Atmospheric turbulence intensity and gust factor evaluation method, system and device
By adopting numerical weather forecasting mode and machine learning methods in wind resource assessment, a prediction model of turbulence intensity and gust factor is established, which solves the problem of inaccurate evaluation in the existing technology and achieves a more efficient and accurate wind resource assessment.
Patent Information
- Application Number
- CN202510001583.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-01-02
- Publication Date
- 2025-05-06
AI Technical Summary
The prior art is difficult to accurately evaluate turbulent intensity and gust factors in wind resource assessment, resulting in insufficient assessment of the bearing capacity of wind turbines in extreme wind conditions.
A method based on numerical weather forecast mode (such as WRF mode) is adopted, combined with machine learning methods, to establish a prediction model of turbulence intensity and gust factor. By obtaining the meteorological data of WRF simulation and on-site measurement data, multi-meteorological elements are corrected, and a machine learning regression model is constructed to realize the estimation of turbulence intensity and gust factor.
It improves the accuracy of turbulence intensity and gust factor evaluation, simplifies the evaluation process, reduces the evaluation cost, and provides a more scientific basis for wind farm design and operation decision-making.
Smart Images
Figure CN119937052A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of wind resource assessment, and in particular to a method, system and device for assessing atmospheric turbulence intensity and gust factor. Background Art
[0002] With the transformation of the global energy structure and the advancement of carbon neutrality goals, the development and utilization of wind energy as a clean and renewable energy form has received unprecedented attention. Wind energy is not only environmentally friendly and pollution-free, but also has abundant resources, good economic efficiency and high flexibility. It is an important way to cope with energy crises and environmental challenges.
[0003] As the basis and primary link of wind energy development and utilization, the accuracy of wind resource assessment is directly related to the economic benefits and safety of wind power projects. Traditional wind resource assessment mainly relies on on-site measurement technology. However, this method has problems such as high time cost and expense, limited spatial coverage, and high environmental dependence. In order to overcome these limitations, numerical simulation technology has gradually become an important means of wind resource assessment. Based on meteorological principles and numerical methods, numerical simulation methods use physical models to simulate and predict wind farms, which can obtain comprehensive and continuous wind resource maps, better adapting to the assessment needs of wind farms in different regions and of different sizes.
[0004] In wind resource assessment, accurate assessment of turbulence intensity (TI) and gust factor (GU) is also an important part of wind resource assessment. Turbulence intensity affects the load and life of wind turbines, while gust factor is of great significance for assessing the load-bearing capacity of wind turbines under extreme wind conditions. Turbulence intensity can be simulated using atmospheric models such as weather forecasts and large eddy simulation models. However, the computational cost of large eddy simulation models is too high to simulate for a long time, while mesoscale meteorological models are much more efficient. However, turbulent kinetic energy (TKE) can only be estimated by applying applicable turbulence parameterizations, and then combined with some semi-empirical formulas to estimate TI. This semi-empirical formula is usually based on limited measured data and simplified physical assumptions, and has deficiencies in prediction accuracy and generalization ability. Machine learning methods can establish the relationship between TKE and TI in a more accurate and effective way, thereby achieving accurate assessment of TI. In addition, the gust factor is of great significance for evaluating the load bearing capacity of wind turbines under extreme wind conditions and the structural design of wind turbines. Therefore, accurate evaluation of the gust factor is also of great significance for wind resource assessment. Therefore, how to establish an accurate estimation framework for turbulence intensity and gust factor based on WRF simulation results is of great significance for wind resource assessment.
[0005] In order to overcome the limitations of existing methods, a framework for estimating turbulence intensity and gust factor based on numerical weather forecast models (such as the WRF model) has emerged. This framework uses meteorological data simulated by the WRF model and combines machine learning methods to establish a prediction model for turbulence intensity and gust factor. By mining the potential information in meteorological data, the framework can more accurately reflect the complex relationship between turbulence intensity and gust factor and meteorological elements, thereby improving the accuracy and generalization of predictions.
