A data-driven wind turbine blade icing mass prediction method

Abstract

The application discloses a kind of wind turbine blade icing mass prediction methods based on data driving, method includes: based on preset value range, obtain sampling data;Simulation is carried out by CFD simulation software, and the corresponding icing mass data set under different parameter conditions is obtained;Icing mass data set obtained by simulation is compared with the data set of laboratory environment simulation result and is corrected;According to the icing mass data set obtained after correction, respectively to each variable Application polynomial fitting obtains the order relationship of the variable and icing mass after no-parameter system identification, obtains the function relationship of each parameter and icing mass;The variable value to be predicted is obtained by actual environmental information, and the variable value to be predicted is predicted according to the function relationship, and the icing prediction result is obtained.The application has the advantages of low cost, strong real-time, high precision, small data processing amount when using, etc., and can be widely applied in data processing technical field.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a data-driven method for predicting the icing quality of wind turbine blades. Background Technology

[0002] In recent years, wind power generation has developed rapidly and has become a research hotspot in the field of new energy. Ice accumulation on wind turbine blades can have a significant impact on the operation of wind turbines. If large-scale continuous tripping of wind turbines occurs under extreme weather conditions, it will lead to a large power deficit in the system, and may even cause large-scale power outages in some areas.

[0003] Current domestic and international research mainly relies on machine learning to predict the icing quality of wind turbine blades based on historical wind farm monitoring data. This method has insufficient prediction accuracy and lacks real-time performance. Furthermore, it requires a large amount of data, resulting in high prediction complexity. Summary of the Invention

[0004] In view of this, embodiments of the present invention provide a data-driven method for predicting the icing quality of wind turbine blades that is real-time, highly accurate, and low-cost.

[0005] One aspect of this invention provides a data-driven method for predicting the icing quality of wind turbine blades, comprising:

[0006] Based on a preset value range, sampling data is acquired; wherein, the sampling data includes ambient wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, and blade pitch angle;

[0007] The sampled data were simulated using CFD simulation software to obtain the icing mass dataset under different parameter conditions.

[0008] The simulation results of ice accumulation mass are compared with the simulation results of laboratory environment to correct the simulation process.

[0009] Based on the corrected icing mass dataset, polynomial fitting was applied to each variable to obtain the order relationship between the variable and the icing mass.

[0010] Based on the order relationship, parameterless system identification is performed to obtain the functional relationship between each parameter and the icing mass;

[0011] The values ​​of the variables to be predicted are obtained by using actual environmental information, and the values ​​of the variables to be predicted are predicted according to the functional relationship to obtain the icing prediction results.

[0012] Optionally, acquiring sampling data based on a preset value range includes:

[0013] The sampling was performed using Latin hypercube sampling at wind speeds ranging from 0 m / s to 20 m / s, temperatures ranging from -15°C to 5°C, average effective diameters of supercooled water droplets ranging from 15 μm to 50 μm, and g / m³. 3 ~2g / m 3 Discrete sampling was performed on the air moisture content, the wind turbine blade speed from 5 rpm to 30 rpm, and the blade pitch angle from 0° to 5° to obtain sampling data.

[0014] Optionally, the step of simulating the sampled data using CFD simulation software to obtain icing mass datasets under different parameter conditions includes:

[0015] The Latin hypercube sampling data was imported into CFD software for batch processing and large-scale simulation, recording the icing mass corresponding to different wind speeds, temperatures, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, and blade pitch angle.

[0016] Optionally, comparing the icing mass dataset obtained from the simulation with the dataset of laboratory environment simulation results to correct the simulation process includes:

[0017] The icing mass is obtained by importing the wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, and pitch angle from the dataset obtained from the environmental simulation experiment into a functional relationship. This data is then compared with the simulation results obtained from the CFD simulation software to confirm whether it is within the error limit. If it is, the simulation result is considered to have a high degree of fit; otherwise, the cause of the error is analyzed, and the simulation process is corrected.

[0018] Optionally, the step of applying a polynomial fit to each variable based on the corrected icing mass dataset to obtain the order relationship between the variable and the icing mass includes:

[0019] Import the dataset into the data analysis software;

[0020] Determine the expression for a single variable while keeping the other variables fixed.

[0021] Based on the expression of a single variable, a polynomial fitting is applied to obtain the order relationship between the single variable and the ice accumulation mass.

