Method and apparatus for calculating representative wind-turbulence space

Abstract

The present disclosure provides a method and device for calculating wind turbine tower turbulence space representation. The method can include: obtaining flow field data and geographical data of a target position in a wind farm and a wind turbine tower; extracting a characteristic factor related to turbulence according to the flow field data and geographical data of the target position and the flow field data and geographical data of the wind turbine tower; and applying the characteristic factor to a turbulence space representation model to calculate the turbulence space representation of the wind turbine tower to the target position.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of wind power generation technology, and more particularly, to a method of calculating turbulence space representativeness of a wind measurement tower and an apparatus thereof. BACKGROUND

[0002] Wind resource data plays a crucial role in annual energy production of a wind farm, and turbulence representativeness of a wind measurement tower is a main factor affecting accuracy and reliability of the wind resource data. In a wind resource analysis process, turbulence has always been an important index.

[0003] At the present stage, for turbulence space representativeness of a wind measurement tower, wind power engineers make a subjective judgment based on geographical and meteorological environmental conditions to complete the evaluation work of turbulence representativeness of a wind measurement tower. There is no calculation method for turbulence space representativeness of a wind measurement tower. SUMMARY

[0004] An aspect of the present disclosure is to provide a method of calculating turbulence space representativeness of a wind measurement tower, which can include obtaining flow field data and geographical data of a target location and the wind measurement tower in a wind farm, extracting a characteristic factor related to turbulence based on the flow field data and the geographical data of the target location and the wind measurement tower, and applying the characteristic factor to a turbulence space representativeness model to calculate turbulence space representativeness of the wind measurement tower with respect to the target location.

[0005] The characteristic factor can include at least one of a turbulence intensity difference between the target location and the wind measurement tower, a height distance, a horizontal distance, a wind direction deflection angle difference, an inflow angle difference, a terrain complexity, and a roughness.

[0006] The turbulence space representativeness can be quantified as one of a bias value, a mean square error, a root mean square error, a standard deviation, and a variance of turbulence intensity.

[0007] The flow field data can be obtained based on at least one of mesoscale data and actual wind measurement data via wind resource numerical simulation calculation.

[0008] In the method, the turbulence space representativeness model can be established by using a machine learning method.

[0009] In the method, the turbulence space representativeness model can be established by using a regression method with a characteristic factor extracted from wind measurement data, flow field data, and geographical data of at least two wind measurement towers as an input of the turbulence space representativeness model and a comparison result between a turbulence intensity measurement value and a numerical simulation calculation value of the wind measurement tower as an output of the turbulence space representativeness model.

[0010] The wind measurement data can include at least one of wind speed, wind direction, and turbulence intensity, the flow field data can include at least one of wind speed-up factor, turbulence intensity, wind direction deflection angle, inflow angle, and the geographic data can include at least one of coordinates, altitude, and roughness.

[0011] The method can further include adjusting parameters of the turbulence spatial representative model with a least square error minimization as an optimization objective, and testing stability of the turbulence spatial representative model using 10-fold cross-validation.

[0012] The turbulence spatial representative model can be established based on a mutual prediction result of at least two wind measurement towers in an actual completed project site.

[0013] The method can further include displaying a map of turbulence spatial representation of the wind measurement towers on the target location, or displaying a quantitative value of turbulence spatial representation of the wind measurement towers on the target location.

[0014] Another aspect of the disclosure is to provide an apparatus for calculating turbulence spatial representation of a wind measurement tower, which can include a data acquisition module configured to acquire flow field data and geographic data of a target location and a wind measurement tower in a wind farm, and a data processing module configured to extract a feature factor related to turbulence from the flow field data and the geographic data of the target location and the wind measurement tower, and apply the feature factor to a turbulence spatial representative model to calculate turbulence spatial representation of the wind measurement tower on the target location.

[0015] The data processing module can establish the turbulence spatial representative model by using a machine learning method.

[0016] The data processing module can establish the turbulence spatial representative model by using a regression method, with feature factors extracted from wind measurement data, flow field data, and geographic data of at least two wind measurement towers as inputs of the turbulence spatial representative model and a comparison result between turbulence intensity measurement values and numerical simulation calculation values of the wind measurement towers as an output of the turbulence spatial representative model.

