3 This is an example of a binary image of a fan's dwell effect point and a fan point in a preferred embodiment of the present invention;

[0066] Figure 4 2. Schematic diagram of the calculation principle of the fan height value Height according to the preferred embodiment of the present invention;

[0067] Figure 5 This is an example diagram of a rectangular bounding box of a binary image of a wind turbine point according to an embodiment of the present invention;

[0068] Figure 6 This is a schematic diagram of modeling the relationship between the height and diameter of a wind turbine and the weight of the rotor, nacelle, and tower according to an embodiment of the present invention;

[0069] Figure 7 This is an example diagram of the spatial distribution of material inventory (copper) of a fan according to an embodiment of the present invention;

[0070] Figure 8 This is an example diagram of the spatial distribution of material inventory (aluminum) of a wind turbine according to an embodiment of the present invention. DETAILED DESCRIPTION

[0071] The following describes embodiments of the present invention in detail with reference to the accompanying drawings. It should be understood that the embodiments described are only a portion of the embodiments of the present invention, and not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are intended to fall within the scope of protection of the present invention.

[0072] Those skilled in the art should be aware that the following specific embodiments or implementations are a series of optimized configurations listed in the present invention to further explain the specific content of the invention, and these configurations can be combined or used in conjunction with each other, unless the present invention explicitly states that some or a specific embodiment or implementation cannot be combined or used in conjunction with other embodiments or implementations. At the same time, the following specific embodiments or implementations are only intended to be optimized configurations and are not to be understood as limiting the scope of protection of the present invention.

[0073] In a specific embodiment of the present invention, Figure 1 As shown, the main steps can be set as follows:

[0074] S1: Basic data acquisition, including SAR remote sensing image data and publicly available offshore wind turbine height and diameter data. This data serves as the foundation for this solution and subsequent fitting and estimation operations.

[0075] For example, we pre-process the acquired remote sensing image data, wind turbine height data, and diameter data to facilitate subsequent processing. Step S1 specifically includes:

[0076] S11: Obtain public SAR satellite image time series data, perform image preprocessing such as cropping and cloud removal on the data, calculate the median of the time series data for the entire year, and obtain the synthetic image data Image median :

[0077] Image median =Median(ImageCollection)

[0078] ImageCollection represents the time series collection for the entire year, and Median represents the median of the image time series.

[0079] S12: Search existing data to obtain the height of offshore wind turbines in countries around the world that have been made public. open Data, diameter open data.

[0080] It should be noted that the order of the above steps S11 and S12 is not specific, and the two steps can be performed simultaneously or in a reversed order.

[0081] S2: After the basic data of S1 is acquired and processed, the wind turbine point distribution data is determined using methods such as morphology, empirical thresholds, and spatial location distribution judgment, and the wind turbine farms are distinguished into different types through spatial clustering methods.

[0082] For example, morphological methods can be preferably implemented in the following ways:

[0083] S21: Using morphological corrosion and expansion operations, eliminate interference points in the offshore environment and enhance the wind turbine point distribution range information. In this embodiment, the corrosion and expansion operation formulas are as follows:

[0084] AB={x,y|(B) xy ∈A}

[0085]

[0086] Among them, A represents the image, B represents the convolution kernel, and x and y represent the coordinate positions of the image pixels.

[0087] S22: Determine the threshold T for wind turbine point screening by empirical threshold method WT =0, such as Figure 2 The figure shows the original SAR image of the wind turbine point and the binary image obtained by thresholding. That is, by comparing the pixel value with the threshold, the eroded and expanded image data is converted into a binary image, and the wind turbine point pixels are converted into vector points. The vector point conversion can use existing public tools, such as the raster-to-vector tool of GIS software.

