Image recognition method and device for wind farm group wake effect
By coupling the Fitch wake model with the mesoscale WRF model and the ellipse fitting method, the problem of low accuracy in identifying the wake effect region of wind farm clusters was solved, achieving rapid and accurate identification of the wake effect region and optimizing wind farm layout and selection.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENGDONG RUDONG OFFSHORE WIND POWER CO LTD
- Filing Date
- 2023-03-10
- Publication Date
- 2026-06-26
Smart Images
Figure CN116229270B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of wind turbine wake calculation technology, and in particular to an image recognition method and apparatus for wind farm wake effects. Background Technology
[0002] Currently, the offshore wind power industry has entered the construction phase with single-unit capacities of 8-12MW, and the construction of offshore wind power bases has become a trend. However, this context will lead to an increasingly prominent wake effect between wind farms, characterized by "low wind speed and high turbulence," resulting in power losses in downstream wind farms, accelerated fatigue damage to wind turbines, and reduced operating efficiency. Therefore, enhancing research on the cluster effects and operational characteristics of offshore wind power bases is one of the most challenging issues in the wind energy field.
[0003] Previous studies on wake effects have generally focused on spatial scales below tens of kilometers and primarily addressed individual wind turbines or a few turbines, lacking research on wake effects within wind farms or wind power bases. Furthermore, offshore wind power planning often prioritizes maximizing single-farm power generation and minimizing construction costs. However, the wake effect of wind farm clusters significantly impacts offshore wind farm power generation, leaving considerable room for optimization in turbine selection and cluster layout. Conventional wind farm wake effect calculations rely on computational fluid dynamics (CFD) numerical simulations. While this method uses actuation lines and actuation disk models to reflect the physical motion of the wind turbine and offers high simulation accuracy, its computational cost is prohibitively high.
[0004] The mesoscale WRF (Weather Research Forecast) model system is a mesoscale forecasting and assimilation system suitable for meteorological simulation applications ranging from tens of meters to thousands of kilometers. WRF models have been used to assess and evaluate wind energy resources and wind farms with good results. However, mesoscale WRF models also suffer from excessive computational costs, typically requiring supercomputing platforms for calculations; calculating the wake of a 100km × 100km wind farm can take a week or several weeks. Therefore, there is currently a lack of methods for rapidly establishing the wake effect of wind farm clusters. Summary of the Invention
[0005] This application aims to at least partially address one of the technical problems in the related art.
[0006] Therefore, the first objective of this application is to propose an image recognition method for the wake effect of wind farm clusters, which solves the technical problem of low accuracy in identifying the wake effect region of wind farms in existing methods, and realizes accurate identification of the wake effect region of wind farms.
[0007] The second objective of this application is to propose an image recognition device for the wake effect of wind farm clusters.
[0008] The third objective of this application is to propose a computer device.
[0009] To achieve the above objectives, the first aspect of this application proposes an image recognition method for the wake effect of a wind farm cluster, comprising: acquiring wind turbine data of the wind farm to be identified, wherein the wind turbine data includes the placement position of each wind turbine; simulating the wind turbines in the wind farm to be identified within a simulation area based on the wind turbine data to obtain a wake effect cloud map of the wind farm cluster; and identifying and covering the wake effect region of the wind farm cluster in the wake effect cloud map of the wind farm cluster using an ellipse fitting method to determine the elliptical region of the wake effect of the wind farm cluster to be identified.
[0010] The image recognition method for the wake effect of wind farm clusters in this application first determines the contour of the wake effect cloud map by coupling the Fitch wake model with the mesoscale WRF mode, and then determines the wake effect region of the wind farm cluster by ellipse fitting method, thereby achieving accurate identification of the wake effect region of the wind farm.
[0011] Optionally, in one embodiment of this application, the wake effect cloud map of the wind farm cluster uses the wind speed deficit ratio as the boundary of the wake effect region, and the wind speed deficit ratio is obtained by coupling the mesoscale WRF model with the Fitch wake model.