[0017] The data processing module can adjust parameters of the turbulence spatial representative model with a least square error minimization as an optimization objective.

[0018] The data processing module can test stability of the turbulence spatial representative model using 10-fold cross-validation.

[0019] The data processing module can establish the turbulence spatial representative model based on a mutual prediction result of at least two wind measurement towers in an actual completed project site.

[0020] The device can further comprise a display for displaying a map of the turbulence spatial representative of the target location by the wind measurement tower; or displaying a quantitative value of the turbulence spatial representative of the target location by the wind measurement tower.

[0021] According to an exemplary embodiment of the present disclosure, a computer readable storage medium storing a computer program is provided, which, when executed by a processor, implements the method for calculating the turbulence spatial representative of the wind measurement tower as described above.

[0022] According to another exemplary embodiment of the present disclosure, a computer is provided, comprising a readable medium storing a computer program and a processor, characterized in that when the processor executes the computer program, the method for calculating the turbulence spatial representative of the wind measurement tower as described above is executed.

[0023] The method and device described above can quantitatively determine the turbulence spatial representative of the wind measurement tower to the field area, provide technical support for the wind measurement scheme design, and can be used to determine the reliability of the turbulence intensity simulation result at the wind turbine position, and provide technical support for the wind turbine load optimization.

[0024] Furthermore, additional aspects and / or advantages of the present general inventive concept will be set forth in part in the description that follows, and in part will be obvious from the description, or can be learned by practice of the present general inventive concept. BRIEF DESCRIPTION OF DRAWINGS

[0025] These and / or other aspects and advantages of the present disclosure will become apparent and more readily appreciated from the following description, taken in conjunction with the accompanying drawings, in which:

[0026] Figure 1 is a flow chart illustrating a method for calculating the turbulence spatial representative of the wind measurement tower according to an exemplary embodiment of the present disclosure;

[0027] Figure 2 is a flow chart illustrating a method for establishing a turbulence spatial representative model according to an exemplary embodiment of the present disclosure; and

[0028] Figure 3 is a block diagram illustrating a device for calculating the turbulence spatial representative of the wind measurement tower according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] The following description with reference to the accompanying drawings is provided to assist in a comprehensive understanding of embodiments of the present disclosure as defined by the claims and their equivalents. Various specific details are included to assist in understanding but are not intended to limit the present disclosure. Therefore, one of ordinary skill in the art will recognize that various changes and modifications of the embodiments described herein can be made without departing from the scope and spirit of the present disclosure. In addition, descriptions of well-known functions and constructions are omitted for clarity and conciseness.

[0030] The terms used in the specification will be defined briefly, and the embodiments will be described in detail. In the embodiments, wind power, also known as wind power generation, refers to the conversion of wind kinetic energy into electric energy. A wind farm is a tool invented by humans to utilize wind energy and combine a series of generators to achieve the purpose of generating electricity using wind energy. The turbulence intensity refers to the degree of random fluctuation of short-time wind speed, which is generally represented by the ratio of the average standard deviation of ten-minute wind speed measurement results to the average wind speed. The mesoscale data is meteorological data calculated using a mesoscale model, which can provide wind speed and direction time series data at a specified location as input data for numerical simulation of wind resources in the field area. The wind measurement scheme design gives the number, location, and equipment configuration of wind measurement points required for wind measurement in the wind farm.

[0031] All terms used in the specification, including descriptive or technical terms, should be interpreted as having meanings apparent to those of ordinary skill in the art. However, these terms can have different meanings according to the intention of those of ordinary skill in the art, precedents, or the emergence of new technology. In addition, some terms can be arbitrarily selected by the applicant, and in this case, the meaning of the selected terms will be described in detail in the detailed description of the disclosure. Therefore, the terms used in the disclosure should not be interpreted based on their names alone, but must be defined based on the meaning of the terms together with the description in the entire specification.

[0032] In the following specification, the singular form includes the plural form unless the context clearly indicates otherwise.

