A pitch angle control method and device, electronic equipment and wind turbine generator

Abstract

The application discloses a pitch angle control method and device, electronic equipment and wind turbine, wherein the pitch angle control method comprises: obtaining real-time operation data of a wind turbine, and obtaining azimuth information of a current maximum wind speed point according to the real-time operation data; obtaining a pitch angle adjustment signal and an azimuth angle signal of a blade i; obtaining a pitch angle adjustment signal of the blade i according to the pitch angle adjustment signal, the azimuth angle signal of the blade i and the azimuth information of the current maximum wind speed point; obtaining a unified pitch adjustment signal; and obtaining a pitch angle control signal of the blade i according to the unified pitch adjustment signal and the pitch angle adjustment signal of the blade i. Thus, a pitch angle actuator can control each blade to perform a pitch action according to the pitch angle control signal of each blade, so that the influence of nP aerodynamic torque on output power and fatigue load of the wind turbine is reduced while the vibration of 1P aerodynamic load of the impeller is suppressed, and the output power quality of the wind turbine is improved.

Description

Technical Field

[0001] This invention relates to the field of wind power generation control technology, specifically to a pitch angle control method, device, electronic equipment, and wind turbine. Background Technology

[0002] Wind energy, as a green and renewable energy source, is cleaner and pollution-free than traditional fossil fuels, leading to its increasingly widespread use. However, unlike conventional power generation, wind turbines are constantly subjected to significant disturbances due to the randomness and volatility of wind, resulting in power fluctuations that pose a significant challenge to the stability and economic operation of the power system. Therefore, understanding the patterns of wind speed variation and its impact on power fluctuation characteristics is crucial for the safe, economical, and stable operation of the power system.

[0003] As the single-unit capacity and rotor diameter of wind turbines continue to increase, the impact of wind shear and tower shadow effects on wind turbines is becoming increasingly severe. The direct impact is that uneven stress on the blades leads to increased blade root load. Independent pitch control technology can control the pitch angle according to the position of each blade and the wind speed it experiences. This not only ensures stable power output and reduces the overspeed failure rate of the unit, but also effectively reduces the load on the blade root and hub, thereby reducing the overall cost of the unit and improving the reliability and lifespan of the wind turbine.

[0004] Therefore, there is an urgent need for a blade pitch angle control method based on wind speed distribution information in the wind turbine plane to mitigate blade vibration caused by uneven wind speed and improve the impact of impeller rotation frequency doubling on unit load and output power. Summary of the Invention

[0005] In view of this, embodiments of the present invention provide a pitch angle control method, device, electronic device and wind turbine, to provide a pitch control strategy that can simultaneously suppress two types of vibrations: impeller rotation frequency 1P aerodynamic load vibration and impeller rotation frequency multiple nP aerodynamic torque vibration.

[0006] In a first aspect, embodiments of the present invention provide a pitch angle control method, comprising the following steps: acquiring real-time operating data of a wind turbine; obtaining azimuth information of the current maximum wind speed point based on the real-time operating data; acquiring a pitch angle adjustment signal and an azimuth angle signal of blade i; obtaining a pitch angle adjustment signal of blade i based on the pitch angle adjustment signal, the azimuth angle signal of blade i, and the azimuth information of the current maximum wind speed point; acquiring a unified pitch signal; and obtaining a pitch angle control signal of blade i based on the unified pitch signal and the pitch angle adjustment signal of blade i.

[0007] Specifically, obtaining the unified pitch signal includes: obtaining the generator speed and the speed reference value respectively; calculating the difference between the generator speed and the speed reference value; and obtaining the unified pitch signal based on the difference.

[0008] Specifically, obtaining the azimuth information of the current maximum wind speed point based on the real-time operating data includes: acquiring a training dataset, which includes multiple sets of training data, each set of training data including historical operating data of the wind turbine at the same time and the azimuth information of the historical maximum wind speed point; training the azimuth solving model using the training dataset by inputting the real-time operating data into the trained azimuth solving model to obtain the azimuth information of the current maximum wind speed point.