[0012] Optionally, in one embodiment of this application, the wind speed loss ratio is expressed as:
[0013]
[0014] Wherein, WRF represents a mesoscale meteorological model, WRF(Fitch) is the simulation result of the WRF model coupled with the wind turbine model after the Fitch wake model is enabled, and WRF(without) is the simulation result of the WRF model without the wind turbine model after the Fitch model is disabled.
[0015] Optionally, in one embodiment of this application, the wake effect region of the wind farm group in the wake effect cloud map is identified and covered by the ellipse fitting method, and the wake effect ellipse region of the wind farm to be identified is determined, including:
[0016] The wake effect region in the wake effect cloud map of the wind farm group is fitted with an ellipse equation as a model, so that the ellipse equation covers the wake effect region, and the fitted ellipse equation is obtained.
[0017] Obtain the parameters of the fitted ellipse equation, and determine the center of the fitted ellipse equation based on the parameters as the identification result.
[0018] To achieve the above objectives, a second aspect of the present invention provides an image recognition device for the wake effect of a wind farm cluster, comprising an acquisition module, a simulation module, and a recognition module, wherein...
[0019] The acquisition module is used to acquire wind turbine data of the wind farm to be identified, including the placement location of each wind turbine.
[0020] The simulation module is used to simulate the wind turbines in the wind farm to be identified within the simulation area based on the wind turbine data, and obtain a cloud map of the wake effect of the wind farm group.
[0021] The identification module is used to identify and cover the wake effect region of the wind farm group in the wake effect cloud map of the wind farm group using the ellipse fitting method, and to determine the elliptical region of the wake effect of the wind farm to be identified.
[0022] Optionally, in one embodiment of this application, the wake effect cloud map of the wind farm cluster uses the wind speed deficit ratio as the boundary of the wake effect region, and the wind speed deficit ratio is obtained by coupling the mesoscale WRF model with the Fitch wake model.
[0023] Optionally, in one embodiment of this application, the wind speed loss ratio is expressed as:
[0024]
[0025] Wherein, WRF represents a mesoscale meteorological model; WRF(Fitch) represents the simulation results of the WRF model coupled with the wind turbine model after enabling the Fitch wake model; and WRF(without) represents the simulation results of the WRF model without coupling the wind turbine model after disabling the Fitch model.
[0026] Optionally, in one embodiment of this application, the wake effect region of the wind farm group in the wake effect cloud map is identified and covered by the ellipse fitting method, and the wake effect ellipse region of the wind farm to be identified is determined, including:
[0027] The wake effect region in the wake effect cloud map of the wind farm group is fitted with an ellipse equation as a model, so that the ellipse equation covers the wake effect region, and the fitted ellipse equation is obtained.
[0028] Obtain the parameters of the fitted ellipse equation, and determine the center of the fitted ellipse equation based on the parameters as the identification result.
[0029] To achieve the above objectives, a third aspect of the present invention provides a computer device, comprising: a processor; and a memory for storing a computer program of the processor, wherein when the processor executes the computer program, the above-described image recognition method for the wake effect of a wind farm group is implemented.
[0030] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description
[0031] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the following description of the embodiments taken in conjunction with the accompanying drawings, wherein:
[0032] Figure 1 This is a flowchart illustrating an image recognition method for the wake effect of a wind farm cluster provided in Embodiment 1 of this application.
[0033] Figure 2 This is an example diagram illustrating the identification of the wake effect region of a wind farm cluster according to an embodiment of this application.
[0034] Figure 3 This is another example diagram illustrating the identification of the wake effect region of a wind farm group according to an embodiment of this application;
[0035] Figure 4 This is an example diagram illustrating the determination of the wake effect size of a wind farm cluster according to an embodiment of this application.
[0036] Figure 5 This is a schematic diagram of the structure of an image recognition device for the wake effect of a wind farm cluster, provided in an embodiment of this application. Detailed Implementation
[0037] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain this application, and should not be construed as limiting this application.