[0033] The existing method has a great dependence on the technical and experience levels of the staff because an engineer needs to artificially judge the turbulence space representativeness of the wind measurement tower to the wind turbine generator in the wind farm according to the geographical and meteorological environment. This brings great uncertainty to the wind measurement scheme design, the risk is difficult to quantify, and directly affects the economic benefit of the wind power project. In addition, for a field area with complex wind resources, such as a mountain wind farm, it is difficult for an engineer to ensure the turbulence representativeness of the wind measurement tower to the position of the wind turbine generator based on experience, and the method and process of evaluating the turbulence space representativeness of the wind measurement tower based on experience are difficult to trace and cannot achieve systematic knowledge management.

[0034] The disclosure reduces the uncertainty introduced by the staff based on experience by quantifying the turbulence space representativeness of the wind measurement tower, and can directly find areas with low turbulence space representativeness of the wind measurement tower to provide a basis for risk avoidance or supplementary wind measurement. At the same time, it also achieves systematic, manageable, and upgradeable methods.

[0035] Hereinafter, according to various embodiments of the disclosure, the method and apparatus of the disclosure will be described with reference to the accompanying drawings.

[0036] Figure 1 is a flowchart showing a method of calculating a representative of a turbulence space of a wind measurement tower according to an example embodiment of the present disclosure. The method of the present disclosure can be executed by a main controller of a wind turbine generator unit or can be executed by a separate processor.

[0037] Since the turbulence space distribution calculation process is a highly complex nonlinear process, the present disclosure does not analyze from the principle of a numerical method turbulence model, but starts from the calculation results of actual project cases, and establishes an evaluation method of a representative of a turbulence space of a wind measurement tower through a machine learning method, which will be described in detail below with reference to Figure 1 .

[0038] Referring to Figure 1 , in step S101, flow field data and geographical data of a target location and a wind measurement tower in a wind farm are acquired.

[0039] As an example, mesoscale data of a wind farm to be developed can be collected first, and a wind resource numerical simulation calculation is performed on the wind farm area according to the collected mesoscale data, and then flow field data of the target location and the wind measurement tower in the wind farm can be extracted from the wind resource numerical simulation calculation results.

[0040] Alternatively, actual wind measurement data can be used as input to obtain flow field data via wind resource numerical simulation calculation. Alternatively, both actual wind measurement data and collected mesoscale data can be used as input to obtain flow field data via wind resource numerical simulation.

[0041] As another example, mesoscale data at the location of the wind measurement tower can be collected, the field area is gridded, and a wind resource numerical simulation calculation is performed on the wind farm, and flow field data of each grid point at a specified height within the wind farm area is extracted from the wind resource numerical simulation calculation results, and flow field data at the same specified height at the location of the wind measurement tower is obtained from the wind resource numerical simulation calculation results.

[0042] In the present disclosure, the flow field data can include the results of the field area flow field numerical simulation calculation, such as wind acceleration factor, turbulence intensity, horizontal wind direction deflection, inflow angle, etc. at the wind measurement tower and the wind turbine generator unit. The geographical data can include the coordinates, elevation, roughness, etc. of the wind measurement tower and the wind turbine generator unit. However, the above examples are only exemplary, and the present disclosure is not limited thereto.

[0043] In step S102, turbulence-related characteristic factors are extracted from the flow field data and geographical data of the target location and the flow field data and geographical data of the wind measurement tower.

[0044] The extraction of the characteristic factors can be accomplished by calculation between the flow field data and geographical data of the target location and the flow field data and geographical data of the wind measurement tower. Here, since it is for the wind farm to be developed, the flow field data of the wind measurement tower and the target location can be numerical simulation results. The suitable address of the wind measurement tower and the wind turbine generator can be selected according to the numerical simulation results and the turbulence space representative model.

[0045] As an example, the characteristic factors of the present disclosure can include at least one of the turbulence intensity difference, the height distance, the horizontal distance, the wind direction deflection angle difference, the inflow angle difference, the terrain complexity, and the roughness between the target location and the wind measurement tower, however the above example is only exemplary, and the present disclosure is not limited thereto.