[0006] In summary, the framework for estimating turbulence intensity and gust factor based on numerical weather forecast models is an important technical support for the development and utilization of wind energy resources. In the future, with the continuous accumulation of measured data and the continuous optimization of machine learning methods, the prediction performance and generalization ability of this framework will be further improved, providing more powerful technical support for the sustainable development of the wind energy industry. Summary of the invention
[0007] The present invention aims to overcome the above-mentioned shortcomings of the prior art and provide a method, system and device for evaluating atmospheric turbulence intensity and gust factor.
[0008] The technical solution adopted by the present invention is as follows:
[0009] A method for evaluating atmospheric turbulence intensity and gust factor comprises the following steps:
[0010] S1: Obtain multiple meteorological elements including wind speed simulated by WRF, use the field measured wind speed data, and adopt machine learning methods to correct the horizontal wind speed;
[0011] S2: Obtain multiple meteorological elements including turbulent kinetic energy simulated by WRF, use the field measured turbulent kinetic energy, and adopt machine learning methods to correct the turbulent kinetic energy;
[0012] S3: Based on the measured horizontal wind speed and turbulent kinetic energy data as input, the horizontal turbulence intensity and gust factor calculated according to the measured data are used as outputs to construct machine learning regression models of turbulence intensity and gust factor;
[0013] S4: Based on the corrected horizontal wind speed and turbulent kinetic energy, the turbulence intensity and gust factor are estimated using the machine learning regression model of the turbulence intensity and gust factor.
[0014] Furthermore, in steps S1 and S2, the field measured wind speed data is cleaned, including: using a preset outlier identification method to identify and delete outlier data in the wind speed data, and using a preset missing value processing method to interpolate missing data in the wind speed data to obtain cleaned data.
[0015] Furthermore, in steps S1 and S2, the time resolution of the field measured data is higher than 1 Hz.
[0016] Furthermore, the multiple meteorological elements in step S1 are wind speed, temperature, humidity and pressure; and the multiple meteorological elements in step S2 are wind speed, turbulent kinetic energy, temperature, humidity and pressure.
[0017] Furthermore, the machine learning regression model of turbulence intensity established in step S3 takes turbulent kinetic energy and horizontal wind speed as input, and takes horizontal turbulence intensity as output; the machine learning regression model of gust factor takes turbulent kinetic energy and horizontal wind speed as input, and takes gust factor as output.
[0018] Furthermore, machine learning methods or models include multi-layer perceptron, support vector machine and random forest algorithm.
[0019] Furthermore, an atmospheric turbulence intensity and gust factor evaluation system comprises:
[0020] Wind speed correction module: used to obtain multiple meteorological elements including wind speed simulated by WRF, use the field measured wind speed data, and adopt machine learning methods to correct the horizontal wind speed;
[0021] Turbulent kinetic energy correction module: used to obtain multiple meteorological elements including turbulent kinetic energy simulated by WRF, and use the field measured turbulent kinetic energy to correct the turbulent kinetic energy using machine learning methods;
[0022] Model building module: used to build machine learning regression models of turbulence intensity and gust factor based on the measured horizontal wind speed and turbulent kinetic energy data as input and the horizontal turbulence intensity and gust factor calculated based on the measured data as output;
[0023] Evaluation module: used to estimate turbulence intensity and gust factor based on the corrected horizontal wind speed and turbulent kinetic energy using the machine learning regression model of turbulence intensity and gust factor.
[0024] Furthermore, an atmospheric turbulence intensity and gust factor assessment device includes a memory and one or more processors, wherein the memory stores executable code, and when the processor executes the executable code, an atmospheric turbulence intensity and gust factor assessment method is implemented.
[0025] Furthermore, a computer-readable storage medium stores a program thereon, and when the program is executed by a processor, a method for evaluating atmospheric turbulence intensity and gust factor is implemented.
[0026] Furthermore, a computer program product includes a computer program, and when the computer program is executed by a processor, a method for evaluating atmospheric turbulence intensity and gust factor is implemented.