[0038] The image recognition method and apparatus for the wake effect of wind farm groups according to embodiments of this application are described below with reference to the accompanying drawings.
[0039] Figure 1 This is a flowchart illustrating an image recognition method for the wake effect of a wind farm cluster provided in Embodiment 1 of this application.
[0040] like Figure 1 As shown, the image recognition method for the wake effect of this wind farm group includes the following steps:
[0041] Step 101: Obtain wind turbine data of the wind farm to be identified, wherein the wind turbine data includes the placement location of each wind turbine;
[0042] Step 102: Further obtain the wake effect cloud map of the wind farm cluster using the mesoscale WRF model;
[0043] Step 103: Identify and cover the wake effect region of the wind farm group in the wake effect cloud map of the wind farm group using the ellipse fitting method, and determine the elliptical region of the wake effect of the wind farm to be identified.
[0044] The image recognition method for the wake effect of wind farm clusters in this application first determines the contour of the wake effect cloud map by coupling the Fitch wake model with the mesoscale WRF mode, and then determines the wake effect region of the wind farm cluster by ellipse fitting method, thereby achieving accurate identification of the wake effect region of the wind farm.
[0045] Optionally, in one embodiment of this application, the wake effect cloud map of the wind farm cluster uses the wind speed deficit ratio as the boundary of the wake effect region. The wind speed deficit ratio is obtained by coupling a mesoscale WRF model with a Fitch wake model. The mesoscale WRF (Weather Research Forecast) model system is a mesoscale forecasting model and assimilation system. Coupling the Fitch wake model with the mesoscale WRF model is equivalent to placing each wind turbine in the wind farm within the simulation region. After calculation, the wake effect cloud map of the wind farm cluster can be obtained, such as... Figure 2 , Figure 3 The image shows wake effect cloud maps of an offshore wind farm at different times and with different wind speeds and directions.
[0046] Optionally, in one embodiment of this application, the wind speed loss ratio is defined as:
[0047]
[0048] Here, WRF represents the mesoscale meteorological (WRF) model. WRF(Fitch) indicates the Fitch wake model is enabled, meaning the simulation results of the WRF model coupled with the wind turbine model; WRF(without) indicates the Fitch model is disabled, meaning the simulation results are not coupled with the wind turbine model. The purpose of defining the wind speed loss ratio is to eliminate the influence of uneven spatial distribution of wind speed and to intuitively show the wind speed attenuation effect caused by the wind field wake.
[0049] Generally, when the wind speed decays back to -5% to -2%, it is considered that the speed loss is negligible. In this embodiment, the boundary of the wake effect is defined as a wind speed loss ratio of -0.04.
[0050] Optionally, in one embodiment of this application, the wake effect region of the wind farm group in the wake effect cloud map is identified and covered by the ellipse fitting method to determine the elliptical region of the wake effect of the wind farm to be identified. The basic idea of the ellipse fitting method is: for the simulation results of a specific offshore wind power planning area, such as... Figure 2 , 3As shown, the goal is to find an ellipse that covers the boundary where the wind speed deficit ratio is -0.04, representing the wake effect. In other words, a set of data from the image is fitted using an ellipse equation as a model, such that a certain ellipse equation best satisfies these data points, and the parameters of this ellipse equation are calculated. The center of the optimal ellipse is then the target center for the search.
[0051] The elliptical region of the wake effect of the wind farm to be identified is determined by elliptical fitting, specifically including:
[0052] The wake effect region in the wake effect cloud map of the wind farm group is fitted with an ellipse equation as a model, so that the ellipse equation covers the wake effect region, and the fitted ellipse equation is obtained.
[0053] Obtain the parameters of the fitted ellipse equation, and determine the center of the fitted ellipse equation based on the parameters as the identification result.