[0009] Specifically, training the orientation solution model using the training dataset includes: acquiring historical environmental information for each set of training data; dividing the training dataset into multiple sub-training datasets with different environmental information ranges based on the historical environmental information of each set of training data; and training the orientation solution model using each sub-training dataset to obtain multiple trained orientation solution models.

[0010] Specifically, inputting the real-time operating data into a pre-trained azimuth solving model to obtain the azimuth information of the current maximum wind speed point includes: acquiring actual environmental information and determining the environmental information range to which the actual environmental information belongs; searching among multiple trained azimuth solving models for an azimuth solving model corresponding to the environmental information range to which the actual environmental information belongs; and inputting the real-time operating data into the found azimuth solving model to obtain the azimuth information of the current maximum wind speed point.

[0011] Specifically, obtaining the pitch angle adjustment signal includes: obtaining the generator power; inputting the generator power into a bandpass filter to obtain the nP component of the generator power; fine-tuning the nP component of the generator power to obtain the pitch angle adjustment signal; or, obtaining the pitch angle adjustment signal using blade root load.

[0012] Specifically, obtaining the pitch angle adjustment signal of blade i based on the pitch angle adjustment signal, the azimuth angle signal of blade i, and the azimuth information of the current maximum wind speed point includes: subtracting the azimuth information of the current maximum wind speed point from the azimuth angle signal of blade i to obtain the angle difference; calculating the trigonometric function value of the angle difference; and obtaining the pitch angle adjustment signal of blade i using the pitch angle adjustment signal and the trigonometric function value of the angle difference.

[0013] Specifically, obtaining the pitch angle control signal of blade i based on the unified pitch signal and the pitch angle adjustment signal of blade i includes: obtaining the pitch angle control signal of blade i by adding the pitch angle adjustment signal of blade i to the unified pitch signal.

[0014] Secondly, embodiments of the present invention also provide a pitch angle control device, including an azimuth solving module, a pitch angle fine-tuning increment module, an azimuth adjustment module, a unified pitch signal determination module, and a pitch angle control signal determination module; the azimuth solving module is used to acquire real-time operating data and obtain the azimuth information of the current maximum wind speed point based on the real-time operating data; the pitch angle fine-tuning increment module is used to acquire a pitch angle adjustment signal; the azimuth adjustment module is used to acquire the azimuth signal of blade i and obtain the pitch angle adjustment signal of blade i based on the pitch angle adjustment signal, the azimuth signal of blade i, and the azimuth information of the current maximum wind speed point; the unified pitch signal determination module is used to acquire a unified pitch signal; and the pitch angle control signal determination module is used to obtain the pitch angle control signal of blade i based on the unified pitch signal and the pitch angle adjustment signal of blade i.

[0015] Thirdly, embodiments of the present invention also provide an electronic device, including a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform the pitch angle control method described in the first aspect or any embodiment of the first aspect.

[0016] Fourthly, embodiments of the present invention also provide a wind turbine generator, including the electronic equipment described in the third aspect.

[0017] The pitch angle control method, device, electronic equipment, and wind turbine provided in this invention adopt the following technical solution: acquiring real-time operating data of the wind turbine, and obtaining the azimuth information of the current maximum wind speed point based on the real-time operating data; acquiring the pitch angle adjustment signal and the azimuth angle signal of blade i; obtaining the pitch angle adjustment signal of blade i based on the pitch angle adjustment signal, the azimuth angle signal of blade i, and the azimuth information of the current maximum wind speed point; acquiring a unified pitch signal; and obtaining the pitch angle control signal of blade i based on the unified pitch signal and the pitch angle adjustment signal of blade i. Therefore, the pitch angle actuator can control each blade to perform pitch adjustment actions according to the pitch angle control signal of each blade, thereby suppressing the aerodynamic load vibration of the impeller rotation frequency 1P while reducing the impact of the aerodynamic torque of the impeller rotation frequency multiple nP on the output power and the fatigue load of the unit, thus improving the output power quality of the wind turbine. Attached Figure Description

[0018] The features and advantages of the invention will be more clearly understood by referring to the accompanying drawings, which are schematic and should not be construed as limiting the invention in any way. In the drawings:

[0019] Figure 1 This is a flowchart illustrating the pitch angle control method in an embodiment of the present invention.