[0027] Based on the numerical weather forecast model, the present invention proposes an innovative method, system and device for evaluating atmospheric turbulence intensity and gust factor. The invention has important breakthroughs and practical value in the field of wind resource evaluation technology, and the specific beneficial effects are as follows:
[0028] 1. Improve the accuracy of assessment: By combining machine learning methods, the wind speed and turbulent kinetic energy simulated by WRF (Weather Research and Forecasting Model) are corrected for multiple meteorological factors, effectively reducing the deviation between WRF simulation results and measured data. This makes the assessment results more accurate and reliable, providing a solid foundation for wind resource assessment.
[0029] 2. Solve the problem of output variable application: This invention solves the problem that WRF output variables cannot be directly used to estimate turbulence intensity and gust factor. By establishing a prediction model based on parameters such as wind speed and turbulent kinetic energy, it is possible to directly apply these output variables to the estimation of turbulence intensity and gust factor, simplifying the evaluation process and improving the evaluation efficiency.
[0030] 3. Promote the development and utilization of wind energy resources: Accurate assessment of atmospheric turbulence intensity and gust factor is crucial for the development and utilization of wind energy resources. The present invention provides a more accurate and effective way to help optimize the site selection, design and operation of wind farms, improve wind energy utilization efficiency, reduce power generation costs, and promote the sustainable development of the wind energy industry.
[0031] 4. Enhanced adaptability: The assessment method, system and device can adapt to the wind resource assessment needs in different regions and under different meteorological conditions, and have strong versatility and practicality. Whether in complex terrain or changing climate conditions, it can provide accurate assessment results and provide strong support for the development of wind energy resources.
[0032] 5. Reduce assessment costs: Traditional wind resource assessment methods often require a lot of on-site observations and data collection, which is costly and time-consuming. However, the present invention uses numerical weather forecast models and machine learning methods to significantly reduce assessment costs, shorten assessment cycles, and improve assessment efficiency.
[0033] 6. Improve scientific decision-making: Accurate turbulence intensity and gust factor assessment results can provide a scientific basis for the design, construction and operation of wind farms. Through the method of the present invention, the system can generate a more refined wind resource assessment report to help decision makers make more scientific and reasonable decisions, reduce investment risks and increase project returns.
[0034] 7. Promote technological progress: This invention combines numerical weather forecasting models with machine learning methods to provide a new idea and method for wind resource assessment technology. This interdisciplinary technology integration helps promote the progress and development of wind resource assessment technology and provide impetus for innovation in the wind energy industry.
[0035] In summary, the method, system and device for evaluating atmospheric turbulence intensity and gust factor based on numerical weather forecast model of the present invention are not only technically innovative and practical, but also have positive impacts in many aspects such as economy, environment and society, and are of great significance for promoting the development and utilization of wind energy resources. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] Figure 1 It is a flow chart of a method for evaluating atmospheric turbulence intensity and gust factor based on a numerical weather forecast model provided by an embodiment of the present invention;
[0037] Figure 2 It is a technical roadmap of an atmospheric turbulence intensity and gust factor evaluation method based on a numerical weather forecast model provided by an embodiment of the present invention;
[0038] Figure 3 It is a WRF simulation area setting diagram in a method for evaluating atmospheric turbulence intensity and gust factor based on a numerical weather forecast model provided by an embodiment of the present invention.
[0039] Figure 4 It is a structural schematic diagram of an atmospheric turbulence intensity and gust factor evaluation device based on a numerical weather forecast model provided in an embodiment of the present invention.
[0040] Specific Examples
[0041] The present invention will be described in detail below in conjunction with the accompanying drawings.
[0042] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.