[0054] Furthermore, another preferred embodiment of the ellipse fitting method is as follows:
[0055] Using Python's OpenCV library, the cv2.Canny function was first used for edge detection, followed by the cv2.findContours function for contour detection, thus identifying the elliptical region of the wind farm cluster's wake effect. The identification was accurate and could be completed within tens of seconds.
[0056] Figure 4 Example diagram for determining the size of the wake effect of a wind farm cluster. The specially fitted ellipse parameters, major axis a(3) is related to the wind farm capacity and wind speed, and minor axis b(4) is related to the span width of the wind farm. Their functional relationship is as follows:
[0057] a=m×Q+n×V
[0058] b = k × L
[0059] Where m, n, and k are undetermined coefficients, with m ranging from 0.01 to 0.5, n ranging from 1 to 8, and k ranging from 0.5 to 0.7.
[0060] To achieve the above embodiments, this application also proposes an image recognition device for the wake effect of wind farm clusters.
[0061] Figure 5 This is a schematic diagram of the structure of an image recognition device for the wake effect of a wind farm cluster, provided in an embodiment of this application.
[0062] like Figure 5 As shown, the image recognition device for the wake effect of this wind farm cluster includes an acquisition module, a simulation module, and a recognition module, wherein...
[0063] The acquisition module is used to acquire wind turbine data of the wind farm to be identified, including the placement location of each wind turbine.
[0064] The simulation module is used to simulate the wind turbines in the wind farm to be identified within the simulation area based on the wind turbine data, and obtain a cloud map of the wake effect of the wind farm group.
[0065] The identification module is used to identify and cover the wake effect region of the wind farm group in the wake effect cloud map of the wind farm group using the ellipse fitting method, and to determine the elliptical region of the wake effect of the wind farm to be identified.
[0066] Optionally, in one embodiment of this application, the wake effect cloud map of the wind farm cluster uses the wind speed deficit ratio as the boundary of the wake effect region, and the wind speed deficit ratio is obtained by coupling the mesoscale WRF model with the Fitch wake model.
[0067] Optionally, in one embodiment of this application, the wind speed loss ratio is expressed as:
[0068]
[0069] Here, WRF represents the mesoscale meteorological (WRF) model. WRF(Fitch) indicates the Fitch wake model is enabled, meaning the simulation results of the WRF model coupled with the wind turbine model; WRF(without) indicates the Fitch model is disabled, meaning the simulation results are not coupled with the wind turbine model. The purpose of defining the wind speed loss ratio is to eliminate the influence of uneven spatial distribution of wind speed and to intuitively show the wind speed attenuation effect caused by the wind field wake.
[0070] Optionally, in one embodiment of this application, the wake effect region of the wind farm group in the wake effect cloud map is identified and covered by the ellipse fitting method, and the wake effect ellipse region of the wind farm to be identified is determined, including:
[0071] The wake effect region in the wake effect cloud map of the wind farm group is fitted with an ellipse equation as a model, so that the ellipse equation covers the wake effect region, and the fitted ellipse equation is obtained.
[0072] Obtain the parameters of the fitted ellipse equation, and determine the center of the fitted ellipse equation based on the parameters as the identification result.
[0073] It should be noted that the explanation of the above-described embodiment of the image recognition method for the wake effect of wind farm clusters also applies to the image recognition device for the wake effect of wind farm clusters in this embodiment, and will not be repeated here.
[0074] To implement the above embodiments, the present invention also proposes a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the method described in the above embodiments.
[0075] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0076] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this application, "multiple" means at least two, such as two, three, etc., unless otherwise explicitly specified.
[0077] Any process or method description in the flowchart or otherwise herein can be understood as representing a module, segment, or portion of code comprising one or more executable instructions for implementing custom logic functions or processes, and the scope of the preferred embodiments of this application includes additional implementations in which functions may be performed not in the order shown or discussed, including substantially simultaneously or in reverse order depending on the functions involved, as should be understood by those skilled in the art to which embodiments of this application pertain.