[0046] In step S103, the characteristic factors are applied to the turbulence space representative model to calculate the turbulence space representation of the wind measurement tower to the target location. The turbulence space representative model of the present disclosure can be established based on the mutual promotion results of at least two wind measurement towers in the actual completed project site area. Preferably, the mutual promotion results of the wind measurement towers in the actual completed multiple project site areas (the number of wind measurement towers in each project site area is not less than two) can be used to establish the turbulence space representative model.

[0047] In the present disclosure, the quantifiable value of the turbulence space representation of the wind measurement tower is defined, that is, the wind measurement data of the wind measurement tower is taken as the input data of the flow field simulation to calculate the turbulence intensity at the target location of the site area, and the absolute deviation that can occur by comparing the calculated turbulence intensity at the target location with the true turbulence intensity is the turbulence space representation of the wind measurement tower to the target location.

[0048] Optionally, the turbulence space representation can be quantified as one of the deviation value, the mean square error, the root mean square error, the standard deviation, and the variance between the turbulence intensities, thereby improving the accuracy of evaluating the turbulence space representation of the wind measurement tower.

[0049] As an example, the quantifiable value of the turbulence space representation of the wind measurement tower to the target location can be displayed, and the quantifiable value can be extracted. Optionally, the atlas of the turbulence space representation of the wind measurement tower to the target location can be displayed.

[0050] In addition, the turbulence space representation of the sector of the wind farm can be calculated, or the sector results can be integrated according to the wind frequency. For example, the main wind frequency and the main wind energy wind direction are important reference wind directions for the design of the wind farm, and the characteristic factors extracted from the input sector flow field numerical simulation calculation results in the turbulence space representative model, that is, the turbulence space representation of the wind measurement tower to the corresponding sector of the site area can be calculated and obtained.

[0051] In the present disclosure, when a wind resource numerical simulation calculation is performed using mesoscale data, flow field data and geographical data of each grid point at a specified height within the wind farm can be extracted and calculated with flow field data and geographical data at the same height as the location of the wind measurement tower, and the extraction of the characteristic factors related to turbulence is completed. The characteristic factors of each grid point are applied to the turbulence spatial representative model, thereby obtaining the turbulence spatial representation of the wind measurement tower to the wind farm area. Similarly, the turbulence spatial representation of the wind measurement tower to the sub-sector can also be calculated.

[0052] How to establish a turbulence spatial representative model will be described in detail below with reference to Figure 2 Figure 2 is a flow chart showing a method of establishing a turbulence spatial representative model according to an exemplary embodiment of the present disclosure. As shown in Figure 2 The turbulence spatial representative model can be established by using a machine learning method.

[0053] Referring to Figure 2 In step S201, wind measurement data, flow field data and geographical data of at least two wind measurement towers in an existing project wind farm are obtained. Here, the wind measurement data can include at least one of wind speed, wind direction and turbulence intensity, the flow field data can include at least one of wind acceleration factor, turbulence intensity, wind direction deflection angle, inflow angle, and the geographical data can include at least one of coordinates, elevation and roughness. However, the above examples are only exemplary, and the present disclosure is not limited thereto.

[0054] The turbulence spatial representative model of the present disclosure can be established based on the mutual promotion results of at least two wind measurement towers in an actual completed project area. Preferably, the turbulence spatial representative model can be established by using the mutual promotion results of the wind measurement towers in a plurality of actual completed project areas (the number of wind measurement towers in each project area is not less than two).

[0055] As an example, two wind measurement towers are selected in a completed project area, one of which is an input wind measurement tower and the other is an output wind measurement tower. The information to be collected can include wind measurement data, flow field data and geographical data of the input wind measurement tower and the output wind measurement tower. For example, the wind measurement data of the input and output wind measurement towers can include time series data of wind speed, wind direction and turbulence intensity, the flow field data can include wind acceleration factor, turbulence intensity, horizontal wind direction deflection, inflow angle, etc. at the positions of the input and output wind measurement towers, and the geographical data can include coordinates, elevation, roughness, etc. at the positions of the input and output wind measurement towers. However, the above examples are only exemplary, and the present disclosure is not limited thereto.