[0043] Embodiment 1
[0044] An embodiment of the present invention is a method for evaluating atmospheric turbulence intensity and gust factor based on a numerical weather model WRF, such as Figure 1 and Figure 2 As shown, the specific steps are as follows:
[0045] High-precision wind speed measurement equipment was used to continuously collect observation data from Doppler wind radars deployed in a certain area for one month, with a sampling frequency of at least 1 Hz. The wind speed data was then cleaned and outliers were identified and removed using a moving median filter with a window size of 600. Missing values were then interpolated using linear interpolation.
[0046] The WRF model is used to simulate the wind farm planning area. The central longitude and latitude coordinates are 40.06°E, 97.54°N. A three-layer nested grid design is adopted. The resolutions of D01, D02 and D03 are 9km, 3km and 1km respectively, and the number of grids is 121×121 (e.g. Figure 3 As shown in the figure, the PBL parameterization scheme adopts the MYNN2 planetary boundary layer parameterization scheme that can accurately simulate convective weather phenomena, the surface parameterization scheme uses MYNN, the land surface model uses the Noah scheme, the longwave radiation uses the RRTM scheme, the shortwave radiation uses the Dudhia scheme, the cumulus parameterization uses Kain-Fritsch (1km, 3km closed), and the microphysical process uses the WSM6 scheme.
[0047] Using machine learning methods such as support vector machines, multi-layer perceptrons and random forests, the wind speed and turbulent kinetic energy simulated by WRF were corrected for multiple meteorological factors. The meteorological factors such as wind speed, temperature, humidity and pressure simulated by WRF were used as input, and the measured wind speed was used as output to correct the horizontal wind speed to improve the accuracy of the simulated wind speed; then the meteorological factors such as wind speed, turbulent kinetic energy, temperature, humidity and pressure simulated by WRF were used as input, and the measured turbulent kinetic energy was used as output to correct the turbulent kinetic energy to obtain more accurate turbulent kinetic energy data. By comparing the correction effects of different methods, that is, according to the size of parameters such as RMSE, the random forest algorithm was selected for the subsequent steps.
[0048] Using machine learning methods such as support vector machine, multi-layer perceptron and random forest, the wind speed and turbulent kinetic energy calculated by Doppler wind radar are used as input, and the horizontal turbulence intensity and gust factor calculated according to the measured data are used as output. Multi-layer perceptron, support vector machine and random forest algorithms are used for training to obtain the regression model of turbulence intensity and gust factor. The training process is as follows: the data set is divided into training set and test set in a ratio of 3:1, where the training set is used for learning and the test set is used for evaluating the algorithm model; during the training process, the machine learning algorithm parameters are tuned, and the corresponding loss function value is calculated by trying different parameter values, and the parameter combination that minimizes the loss function is selected as the final model parameter setting.
[0049] Based on the corrected horizontal wind speed and turbulent kinetic energy, the turbulence intensity and gust factor are estimated using the regression model of the turbulence intensity and gust factor.
[0050] Using the above framework, the turbulence intensity and gust factor were estimated based on the WRF simulation results. The prediction results of the test set were verified by measured data to evaluate the accuracy and reliability of the estimated results. It was found that there was good consistency between the estimated turbulence intensity and the measured data, and the determination coefficient R 2 The estimated results of gust factor also show good performance similar to that of turbulence intensity, R 2 The correlation is significant. In summary, the estimation framework based on the WRF model proposed in this method can accurately and effectively estimate the turbulence intensity and gust factor, providing strong support for the research in the field of wind resource assessment.
[0051] Finally, based on the verification results, the model is optimized and iterated. The prediction accuracy of turbulence intensity and gust factor is further improved by adjusting model parameters and adding characteristic variables.
[0052] Embodiment 2
[0053] Corresponding to the above-mentioned embodiment of the method for evaluating atmospheric turbulence intensity and gust factor based on numerical weather forecast model, the present invention also provides an embodiment of an atmospheric turbulence intensity and gust factor evaluation system based on numerical weather forecast model. The system includes a wind speed correction module, a turbulent kinetic energy correction module, a model building module and an evaluation module; the implementation process of each module is specifically referred to the implementation steps of the above-mentioned evaluation method.