[0088] S23: Offshore wind turbines have a distribution pattern and a certain number of regularities. Based on the spatial characteristics of the cluster distribution of wind turbine points, we further eliminate unreasonable wind turbine points, such as isolated points. We use GIS software to perform a 3km buffer analysis on the extracted wind turbine points one by one, and eliminate points with less than 3 wind turbine points in the buffer area. The above elimination conditions can be expressed as follows:

[0089] WTPointsOut=Filter(buffer WTPointsIn (3km)>3)

[0090] WTPointsIn represents the wind turbine point data before elimination, WTPointsOut represents the wind turbine point data after elimination, buffer represents the buffer operation with the wind turbine point as the center, and Filter represents the elimination operation. For example, the buffer operation can be performed as follows: with the wind turbine point as the center and the set buffer distance as the radius, for example, a circle with a radius of 3km is drawn here as a 3km buffer. If the number of wind turbine points in the buffer is less than 3 (for example), then the wind turbine point is deleted. Generally, the 3km buffer wind point elimination and screening in this step only needs one round.

[0091] S24: Next, we use the DBSCAN algorithm to perform spatial clustering on the remaining wind turbine points after elimination, dividing each wind turbine point into different wind farms. The input, output and specific steps of the spatial clustering algorithm are as follows:

[0092] Input: Sample set D = (x1, x2, ..., x m ), neighborhood parameter (∈, MinPts), sample distance metric, illustratively, the distance metric here can be Euclidean distance.

[0093] Output: Cluster partition C.

[0094] a) Initialize parameters and set all objects in the sample set to unvisited;

[0095] b) Randomly select an unvisited object from the sample set, use this object as the starting object to establish a new class, recursively find all objects that are density-reachable from this object, add them to the class, and mark them as visited;

[0096] c) Until all objects have been visited, the clustering results are output and the algorithm ends; otherwise, go to step b).

[0097] S3: Based on the wind turbine point distribution data and SAR median synthetic image data, the automatic threshold is used to obtain the wind turbine's residence effect point and wind turbine point. The wind turbine point height and diameter are calculated according to the formula. Combined with the public wind turbine height and diameter data, the height and diameter values ​​calculated by the formula are fitted with the public values ​​by least squares to determine the optimal thresholds for calculating the wind turbine height and diameter, namely the height threshold and diameter threshold.

[0098] Step S3 specifically includes:

[0099] S31: Based on the wind turbine point data and SAR image data, a 300-meter buffer zone is established for each wind turbine point in each wind farm, and the SAR image data within this range is cropped as the stay effect point and wind turbine point candidate area;

[0100] S32: For each candidate area image, use the SAR median synthetic image data automatic threshold t to obtain Figure 3 The example of the fan stop effect point and the fan point binary image is shown. The fan stop effect point binary image is converted into a vector point, and the distance Dist is calculated with the fan point extracted in step S23 (i.e., the fan point retained after elimination). The image imaging angle data Angle in the SAR data is obtained according to the fan point position, and the fan height value Height is calculated using the SAR imaging principle. The calculation principle is as follows: Figure 4 As shown, the Height calculation formula is as follows:

[0101] Height t =Dist t *tan(Angle*π / 180),t∈[Thesh start ,Thesh end ]

[0102] Among them, t represents the image automatic threshold, t∈[Thesh start ,Thesh end ], the automatic iteration step can be set to, for example, 5, Thesh start and Thesh end are the values ​​of the median composite image data, representing the starting and ending points of the automatic threshold range, which is determined by the distribution range of the values ​​of the wind turbine point image in the median composite image.

[0103] S33: Generate a rectangular bounding box for the binary image of the wind turbine point obtained in step S32. The generated bounding box example is shown in the figure below: Figure 5 As shown in the figure, the length and width of the bounding box represent the diameter of the wind turbine and the width of the nacelle, respectively. The diameter and width are calculated from the area and perimeter of the bounding box, using the following formula:

[0104]

[0105]

[0106] The area and perimeter of the rectangular bounding box are known and can be directly obtained by statistical tools. Max and Min are the judgment conditions for the diameter and width of the wind turbine, respectively.

[0107] S34: Combine the wind turbine height and diameter data from the public data and calculate the sum of squares of the height and diameter values ​​calculated by the formula with the public data. Obtain the value of the median synthetic image data with the minimum distance difference as the optimal threshold for calculating the wind turbine height and diameter, i.e., the height threshold and diameter threshold. For example, the optimal height threshold determination conditions are as follows:

[0108]

[0109] Among them, J(T) represents the function of obtaining the optimal threshold T, m represents the number of wind turbines in the wind farm, Height cali and Height Openi The formula for calculating the optimal diameter threshold is the same as the height threshold calculated in this step. Those skilled in the art can reasonably deduce the formula based on this, and will not be further elaborated here.