[0022] The expression for the single variable is:

[0023] M = A k x n k +A k-1 x nk-1 +A k-2 x n k-2 +……+φ

[0024] Where M is the mass of the ice layer, x n For the value of each group of a single variable, A k A k-1 A k-2 ... represents the correlation coefficient, n represents the number of groups, and φ represents the sum of the unknown effects of the remaining fixed variables.

[0025] Optionally, the step of performing parameterless system identification based on the order relationship to obtain the functional relationship between each parameter and the icing mass includes:

[0026] Based on the known order, the coefficients obtained from each set of data are subjected to the least squares method to obtain the functional relationship between ambient wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, blade pitch angle and icing mass.

[0027] Another aspect of this invention provides a data-driven wind turbine blade icing quality prediction device, comprising:

[0028] The first module is used to acquire sampling data based on a preset value range; wherein, the sampling data includes ambient wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, and blade pitch angle.

[0029] The second module is used to simulate the sampled data using CFD simulation software to obtain the icing mass dataset corresponding to different parameter conditions.

[0030] The third module is used to compare the icing quality dataset obtained from the simulation with the dataset of the laboratory environment simulation results, and to correct the simulation process.

[0031] The fourth module is used to apply polynomial fitting to each variable based on the corrected icing mass dataset to obtain the order relationship between the variable and the icing mass.

[0032] The fifth module is used to identify the parameterless system based on the order relationship and obtain the functional relationship between each parameter and the icing mass.

[0033] The sixth module is used to obtain the value of the variable to be predicted through actual environmental information, predict the value of the variable to be predicted according to the functional relationship, and obtain the icing prediction result.

[0034] Another aspect of the present invention provides an electronic device, including a processor and a memory;

[0035] The memory is used to store programs;

[0036] The processor executes the program to implement the method described above.

[0037] Another aspect of this invention provides a computer-readable storage medium storing a program that is executed by a processor to implement the methods described above.

[0038] This invention also discloses a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium and execute the computer instructions, causing the computer device to perform the aforementioned method.

[0039] The embodiments of this invention acquire sampling data based on a preset value range; simulate the sampling data using CFD simulation software to obtain icing mass datasets corresponding to different parameter conditions; compare the icing mass datasets obtained from the simulation with the datasets of laboratory environmental simulation results to correct the simulation process; based on the corrected icing mass datasets, apply polynomial fitting to each variable to obtain the order relationship between the variable and icing mass; perform parameterless system identification based on the order relationship to obtain the functional relationship between each parameter and icing mass; obtain the value of the variable to be predicted through actual environmental information, and predict the value of the variable to be predicted based on the functional relationship to obtain the icing prediction result. This invention combines CFD simulation, is data-driven, obtains the functional relationship between environmental state and icing mass in advance through parameterless system identification, and completes icing mass prediction based on actual environmental information. This invention has the advantages of low cost, strong real-time performance, high accuracy, and small data processing volume during use. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0041] Figure 1 The overall process flowchart provided for embodiments of the present invention. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0043] To address the problems existing in the prior art, this invention is based on data-driven analysis. It uses CFD simulation combined with experimental correction to analyze the effects of environmental wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, and pitch angle on the icing quality of wind turbine blades. The invention also fits the functional relationship between these variables and icing quality, providing a low-cost method for predicting the icing quality of wind turbine blades.

[0044] Specifically, such as Figure 1 As shown, the prediction method of the present invention includes the following steps:

[0045] (1) Based on the preset range of parameters such as ambient wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, and blade pitch angle, a discrete sampling method is used to obtain sampling results with the required accuracy.

[0046] (2) Based on the obtained sampling results, simulation was performed in CFD simulation software to obtain the corresponding icing mass under different wind speeds, temperatures, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speeds, and blade pitch angles.

[0047] (3) Based on the icing mass dataset obtained from the simulation, compare it with the dataset of the laboratory environment simulation results to correct the simulation process.

[0048] (4) Based on the corrected data, while keeping the other variables fixed, apply polynomial fitting to each variable to obtain the order relationship between the variable and the icing mass.

[0049] (5) Based on the obtained data, perform parameterless system identification and analyze the functional relationships between ambient wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, blade pitch angle and icing mass.

[0050] (6) Based on actual environmental information, input the corresponding variable values ​​to predict the icing quality of wind turbine blades.