[0054] The wind speed correction module is used to obtain multiple meteorological elements including wind speed simulated by WRF, and use the field measured wind speed data to correct the horizontal wind speed using a machine learning method;
[0055] The turbulent kinetic energy correction module is used to obtain multiple meteorological elements including turbulent kinetic energy simulated by WRF, and uses the turbulent kinetic energy measured on site to correct the turbulent kinetic energy using a machine learning method;
[0056] The model building module is used to build a machine learning regression model of turbulence intensity and gust factor based on the measured horizontal wind speed and turbulent kinetic energy data as input, and the horizontal turbulence intensity and gust factor calculated according to the measured data as output;
[0057] The evaluation module is used to estimate the turbulence intensity and gust factor based on the corrected horizontal wind speed and turbulent kinetic energy using the machine learning regression model of the turbulence intensity and gust factor.
[0058] Embodiment 3
[0059] Corresponding to the aforementioned embodiment of a method for evaluating atmospheric turbulence intensity and gust factor based on a numerical weather forecast model, the present invention also provides an embodiment of a device for evaluating atmospheric turbulence intensity and gust factor based on a numerical weather forecast model.
[0060] See also Figure 4 An embodiment of the present invention provides an atmospheric turbulence intensity and gust factor assessment device based on a numerical weather forecast model, comprising a memory and one or more processors, wherein the memory stores executable code, and when the processor executes the executable code, it is used to implement an atmospheric turbulence intensity and gust factor assessment method based on a numerical weather forecast model in the above embodiment.
[0061] An embodiment of an atmospheric turbulence intensity and gust factor assessment device based on a numerical weather forecast model provided by the present invention can be applied to any device with data processing capabilities, and the device with data processing capabilities can be a device or apparatus such as a computer. The device embodiment can be implemented through software, or through hardware or a combination of software and hardware. Taking software implementation as an example, as a device in a logical sense, it is formed by the processor of any device with data processing capabilities in which it is located reading the corresponding computer program instructions in the non-volatile memory into the internal memory for execution. From a hardware perspective, if Figure 4 As shown in FIG. 1 , a hardware structure diagram of an atmospheric turbulence intensity and gust factor evaluation device based on a numerical weather forecast model provided by the present invention is provided for any device with data processing capability, except Figure 4 In addition to the processor, memory, network interface, and non-volatile memory shown, any device with data processing capabilities in which the apparatus in the embodiments is located may also include other hardware, generally based on the actual functions of the device with data processing capabilities, which will not be described in detail.
[0062] The implementation process of the functions and effects of each unit in the above-mentioned device is specifically described in the implementation process of the corresponding steps in the above-mentioned method, and will not be repeated here.
[0063] For the device embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The device embodiment described above is only schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of the present invention. Ordinary technicians in this field can understand and implement it without paying creative work.
[0064] Embodiment 4
[0065] An embodiment of the present invention further provides a computer-readable storage medium having a program stored thereon. When the program is executed by a processor, a method for evaluating atmospheric turbulence intensity and gust factor based on a numerical weather forecast model in the above embodiment is implemented.
[0066] The computer-readable storage medium may be an internal storage unit of any device with data processing capability described in any of the aforementioned embodiments, such as a hard disk or a memory. The computer-readable storage medium may also be an external storage device of any device with data processing capability, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), an SD card, a flash card (Flash Card), etc. equipped on the device. Furthermore, the computer-readable storage medium may also include both an internal storage unit and an external storage device of any device with data processing capability. The computer-readable storage medium is used to store the computer program and other programs and data required by any device with data processing capability, and may also be used to temporarily store data that has been output or is to be output.
[0067] The present invention also provides a computer program product, including a computer program, which, when executed by a processor, implements the method for evaluating atmospheric turbulence intensity and gust factor based on a numerical weather forecast model.
[0068] The above description is only a preferred embodiment of the invention and is not intended to limit the invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the invention should be included in the protection scope of the invention.