[0078] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.
[0079] It should be understood that various parts of this application can be implemented using hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented using software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.
[0080] Those skilled in the art will understand that all or part of the steps of the methods in the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, the program includes one or a combination of the steps of the method embodiments.
[0081] Furthermore, the functional units in the various embodiments of this application can be integrated into a processing module, or each unit can exist physically separately, or two or more units can be integrated into a module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
[0082] The storage medium mentioned above can be a read-only memory, a disk, or an optical disk, etc. Although embodiments of this application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting this application. Those skilled in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of this application.
Claims
1. An image recognition method for the wake effect of a wind farm cluster, characterized in that, Includes the following steps: Obtain wind turbine data of the wind farm to be identified, wherein the wind turbine data includes the placement position of each wind turbine; Based on the wind turbine data, the wind turbines in the wind farm to be identified are simulated in the simulation area to obtain a cloud map of the wake effect of the wind farm group. The wake effect region of the wind farm group in the wake effect cloud map of the wind farm group is identified and covered by the ellipse fitting method, and the wake effect ellipse region of the wind farm to be identified is determined. The wake effect cloud map of the wind farm cluster uses the wind speed deficit ratio as the boundary of the wake effect region, and the wind speed deficit ratio is obtained by coupling the mesoscale WRF model with the Fitch wake model. The wind speed loss ratio is expressed as: Wherein, WRF represents a mesoscale meteorological model, WRF( Fitch The results are simulations of the wind turbine model coupled with the WRF mode after enabling the Fitch wake model. without The results are simulations of the WRF mode without coupled wind turbines after the Fitch model is turned off.
2. The method as described in claim 1, characterized in that, The step of identifying and covering the wake effect region of the wind farm group in the wake effect cloud map using the ellipse fitting method, and determining the elliptical region of the wake effect of the wind farm to be identified, includes: The wake effect region in the wake effect cloud map of the wind farm group is fitted with an ellipse equation as a model, so that the ellipse equation covers the wake effect region, and the fitted ellipse equation is obtained. Obtain the parameters of the fitted ellipse equation, and determine the center of the fitted ellipse equation as the identification result based on the parameters.
3. An image recognition device for the wake effect of a wind farm cluster, characterized in that, It includes an acquisition module, a simulation module, and a recognition module, among which, The acquisition module is used to acquire wind turbine data of the wind farm to be identified, wherein the wind turbine data includes the placement position of each wind turbine; The simulation module is used to simulate the wind turbines in the wind farm to be identified within the simulation area based on the wind turbine data, and obtain a cloud map of the wake effect of the wind farm group. The identification module is used to identify and cover the wake effect region of the wind farm group in the wake effect cloud map of the wind farm group by means of ellipse fitting method, and to determine the wake effect ellipse region of the wind farm to be identified. The wake effect cloud map of the wind farm cluster uses the wind speed deficit ratio as the boundary of the wake effect region, and the wind speed deficit ratio is obtained by coupling the mesoscale WRF model with the Fitch wake model. The wind speed loss ratio is expressed as: Wherein, WRF represents a mesoscale meteorological model, WRF( Fitch The results are simulations of the wind turbine model coupled with the WRF mode after enabling the Fitch wake model. without The results are simulations of the WRF mode without coupled wind turbines after the Fitch model is turned off.
4. The apparatus as described in claim 3, characterized in that, The step of identifying and covering the wake effect region of the wind farm group in the wake effect cloud map using the ellipse fitting method, and determining the elliptical region of the wake effect of the wind farm to be identified, includes: The wake effect region in the wake effect cloud map of the wind farm group is fitted with an ellipse equation as a model, so that the ellipse equation covers the wake effect region, and the fitted ellipse equation is obtained. Obtain the parameters of the fitted ellipse equation, and determine the center of the fitted ellipse equation as the identification result based on the parameters.
5. A computer device, characterized in that, The method includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, it implements the method as described in any one of claims 1-2.