[0110] S4: Further use the optimal thresholds (i.e., height threshold and diameter threshold) to calculate the binary images of the wind turbine's stop effect points and wind turbine points in the SAR image, and measure the height, diameter, and width of the wind turbines in areas without public wind turbine data.

[0111] Step S4 specifically includes:

[0112] S41: Further use the optimal threshold to calculate the binary images of the wind turbine stop effect points and wind turbine points in the area without public wind turbine data in the SAR image, and calculate the height, diameter and width of the wind turbines in the area without public wind turbine data according to the formulas in steps S32 and S33.

[0113] S42: The height, diameter, and width of the wind turbines in each wind farm are consistent, and the median value of all wind turbine points in different wind farms is used as the final height, diameter, and width value of each wind turbine point in the wind farm.

[0114] S5: Using publicly available wind turbine datasets, we model the relationship between wind turbine height and diameter and the weight of the rotor, nacelle, and tower. We then estimate the weight of the rotor, nacelle, and tower based on the height and diameter of the wind turbine.

[0115] Step S5 specifically includes:

[0116] S51: Search for publicly available wind turbine attribute datasets (including wind turbine height and diameter, and rotor, nacelle, tower weight, etc.);

[0117] S52: For example, in this embodiment, the height and diameter of the wind turbine and the weight of the rotor, nacelle, and tower conform to the following power exponential function relationship, and the relationship modeling diagram is shown as follows: Figure 6 As shown in the figure, the parameters a and b are fitted to the public wind turbine attribute data set, so that the weight of the rotor, nacelle, and tower can be calculated based on the wind turbine height and diameter:

[0118] q=ap b

[0119] Where q represents the rotor weight, nacelle weight, or tower weight, p represents the height or diameter of the wind turbine, and a and b represent the parameters to be solved for the power function.

[0120] S6: Searching existing data to determine the percentage relationship of each substance contained in the rotor, nacelle, and tower. Step S6 specifically includes: searching existing data to determine the percentage relationship of each substance contained in the rotor, nacelle, and tower, such as copper, iron, and aluminum, and calculating the inventory of each substance.

[0121] S7: Obtain the spatial distribution of the material inventory of the fan and output the material inventory result value to the attribute table of the fan data. Specifically, it includes: obtaining the spatial distribution of the material inventory of the fan according to the material content percentage of each component of the fan, and outputting the material inventory result value to the attribute table of the fan data. The example diagram of the spatial distribution of the material inventory (copper and aluminum) of the fan is as follows Figure 7 and Figure 8 shown.

[0122] In addition to the above embodiments, the solution of the present invention can also be implemented by inverting the material inventory distribution system of an offshore wind turbine. The system may include the following main functional components:

[0123] A data acquisition module is used to acquire satellite image data, publicly available height data and publicly available diameter data of offshore wind turbines, and to pre-process the satellite image data to obtain synthetic image data;

[0124] a wind turbine point determination module, configured to determine wind turbine point distribution data based on synthetic image data, public height data, and public diameter data, and to distinguish wind turbine farms based on the wind turbine point distribution data;

[0125] A threshold determination module is used to obtain the fan's dwell effect point and fan point based on the fan point distribution data and synthetic image data, calculate the fan point height and fan point diameter, and determine the height threshold and diameter threshold by combining the public height data and the public diameter data;

[0126] A module for determining wind turbines with no public data is used to calculate the binary image of the wind turbine's stop effect point and the binary image of the wind turbine point based on the height threshold and the diameter threshold, and to measure the wind turbine height data, wind turbine diameter data, and wind turbine width data in areas with no public data.

[0127] The weight calculation module is used to model the relationship between public height data, public diameter data and rotor weight, nacelle weight, and tower weight based on the public wind turbine data set. Based on the established model, the rotor weight, nacelle weight, and tower weight are calculated using the wind turbine height data and wind turbine diameter data.