[0051] In step (1), a discrete sampling method is used to obtain sampling results with the required accuracy, including:

[0052] The sampling was performed using Latin hypercube sampling at wind speeds ranging from 0 m / s to 20 m / s, temperatures ranging from -15°C to 5°C, average effective diameters of supercooled water droplets ranging from 15 μm to 50 μm, and g / m³. 3 ~2g / m 3Discrete sampling was performed on the air moisture content, the wind turbine blade speed from 5 rpm to 30 rpm, and the blade pitch angle from 0° to 5°.

[0053] In step (2), a simulation is performed using CFD simulation software to obtain the icing mass corresponding to different wind speeds, temperatures, average effective diameters of supercooled water droplets, air moisture content, wind turbine blade speeds, and pitch angles, including:

[0054] The Latin hypercube sampling data was imported into Fluent software, and a UDF was written for batch data processing to perform large-scale simulations. The icing mass m corresponding to different wind speeds, temperatures, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speeds, and pitch angles was recorded. i .

[0055] In step (3), the simulation process is corrected by comparing the results of the laboratory environment simulation, including:

[0056] The icing mass is obtained by importing wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, and blade pitch angle from the dataset obtained from the environmental simulation experiment into a functional relationship. This result is then compared with the simulation results obtained from Fluent to confirm whether it is within the error limit. If it is, it proves that the simulation results have a high degree of fit and are practical. If not, the reasons are analyzed and the simulation process is corrected.

[0057] In step (4), a polynomial fitting is applied to each variable, including:

[0058] Import the dataset into the data analysis software. With the other variables fixed, assume M = A for each individual variable. k x n k +A k-1 x n k-1 +A k-2 x n k-2 +……+φ, where M is the mass of the icing layer, x n For the value of each group of a single variable, A k A k-1 A k-2 ... represents the unknown coefficient, n represents the number of groups, and φ represents the sum of the unknown effects of the remaining variables. Polynomial fitting is used to obtain the order relationship between this variable and the ice accumulation quality.

[0059] In step (5), parameterless system identification is performed, including:

[0060] Based on the known order, the coefficients obtained from each set of data are subjected to the least squares method to obtain the functional relationship between ambient wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, blade pitch angle and icing mass.

[0061] In step (6), the corresponding variable values ​​are input to predict the icing quality of the wind turbine blades, including:

[0062] Import the dataset into Matlab software, run the Matlab program to substitute the data into the function relationship to obtain the icing mass.

[0063] In summary, this invention combines CFD simulation with a data-driven approach, identifying the functional relationship between environmental conditions and icing quality beforehand through a parameterless system, and then using actual environmental information to predict icing quality. This invention offers advantages such as low cost, high real-time performance, high accuracy, and minimal data processing requirements.

[0064] In some alternative embodiments, the functions / operations mentioned in the block diagrams may not occur in the order shown in the operation diagrams. For example, depending on the functions / operations involved, two consecutively shown blocks may actually be executed substantially simultaneously, or the blocks may sometimes be executed in reverse order. Furthermore, the embodiments presented and described in the flowcharts of this invention are provided by way of example to provide a more comprehensive understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and sub-operations described as part of a larger operation are executed independently.

[0065] Furthermore, although the invention has been described in the context of functional modules, it should be understood that, unless otherwise stated, one or more of the described functions and / or features may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in a separate physical device or software module. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the invention. Rather, given the properties, functions, and internal relationships of the various functional modules in the apparatus disclosed herein, the actual implementation of the module will be understood within the scope of conventional skill of an engineer. Therefore, those skilled in the art can implement the invention as set forth in the claims using ordinary techniques without excessive experimentation. It is also understood that the specific concepts disclosed are merely illustrative and not intended to limit the scope of the invention, which is determined by the full scope of the appended claims and their equivalents.

[0066] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0067] 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.

[0068] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), 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). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, because 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 computer memory.

[0069] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in 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.

[0070] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. 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.

[0071] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

[0072] The above is a detailed description of the preferred embodiments of the present invention, but the present invention is not limited to the embodiments described. Those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present invention, and these equivalent modifications or substitutions are all included within the scope defined by the claims of this application.