[0056] In step S202, characteristic factors related to turbulence are extracted according to the wind measurement data, flow field data and geographical data of the at least two wind measurement towers.

[0057] ​First, the wind tower turbulence space representativeness can be quantified. For example, the wind data of the input wind tower is taken as the input data of the flow field simulation, the turbulence intensity at the output wind tower position is calculated, and then the calculated turbulence intensity at the output wind tower position is compared with the actual turbulence intensity at the output wind tower position, and the comparison result is taken as the turbulence space representativeness of the wind tower. Here, the comparison result can include one of the bias value, mean square error, root mean square error, standard deviation and variance of the turbulence intensity between the input and output wind towers. However, the above example is only exemplary, and the present disclosure is not limited thereto.

[0058] Through correlation analysis, the characteristic factors related to turbulence can include at least one of the turbulence intensity difference, height distance, horizontal distance, wind direction deflection angle difference, inflow angle difference, terrain complexity and roughness between the input wind tower and the output wind tower. However, the above example is only exemplary, and the present disclosure is not limited thereto.

[0059] In step S203, the extracted characteristic factors are taken as the input of the turbulence space representativeness model, and the comparison result between the turbulence intensity measurement value and the numerical simulation calculation value of the corresponding wind tower is taken as the output of the turbulence space representativeness model, and the turbulence space representativeness model is established by using a machine learning method. For example, the characteristic factors of the input wind tower and the output wind tower are taken as the input, and the comparison result between the measurement value and the numerical simulation calculation value of the turbulence intensity of the output wind tower is taken as the output, and the turbulence space representativeness model is established by using a machine learning method.

[0060] As an example, a multiple linear regression method can be used to establish the turbulence space representativeness model, the parameters of the turbulence space representativeness model are adjusted to minimize the mean square error as the optimization target, and the stability of the turbulence space representativeness model is tested using 10-fold cross-validation. The above machine learning method is only exemplary, and the present disclosure can also use other machine learning algorithms (such as SVR, MLP, RandomForest, LinearRegression, XGBoost, LightGBM, CatBoost, etc.) and the fusion of machine learning algorithms, etc.

[0061] The turbulence space representativeness model of the present disclosure is variable, that is, the training of machine learning according to different regional project sets obtains a calculation model suitable for different regional environments. Therefore, the method and model according to the present disclosure can be suitable for various projects and / or regions, facilitating upgrading and management.

[0062] According to the embodiment of the present disclosure, instead of starting from the principle of calculating the turbulence model from the numerical value, a quantitative model of the turbulence space representation of the wind measurement tower is established based on the completed projects and the machine learning algorithm, which not only improves the accuracy of evaluating the turbulence space representation of the wind measurement tower on the site, but also intuitively and easily finds the area with low turbulence representation of the wind measurement tower, providing a basis for risk avoidance or supplementary wind measurement.

[0063] Figure 3 is a block diagram illustrating an apparatus for calculating turbulence space representation of a wind measurement tower according to an exemplary embodiment of the present disclosure. The apparatus 300 for calculating turbulence space representation of a wind measurement tower can be implemented by a master controller of a wind turbine generator set, or formed as a single entity separately from the master controller and installed in the wind turbine generator set.

[0064] Referring to Figure 3 , the apparatus 300 can include a data acquisition module 301 and a data processing module 302. Each module in the apparatus 300 can be implemented by one or more modules, and the name of the corresponding module can vary depending on the type of the module. In various embodiments, some modules in the apparatus 300 can be omitted, or additional modules can also be included. In addition, the modules / elements according to various embodiments of the present disclosure can be combined to form a single entity, and thus can equivalently perform the functions of the corresponding modules / elements before the combination.

[0065] The data acquisition module 301 can acquire flow field data and geographical data of a target location and a wind measurement tower in a wind farm. Here, the flow field data can include a wind acceleration factor, a turbulence intensity, a wind direction deflection angle, an inflow angle, etc. The geographical data can include coordinates, an altitude, and a roughness, etc. However, the above examples are merely exemplary, and the present disclosure is not limited thereto.