[0020] Figure 2 This is a schematic diagram of the training process of a 5-layer deep neural network;

[0021] Figure 3 This is a flowchart illustrating an example of a pitch angle control method.

[0022] Figure 4 This is a schematic diagram of the pitch angle control device in an embodiment of the present invention;

[0023] Figure 5 This is a schematic diagram of the structure of an electronic device in an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions, and although a logical order is shown in the flowchart, in some cases the steps shown or described may be executed in a different order than that shown here.

[0026] This invention provides a method for controlling propeller pitch angle. Figure 1 This is a flowchart illustrating the pitch angle control method in an embodiment of the present invention. Figure 1 As shown, the pitch angle control method of this invention includes the following steps:

[0027] S101: Obtain real-time operating data of the wind turbine.

[0028] Specifically, real-time operating data refers to the operating data of wind turbines above the rated wind speed, including wind speed, wind direction, generator speed, generator output power, and wind turbine position.

[0029] S102: Obtain the azimuth information of the current maximum wind speed point based on the real-time operating data.

[0030] Specifically, the real-time operating data can be input into a pre-trained azimuth solving model to obtain the azimuth information of the current maximum wind speed point.

[0031] Before inputting the real-time operating data into the pre-trained azimuth calculation model, the process further includes: acquiring a training dataset, which includes multiple sets of training data, each set including historical operating data of the wind turbines at the same time and azimuth information of the historical maximum wind speed point; and training the azimuth calculation model using the training dataset. The historical operating data of the wind turbines refers to the operating data of wind turbines at wind speeds above the rated wind speed before the current time, including wind speed, wind direction, generator speed, generator output power, and rotor position.

[0032] The location information of the historical maximum wind speed point can be obtained by analyzing the wind speed distribution data of the wind turbine plane. The wind speed distribution data of the wind turbine plane can be obtained using a vertical Doppler lidar or other wind measurement equipment; in addition, it can also be obtained by performing signal processing, wavelet analysis, spectrum analysis and other methods on the historical operating data of the wind turbine.

[0033] Specifically, historical operational data is used as input, and the azimuth information of the historical maximum wind speed point is used as output to train the azimuth solution model.

[0034] Specifically, the orientation solution model can be a deep neural network (DNN) model. This neural network model can be a long short-term memory neural network, a radial basis function neural network, or a generalized regression neural network, among other neural network models.

[0035] like Figure 2 As shown below, the training process of a deep neural network model will be explained using a 5-layer deep neural network as an example:

[0036] Based on the position of different layers, the neural network layers inside a deep neural network model (DNN) can be divided into: input layer, hidden layer, and output layer. Generally, the first layer is the input layer, the last layer is the output layer, and the layers in between are hidden layers.

[0037] The first layer, the hidden layer, has neurons that output... Where d is the number of neurons in the input layer, and H is the number of neurons in the first hidden layer. These are the weight coefficients from the i-th neuron in the input layer to the h-th neuron in the first hidden layer. σ is the threshold of the h-th neuron in the first hidden layer. To prevent gradient vanishing, the activation function σ is the PReLU function.

[0038] The second layer, the hidden layer, has neurons that output... Where q is the number of neurons in the second hidden layer.

[0039] The third layer, the hidden layer, has neurons that output... Where n is the number of neurons in the third hidden layer.

[0040] Output layer, neuron output is

[0041] As mentioned above, the neuron output formula can be generalized to:

[0042] Assuming there are m neurons in the (l-1)th layer, then the output of the h-th neuron in the l-th layer is... The specific expression is as follows

[0043] Therefore, forward propagation is used to compute the output of the training samples, and a loss function is used to measure the loss between the computed output of the training samples and the true training sample labels. Generally, the mean squared error of the network output is used as the loss function for backpropagation, expressed as: Where m is the number of samples used in one training session. Let y be the expected value of the output layer of the neural network. k This is the actual output value.

[0044] By iteratively optimizing the loss function using gradient descent to find its minimum value, suitable weight coefficients and thresholds for the hidden and output layers are found, ensuring that the output calculated from all training sample inputs is as equal to or as close as possible to the sample labels.