Claims
1. A method for evaluating atmospheric turbulence intensity and gust factor, characterized in that: The following steps are involved: S1: Obtain multiple meteorological elements including wind speed simulated by WRF, use the field measured wind speed data, and adopt machine learning methods to correct the horizontal wind speed; S2: Obtain multiple meteorological elements including turbulent kinetic energy simulated by WRF, use the field measured turbulent kinetic energy, and adopt machine learning methods to correct the turbulent kinetic energy; S3: Based on the measured horizontal wind speed and turbulent kinetic energy data as input, the horizontal turbulence intensity and gust factor calculated according to the measured data are used as outputs to construct machine learning regression models of turbulence intensity and gust factor; S4: Based on the corrected horizontal wind speed and turbulent kinetic energy, the turbulence intensity and gust factor are estimated using the machine learning regression model of the turbulence intensity and gust factor.
2. The method for evaluating atmospheric turbulence intensity and gust factor according to claim 1, characterized in that: In the steps S1 and S2, the field measured wind speed data is cleaned, including: using a preset outlier identification method to identify and delete outlier data in the wind speed data, and using a preset missing value processing method to interpolate missing data in the wind speed data to obtain cleaned data.
3. The method for evaluating atmospheric turbulence intensity and gust factor according to claim 1, characterized in that: In the steps S1 and S2, the time resolution of the field measured data is higher than 1 Hz.
4. The method for evaluating atmospheric turbulence intensity and gust factor according to claim 1, characterized in that: The multiple meteorological elements in step S1 are wind speed, temperature, humidity and pressure; the multiple meteorological elements in step S2 are wind speed, turbulent kinetic energy, temperature, humidity and pressure.
5. The method for evaluating atmospheric turbulence intensity and gust factor according to claim 1, characterized in that: The machine learning regression model of turbulence intensity established in step S3 takes turbulent kinetic energy and horizontal wind speed as input, and takes horizontal turbulence intensity as output; the machine learning regression model of gust factor takes turbulent kinetic energy and horizontal wind speed as input, and takes gust factor as output.
6. The method for evaluating atmospheric turbulence intensity and gust factor according to claim 1, characterized in that: The machine learning method or model includes a multi-layer perceptron, a support vector machine and a random forest algorithm.
7. An atmospheric turbulence intensity and gust factor evaluation system, applied to an atmospheric turbulence intensity and gust factor evaluation method according to any one of claims 1 to 6, characterized in that: include: Wind speed correction module: used to obtain multiple meteorological elements including wind speed simulated by WRF, use the field measured wind speed data, and adopt machine learning methods to correct the horizontal wind speed; Turbulent kinetic energy correction module: used to obtain multiple meteorological elements including turbulent kinetic energy simulated by WRF, and use the field measured turbulent kinetic energy to correct the turbulent kinetic energy using machine learning methods; Model building module: used to build machine learning regression models of turbulence intensity and gust factor based on the measured horizontal wind speed and turbulent kinetic energy data as input and the horizontal turbulence intensity and gust factor calculated based on the measured data as output; Evaluation module: used to estimate turbulence intensity and gust factor based on the corrected horizontal wind speed and turbulent kinetic energy using the machine learning regression model of turbulence intensity and gust factor.
8. An atmospheric turbulence intensity and gust factor evaluation device, applied to an atmospheric turbulence intensity and gust factor evaluation method according to any one of claims 1 to 6, characterized in that: It comprises a memory and one or more processors, wherein the memory stores executable codes, and when the processor executes the executable codes, an atmospheric turbulence intensity and gust factor evaluation method as described in claims 1 to 6 is implemented.
9. A computer-readable storage medium, characterized in that: A program is stored thereon, and when the program is executed by a processor, an atmospheric turbulence intensity and gust factor evaluation method as described in claims 1 to 6 is implemented.
10. A computer program product, characterized in that: It comprises a computer program, and when the computer program is executed by a processor, it implements the atmospheric turbulence intensity and gust factor evaluation method described in claims 1-6.