[0128] The material inventory calculation module is used to obtain the spatial distribution of the wind turbine material inventory based on the percentage relationship of each material contained in the rotor, nacelle and tower, as well as the estimated rotor weight, nacelle weight and tower weight.

[0129] The above system can be installed on a server, a PC or other device and run, thereby implementing the various steps involved in the method for inverting the material inventory distribution of an offshore wind turbine in the above embodiment.

[0130] In another embodiment, this solution can be implemented by a device, which may include corresponding modules for performing each or several steps in the above-mentioned embodiments. Therefore, each step or several steps in the above-mentioned embodiments can be performed by the corresponding modules, and the electronic device may include one or more of these modules. The modules may be one or more hardware modules specifically configured to perform the corresponding steps, or implemented by a processor configured to perform the corresponding steps, or stored in a computer-readable medium for implementation by the processor, or implemented by some combination.

[0131] The device can be implemented using a bus architecture. The bus architecture can include any number of interconnecting buses and bridges, depending on the specific application and overall design constraints of the hardware. The bus connects various circuits including one or more processors, memories, and / or hardware modules.

[0132] Any process or method description in the flowchart or otherwise described herein can be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiment of the present invention includes alternative implementations in which the functions may be performed not in the order shown or discussed, including performing the functions in a substantially simultaneous manner or in a reverse order according to the functions involved, as will be understood by those skilled in the art to which the embodiments of the present invention pertain. The processor performs the various methods and processes described above. For example, the method embodiments in the present invention can be implemented as a software program that is tangibly contained in a machine-readable medium, such as a memory. In some embodiments, part or all of the software program can be loaded and / or installed via a memory and / or a communication interface. When the software program is loaded into the memory and executed by the processor, one or more steps in the method described above can be performed. Alternatively, in other embodiments, the processor can be configured to perform one of the above methods in any other appropriate manner (e.g., by means of firmware).

[0133] The logic and / or steps represented in the flowchart or otherwise described herein may be embodied in any readable storage medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch and execute instructions from an instruction execution system, apparatus, or device).

[0134] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present invention should be included in the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be based on the scope of protection of the claims.

Claims

1. A method for inverting the material inventory distribution of offshore wind turbines, characterized in that: The method comprises: S1. Obtain satellite image data, publicly available height data and publicly available diameter data of offshore wind turbines; pre-process the satellite image data to obtain synthetic image data; S2. Determine wind turbine point distribution data based on the synthetic image data, the public height data, and the public diameter data, and distinguish wind turbine farms based on the wind turbine point distribution data; S3. Based on the wind turbine point distribution data and synthetic image data, obtain the wind turbine's dwell effect point and wind turbine point, calculate the wind turbine point height and wind turbine point diameter, and determine the height threshold and diameter threshold by combining the public height data and public diameter data; S4. Based on the height threshold and the diameter threshold, calculate the binary image of the fan's stop effect point and the binary image of the fan point, and measure the fan height data, fan diameter data, and fan width data in the area without public data; S5. Based on the publicly available wind turbine dataset, model the relationship between the publicly available height data, publicly available diameter data, and the rotor weight, nacelle weight, and tower weight. Based on the established model, use the wind turbine height data and wind turbine diameter data to estimate the rotor weight, nacelle weight, and tower weight. S6. Determine the percentage relationship of each substance contained in the rotor, nacelle, and tower; S7. Based on the rotor weight, nacelle weight, tower weight estimated in S5 and the percentage relationship of each material in S6, obtain the spatial distribution of the wind turbine material inventory; In S2, the method for determining the wind turbine point distribution data is: S21, performing erosion and expansion operations on the synthetic image data to enhance the distribution range information of the wind turbine points; S22, based on the fan point screening threshold, processing the synthetic image data into a binary image, and converting the fan point pixels into vector points; S23, setting a first buffer zone for fan points and eliminating unreasonable fan points; S24, performing spatial clustering on the wind turbine points that remain after the elimination to form a wind turbine field, and using the wind turbine point data that remain after the elimination as wind turbine point distribution data; Said S23 further comprises: Set the radius of the first buffer zone and remove points with less than 3 fan points in the first buffer zone. The specific method is: WTPointsOut=Filter(buffer WTPointsIn (3km)>3) Among them, WTPointsIn represents the fan point data before elimination, WTPointsOut represents the fan point data after elimination, buffer represents the buffer operation, and Filter represents the elimination operation.