[0045] The weights and thresholds of the output and hidden layers are in the form of Where η is the learning rate, g k This represents the gradient term of the output layer neurons.

[0046] Using backpropagation of errors to update the weight coefficients and thresholds between neurons in each layer, the update form of the weight coefficients and thresholds between the input layer and the hidden layer is as follows: in This is the gradient term of the h-th neuron in the first hidden layer.

[0047] Meanwhile, to prevent overfitting during training, the Dropout method is used to randomly ignore the weight coefficients of certain hidden layer neurons with a certain probability.

[0048] Furthermore, to avoid the inconvenience and potential errors of manually selecting the number of hidden layers N, the number of neurons M in each hidden layer, and the learning rate η, this invention employs an intelligent optimization algorithm to optimize the aforementioned model parameters, while minimizing the training error as the optimization objective. Where N is the number of iterations in each training session of the neural network. y is the expected output value. i This is the actual output value.

[0049] It should be noted that, in order to improve modeling quality and eliminate the influence of missing, duplicate, and outlier values, the training data in the training dataset can be preprocessed before training the orientation solution model using the training dataset. To eliminate the influence of different units on the model training results, the preprocessed training data can be normalized.

[0050] Considering the significant differences in the magnitude of random wind speed variations under different wind conditions, which can affect the accuracy of the orientation calculation model in determining the location of the maximum wind speed, the training dataset can be divided into different intervals based on environmental information. It should be noted that the training data can be divided into different intervals based on turbulence intensity, wind speed intervals, or sliding time windows.

[0051] In other words, training the orientation solution model using the training dataset includes: acquiring historical environmental information for each set of training data; dividing the training dataset into multiple sub-training datasets with different environmental information ranges based on the historical environmental information of each set of training data; and training the orientation solution model using each sub-training dataset to obtain multiple trained orientation solution models.

[0052] When multiple trained azimuth solving models are obtained through training, the real-time operating data can be input into the pre-trained azimuth solving models to obtain the azimuth information of the current maximum wind speed point. This can be achieved by: acquiring actual environmental information and determining the environmental information range to which the actual environmental information belongs; searching among the multiple trained azimuth solving models for the azimuth solving model corresponding to the environmental information range to which the actual environmental information belongs; and inputting the real-time operating data into the searched azimuth solving model to obtain the azimuth information of the current maximum wind speed point.

[0053] S103: Acquire the pitch angle adjustment signal and the azimuth angle signal of blade i.

[0054] Specifically, the pitch angle adjustment signal can be obtained using any existing technical solution. For example, the generator power can be obtained; the generator power can be input into a bandpass filter to obtain the nP component of the generator power; the nP component of the generator power can be fine-tuned to obtain the pitch angle adjustment signal; another example is that the pitch angle adjustment signal can be obtained using blade root load. Here, nP is the impeller rotation frequency multiplier; in addition, since n in nP is an integer, nP can also be called the impeller rotation integer frequency multiplier.

[0055] The azimuth angle signal of blade i can be obtained by measurement.

[0056] S104: The pitch angle adjustment signal of blade i is obtained based on the pitch angle adjustment signal, the azimuth angle signal of blade i, and the azimuth information of the current maximum wind speed point.

[0057] Specifically, the method for obtaining the pitch angle adjustment signal of blade i based on the pitch angle adjustment signal, the azimuth angle signal of blade i, and the azimuth information of the current maximum wind speed point can be as follows: subtract the azimuth information of the current maximum wind speed point from the azimuth angle signal of blade i to obtain the angle difference; calculate the trigonometric function value of the angle difference; and obtain the pitch angle adjustment signal of blade i using the pitch angle adjustment signal and the trigonometric function value of the angle difference.

[0058] S105: Obtain unified pitch signal.

[0059] Specifically, the unified pitch signal can be obtained by the following method: obtaining the generator speed and the speed reference value respectively; calculating the difference between the generator speed and the speed reference value; and obtaining the unified pitch signal based on the difference.

[0060] S106: The pitch angle control signal of blade i is obtained based on the unified pitch signal and the pitch angle adjustment signal of blade i.