Claims

1. A data-driven method for predicting the icing quality of wind turbine blades, characterized in that, include: Based on a preset value range, sampling data is acquired; wherein, the sampling data includes ambient wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, and blade pitch angle; The sampled data were simulated using CFD simulation software to obtain icing mass datasets under different parameter conditions, including: The Latin hypercube sampling data was imported into CFD software for batch processing and large-scale simulation to record the icing mass corresponding to different wind speeds, temperatures, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, and blade pitch angle. Import the Latin hypercube sampling data into Fluent software, write UDFs for batch data processing, perform large-scale simulations, and record the icing mass corresponding to different wind speeds, temperatures, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speeds, and pitch angles. The simulation-obtained icing mass dataset is compared with the dataset from laboratory environmental simulations to correct the simulation process, including: The wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, and pitch angle from the dataset obtained from the environmental simulation experiment are imported into a functional relationship to obtain the icing mass. The results are compared with the simulation results obtained from the CFD simulation software to confirm whether they are within the error limit. If they are, the simulation results are judged to have a high degree of fit. If not, the error analysis causes are generated and the simulation process is corrected. Based on the corrected icing mass dataset, polynomial fitting was applied to each variable to obtain the order relationship between the variable and the icing mass. Based on the aforementioned order relationship, parameterless system identification is performed to obtain the functional relationships between each parameter and the icing mass, including: Based on the known order, the coefficients obtained from each set of data are subjected to the least squares method to obtain the functional relationship between ambient wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, blade pitch angle and icing mass. The values ​​of the variables to be predicted are obtained through actual environmental information, and the values ​​of the variables to be predicted are predicted according to the functional relationship to obtain the icing prediction results, including: Based on the above functional relationship, a program is designed, the dataset is imported into the program, and the ice accretion quality is obtained using the previously constructed functional relationship; The step of applying a polynomial fit to each variable based on the corrected icing mass dataset to obtain the order relationship between the variable and the icing mass includes: Import the dataset into the data analysis software; Determine the expression for a single variable while keeping the other variables fixed. Based on the expression of a single variable, a polynomial fitting is applied to obtain the order relationship between the single variable and the ice accumulation mass. The expression for the single variable is: M=A k x n k +A k-1 x n k-1 +A k-2 x n k-2 +……+φ Where M is the mass of the ice layer, x n For the value of each group of a single variable, A k A k-1 A k-2 ... represents the correlation coefficient, n represents the number of groups, and φ represents the sum of the unknown effects of the remaining fixed variables.

2. The data-driven method for predicting the icing quality of wind turbine blades according to claim 1, characterized in that, The process of acquiring sampled data based on a preset value range includes: Discrete sampling data was obtained by using Latin hypercube sampling in the range of wind speed from 0 m / s to 20 m / s, temperature from -15℃ to 5℃, average effective diameter of supercooled water droplets from 15 μm to 50 μm, air moisture content from 0.1 g / m³ to 2 g / m³, wind turbine blade speed from 5 rpm to 30 rpm, and blade pitch angle from 0° to 5°.

3. A data-driven wind turbine blade icing quality prediction device, used to implement the method as described in any one of claims 1 to 2, characterized in that, include: The first module is used to acquire sampling data based on a preset value range; wherein, the sampling data includes ambient wind speed, temperature, average effective diameter of supercooled water droplets, air moisture content, wind turbine blade speed, and blade pitch angle. The second module is used to simulate the sampled data using CFD simulation software to obtain the icing mass dataset corresponding to different parameter conditions. The third module is used to compare the icing quality dataset obtained from the simulation with the dataset of the laboratory environment simulation results, and to correct the simulation process. The fourth module is used to apply polynomial fitting to each variable based on the corrected icing mass dataset to obtain the order relationship between the variable and the icing mass. The fifth module is used to identify the parameterless system based on the order relationship and obtain the functional relationship between each parameter and the icing mass. The sixth module is used to obtain the value of the variable to be predicted through actual environmental information, predict the value of the variable to be predicted according to the functional relationship, and obtain the icing prediction result.

4. An electronic device, characterized in that, Including the processor and memory; The memory is used to store programs; The processor executes the program to implement the method as described in any one of claims 1 to 2.

5. A computer-readable storage medium, characterized in that, The storage medium stores a program that is executed by a processor to implement the method as described in any one of claims 1 to 2.

6. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the method as described in any one of claims 1 to 2.

Images