[0066] For the flow field data, the data acquisition module 301 can obtain based on mesoscale data via wind resource numerical simulation calculation. The data acquisition module 301 can also input actual wind measurement data into a wind resource numerical simulation calculation software to obtain the flow field data. Alternatively, the data acquisition module 301 can obtain the flow field data using mesoscale data and actual wind measurement data via wind resource numerical simulation calculation.

[0067] The data processing module 302 can extract turbulence-related characteristic factors from the flow field data and the geographical data of the target location and the wind measurement tower, and apply the characteristic factors to a turbulence space representation model to calculate the turbulence space representation of the wind measurement tower on the target location. Here, the characteristic factors can include at least one of a turbulence intensity difference between the target location and the wind measurement tower, a height distance, a horizontal distance, a wind direction deflection angle difference, an inflow angle difference, a terrain complexity, and a roughness.

[0068] The device 300 can further include a display (not shown). The data processing module 302 can control the display to display a map of the turbulence spatial representativeness of the target location by the wind measurement tower according to the output of the turbulence spatial representativeness model, or display a quantitative value of the turbulence spatial representativeness of the target location by the wind measurement tower.

[0069] In addition, the data processing module 302 can establish the turbulence spatial representativeness model by using a machine learning method. The data processing module 302 can establish the turbulence spatial representativeness model based on the mutual pushing results of at least two wind measurement towers in an actual completed project site. For example, the turbulence spatial representativeness model can be established based on the mutual pushing results of wind measurement towers in a plurality of actual completed projects (the number of wind measurement towers in each project is not less than 2).

[0070] The data processing module 302 can establish the turbulence spatial representativeness model by using a regression method, taking the feature factors extracted from the wind measurement data, flow field data and geographical data of the at least two wind measurement towers as the input of the turbulence spatial representativeness model and taking the comparison results between the turbulence intensity measurement values and the numerical simulation values of the corresponding wind measurement towers as the output of the turbulence spatial representativeness model.

[0071] The data processing module 302 can adjust the parameters of the turbulence spatial representativeness model with the minimum mean square error as the optimization target.

[0072] The data processing module 302 can use 10-fold cross-validation to test the stability of the turbulence spatial representativeness model.

[0073] When the wind resource numerical simulation calculation is performed by using the mesoscale data, the data processing module 302 can extract the flow field data and geographical data of each grid point at a specified height in the wind farm, and perform calculation with the flow field data and geographical data at the same height as the location of the wind measurement tower, complete the extraction of the turbulence-related feature factors, apply the feature factors of each grid point to the turbulence spatial representativeness model, and thus obtain the turbulence spatial representativeness of the wind measurement tower to the site of the wind farm. Similarly, the turbulence spatial representativeness of the wind measurement tower to the sub-sector can also be calculated.

[0074] In addition, with reference to Figures 1 to 2 The method described can be implemented by a program (or instructions) recorded on a computer readable storage medium. For example, according to the exemplary embodiments of the present application, a computer readable storage medium can be provided, in which a program for performing the method described with reference to Figures 1 to 2Computer programs (or instructions) of the steps of the described method. For example, the computer programs (or instructions) can be used to perform the following method steps: obtaining target locations in a wind farm and flow field data and geographical data of a wind measurement tower; extracting turbulence-related characteristic factors from the flow field data and geographical data of the target locations and the flow field data and geographical data of the wind measurement tower; and applying the characteristic factors to a turbulence spatial representative model to calculate a turbulence spatial representation of the wind measurement tower for the target locations.

[0075] On the other hand, each of the above-described devices can also be implemented by hardware, software, firmware, middleware, microcode, or any combination thereof. When implemented in software, firmware, middleware, or microcode, the program code or code segments to carry out the corresponding operations can be stored in a computer-readable medium such as a storage medium, so that the processor can execute the corresponding operations by reading and running the corresponding program code or code segments.