[0061] Specifically, the method for obtaining the pitch angle control signal of blade i based on the unified pitch signal and the pitch angle adjustment signal of blade i can be as follows: the pitch angle control signal of blade i is obtained by adding the unified pitch signal to the pitch angle adjustment signal of blade i.

[0062] The pitch angle adjustment method of this invention can obtain the pitch angle control signal for each blade. Thus, the pitch angle actuator can control each blade to perform pitch adjustment action according to the pitch angle control signal of each blade, thereby suppressing the aerodynamic load vibration of the impeller rotation frequency 1P while reducing the impact of the aerodynamic torque of the impeller rotation frequency multiple nP on the output power and the fatigue load of the unit.

[0063] To illustrate the pitch angle adjustment method of this invention in detail, a specific example is given. For example... Figure 3 As shown, the pitch angle adjustment method includes the following steps:

[0064] Step 1: Utilize the speed deviation e between the generator speed and the rated speed reference value. ω(t) Through PID controller and speed limiting processing, a unified pitch signal β0 is output; at the same time, the impeller rotation frequency multiplier nP component of the power is obtained by using a bandpass filter, and the pitch angle adjustment signal Δβ is obtained by the pitch angle fine-tuning increment module.

[0065] Step 2: After appropriately processing the real-time operating data such as power, wind speed, wind direction, generator speed, and wind turbine position, the data is input into the pre-trained azimuth calculation module. Based on the current environmental information, the appropriate neural network model is selected to obtain the azimuth information θ of the current maximum wind speed point. * Simultaneously, the pitch angle adjustment signal Δβ is transmitted via the azimuth angle adjustment module using the blade azimuth angle signal θ. i and the azimuth information of the maximum wind speed point θ * Converted into blade i pitch angle adjustment signal Δβ i The specific expression is Δβ i =Δβcos(θ) i -θ * );

[0066] Step 3: Based on the unified pitch signal β0, superimpose the signal Δβ. i The actual pitch angle command signal β of blade i is obtained. i The specific expression is β i =β0+Δβ i Simultaneously, the independent pitch signal β i The pitch actuator enables independent pitch control of the unit.

[0067] In summary, this invention provides a pitch control method based on azimuth identification. Based on the azimuth information of the maximum wind speed point on the rotor plane, and on the basis of a unified pitch signal, the pitch angle commands of the three blades are independently fine-tuned. This achieves the goal of suppressing the aerodynamic load vibration of the rotor rotation frequency 1P while reducing the impact of the aerodynamic torque of the rotor rotation frequency multiple nP on the output power and the fatigue load of the unit.

[0068] First, the current operating data of the wind turbine and environmental information data at wind speeds above the rated speed are acquired. This data is then input into the azimuth calculation module, which outputs the predicted azimuth information of the maximum wind speed point on the rotor plane. The azimuth calculation module is trained based on samples of operating data, environmental information, and the azimuth information of the maximum wind speed point on the rotor plane. Based on the unified pitch signal obtained from the PID control of the rotational speed deviation, a micro-adjustment signal for the pitch angle is obtained using the nP component of the rotor rotational frequency multiplier. This signal is then converted into an actual pitch angle adjustment signal for each blade by the azimuth angle adjustment module. The pitch angle actuator performs independent pitch control, thereby improving the aerodynamic characteristics of the blades, mitigating blade vibration caused by uneven wind speeds, and mitigating the impact of the rotor rotational frequency multiplier on aerodynamic torque and output power. This helps improve the quality of the unit's output power and reduce the fatigue load on the unit.

[0069] Corresponding to the above-described pitch angle adjustment method, this embodiment of the invention also provides a pitch angle adjustment device. For example... Figure 4 As shown, the pitch angle adjustment device includes an azimuth solution module 10, a pitch angle fine-tuning increment module 20, an azimuth angle adjustment module 30, a unified pitch signal determination module 40, and a pitch angle control signal determination module 50.

[0070] The azimuth calculation module 10 is used to acquire real-time operating data and obtain the unified pitch signal based on the difference.

[0071] The pitch angle fine-tuning increment module 20 is used to acquire the pitch angle adjustment signal;

[0072] The azimuth angle adjustment module 30 is used to acquire the azimuth angle signal of blade i, and to obtain the blade pitch angle adjustment signal of blade i based on the pitch angle adjustment signal, the azimuth angle signal of blade i, and the azimuth information of the current maximum wind speed point.