2. The method according to claim 1, characterized in that In S1, the satellite image data is time series data, and the median of the time series data for the entire year is calculated as the synthetic image data.

3. The method according to claim 1, characterized in that In the spatial clustering method in S24, the wind turbine point sample set, neighborhood parameters, and distance measurement method are used as inputs, and clusters are used as outputs.

4. The method according to claim 1, wherein Said S3 further comprises: S31. Based on the wind turbine point distribution data, establish a second buffer zone for each wind turbine point, and use the second buffer zone as a candidate area for a stay effect point and a wind turbine point. S32. For each candidate wind turbine point area, obtain a binary image of the stop effect point and a binary image of the wind turbine point in the wind turbine point distribution data, convert the binary image of the stop effect point into a vector point, and then calculate the distance Dist based on the wind turbine point in the wind turbine point distribution data. Obtain the satellite image angle data Angle according to the wind turbine point position in the wind turbine point distribution data, and calculate the height of the wind turbine point Height: Height t =Dist t *tan(Angle*π / 180),t∈[Thresh start ,Thresh end ]; Among them, t represents the automatic threshold of the image, Thresh start and Thresh end is the value of the synthetic image data, which is determined by the distribution range of the numerical values ​​of the wind turbine points in the synthetic image; S33. Generate a rectangular bounding box based on the binary image of the wind turbine point in the wind turbine point distribution data, wherein the bounding box has the wind turbine point diameter and the nacelle width as sides; the wind turbine point diameter is obtained from the bounding box area and the bounding box perimeter, and the bounding box area and the bounding box perimeter are obtained from statistical data; S34. Calculate the sum of the squares of the distances between the wind turbine point height and the public height data using the wind turbine point distribution data and the synthetic image data, and use the value of the synthetic image data with the minimum sum of the squares as the height threshold; calculate the sum of the squares of the distances between the wind turbine point diameter and the public diameter data, and use the value of the synthetic image data with the minimum sum of the squares as the diameter threshold.

5. The method according to claim 4, characterized in that In S33, the fan point diameter Diameter is calculated as follows: The calculation method of cabin width is: Among them, area represents the area of ​​the bounding box, and perimeter represents the perimeter of the bounding box.

6. A system for inverting the material inventory distribution of offshore wind turbines, characterized in that: The system is used to execute the method for inverting material inventory distribution of offshore wind turbines according to any one of claims 1 to 5, and the system comprises: A data acquisition module is used to acquire satellite image data, publicly available height data and publicly available diameter data of offshore wind turbines, and to pre-process the satellite image data to obtain synthetic image data; a wind turbine point determination module, configured to determine wind turbine point distribution data based on synthetic image data, public height data, and public diameter data, and to distinguish wind turbine farms based on the wind turbine point distribution data; A threshold determination module is used to obtain the fan's dwell effect point and fan point based on the fan point distribution data and synthetic image data, calculate the fan point height and fan point diameter, and determine the height threshold and diameter threshold by combining the public height data and the public diameter data; A module for determining wind turbines with no public data is used to calculate the binary image of the wind turbine's stop effect point and the binary image of the wind turbine point based on the height threshold and the diameter threshold, and to measure the wind turbine height data, wind turbine diameter data, and wind turbine width data in areas with no public data. The weight calculation module is used to model the relationship between public height data, public diameter data and rotor weight, nacelle weight, and tower weight based on the public wind turbine data set. Based on the established model, the rotor weight, nacelle weight, and tower weight are calculated using the wind turbine height data and wind turbine diameter data. The material inventory calculation module is used to obtain the spatial distribution of the wind turbine material inventory based on the percentage relationship of each material contained in the rotor, nacelle and tower, as well as the estimated rotor weight, nacelle weight and tower weight.

7. A device for inverting the distribution of material inventory of offshore wind turbines, characterized in that: The device includes a memory and a processor, and the processor calls computer instructions in the memory to execute the method for inverting the material inventory distribution of offshore wind turbines according to any one of claims 1 to 5.

Images