[0076] For example, the exemplary embodiments of the present application can also be implemented as a computing device including a storage component and a processor, the storage component having stored therein a set of computer-executable instructions which, when executed by the processor, perform the method of calculating a turbulence spatial representation of a wind measurement tower according to the exemplary embodiments of the present application.

[0077] Those skilled in the art can understand that the present disclosure includes devices related to performing one or more of the operations / steps described in the present disclosure. These devices can be specifically designed and manufactured for the desired purpose, or can also include known devices in a general-purpose computer. These devices have computer programs stored therein which are selectively activated or reconfigured. Such computer programs can be stored in a computer-readable medium of the device (for example, a computer) or in any type of medium suitable for storing electronic instructions and respectively coupled to the bus, including but not limited to any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic cards or optical cards. That is, the readable medium includes any medium that stores or transmits information in a form readable by a device (for example, a computer).

[0078] While the present disclosure is shown and described with reference to exemplary embodiments, it is to be understood that various other changes can be made and equivalents employed, without departing from the spirit and scope of the disclosure as defined by the following claims and its equivalents.

Claims

1. A method for calculating the spatial representativeness of turbulence from a wind measurement tower, the method comprising: Acquire flow field data and geographic data of target locations and meteorological towers in the wind farm; Based on the target location and the flow field data and geographical data of the wind measuring tower, turbulence-related feature factors are extracted. The feature factors include at least one of the following: turbulence intensity difference between the target location and the wind measuring tower, height distance, horizontal distance, wind direction deflection angle difference, inflow angle difference, terrain complexity, and roughness. Characteristic factors are applied to the turbulent spatial representativeness model to calculate the turbulent spatial representativeness of the wind tower at the target location; The turbulence spatial representative model is established by using feature factors extracted from wind measurement data, flow field data, and geographical data from at least two wind measurement towers as inputs and the comparison between the measured values ​​of turbulence intensity from the wind measurement towers and the calculated values ​​from numerical simulations as outputs.

2. The method as described in claim 1, wherein, The spatial representativeness of turbulence is quantified as one of the following: deviation of turbulence intensity, mean square error, root mean square error, standard deviation, and variance.

3. The method as described in claim 1, wherein, The method further includes: The parameters of a representative model of turbulent space are adjusted with the goal of minimizing the mean square error; and Ten-fold cross-validation was used to test the stability of representative models of turbulent space.

4. The method of claim 1, wherein, The representative model of turbulent space is established based on the cross-referencing results of at least two anemometer towers in the actual completed project site.

5. The method of claim 1, wherein, The method further includes: Display a representative spatial turbulence map of the target location from the meteorological tower; or The display shows a quantitative value representing the spatial representativeness of the turbulence at the target location from the anemometer tower.

6. An apparatus for calculating the spatial representativeness of turbulence from a wind-measuring tower, the apparatus comprising: The data acquisition module is used to acquire flow field data and geographic data of the target location and the meteorological tower in the wind farm; The data processing module is used to extract turbulence-related feature factors based on the target location, the flow field data of the anemometer tower, and the geographical data, and to apply the feature factors to the turbulence spatial representativeness model to calculate the turbulence spatial representativeness of the anemometer tower to the target location. The feature factors include at least one of the following: turbulence intensity difference between the target location and the anemometer tower, height distance, horizontal distance, wind direction deflection angle difference, inflow angle difference, terrain complexity, and roughness. The data processing module is also used to take the feature factors extracted from wind measurement data, flow field data and geographical data from at least two wind measurement towers as input to the spatial representative model of turbulence and the comparison results between the turbulence intensity measurement values ​​of the wind measurement towers and the numerical simulation calculation values ​​as output to the spatial representative model of turbulence, and to establish the spatial representative model of turbulence by using regression methods.

7. An electronic device, comprising: Memory, used to store programs; as well as One or more processors When the program is run, the one or more processors execute the method for calculating the spatial representativeness of turbulence at a wind tower as described in any one of claims 1 to 5.

8. A computer-readable recording medium, wherein, The device stores a program, characterized in that the program includes instructions for performing the method for calculating the spatial representativeness of turbulence at a wind tower as described in any one of claims 1 to 5.

Images