[0073] The unified pitch signal determination module 40 is used to acquire the unified pitch signal;

[0074] The pitch angle control signal determination module 50 is used to obtain the pitch angle control signal of blade i based on the unified pitch signal and the pitch angle adjustment signal of blade i.

[0075] The pitch angle adjustment device also includes an azimuth solution model training module 60. The azimuth solution model training module 60 is used to: acquire a training dataset, which includes multiple sets of training data, each set of training data including historical wind turbine operating data and azimuth information of the historical maximum wind speed point at the same time; and train the azimuth solution model using the training dataset.

[0076] The orientation solution model training module 60 is specifically used for: acquiring historical environmental information of each set of training data; dividing the training dataset into multiple sub-training datasets with different environmental information ranges based on the historical environmental information of each set of training data; and training the orientation solution model using each sub-training dataset to obtain multiple trained orientation solution models.

[0077] The unified pitch signal determination module 40 is specifically used for: acquiring the generator speed and the speed reference value respectively; calculating the difference between the generator speed and the speed reference value; and performing PID control and amplitude limiting / speed limiting processing on the difference to obtain the unified pitch signal.

[0078] The orientation solution module 10 is specifically used for: acquiring actual environmental information and determining the environmental information range to which the actual environmental information belongs; searching for an orientation solution model corresponding to the environmental information range to which the actual environmental information belongs among multiple trained orientation solution models; and inputting the real-time running data into the found orientation solution model to obtain the orientation information of the current maximum wind speed point.

[0079] The pitch angle fine-tuning increment module 20 is specifically used for: obtaining generator power; inputting the generator power into a bandpass filter to obtain the nP component of the generator power; fine-tuning the nP component of the generator power to obtain the pitch angle adjustment signal; or, obtaining the pitch angle adjustment signal using blade root load.

[0080] The azimuth angle adjustment module 30 is specifically used to: obtain the angle difference by subtracting the azimuth information of the current maximum wind speed point from the azimuth angle signal of the blade i; calculate the trigonometric function value of the angle difference; and obtain the pitch angle adjustment signal of the blade i by using the pitch angle adjustment signal and the trigonometric function value of the angle difference.

[0081] The pitch angle control signal determination module 50 is specifically used to: obtain the pitch angle control signal of blade i by adding the unified pitch signal to the pitch angle adjustment signal of blade i.

[0082] For specific details regarding the aforementioned pitch angle adjustment device, please refer to the relevant documentation. Figures 1 to 3 The relevant descriptions and effects in the illustrated embodiments are for understanding purposes only and will not be repeated here.

[0083] Based on the above-described pitch angle control method, this invention also provides an electronic device, such as... Figure 5 The electronic device may include a processor 51 and a memory 52, wherein the processor 51 and the memory 52 may be connected by a bus or other means.

[0084] Furthermore, embodiments of the present invention also provide a wind turbine generator, including the aforementioned electronic equipment.

[0085] Specifically, the processor 51 can be a central processing unit (CPU). The processor 51 can also be other general-purpose processors 51, digital signal processors 51 (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above types of chips.

[0086] Memory 52, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs, non-transitory computer-executable programs, and modules, such as the program instructions / modules corresponding to the pitch angle control method in this embodiment of the invention (e.g., Figure 4 The diagram shows the azimuth solving module 10, the pitch angle fine-tuning increment module 20, the azimuth angle adjustment module 30, the unified pitch signal determination module 40, the pitch angle control signal determination module 50, and the azimuth solving model training module 60. The processor 51 executes various functional applications and data processing by running non-transient software programs, instructions, and modules stored in the memory 52, thereby implementing the pitch angle control method in the above method embodiment.

[0087] The memory 52 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created by the processor 51, etc. Furthermore, the memory 52 may include high-speed random access memory 52, and may also include non-transitory memory 52, such as at least one disk storage device 52, a flash memory device, or other non-transitory solid-state memory 52. ​​In some embodiments, the memory 52 may optionally include remotely located memories 52 relative to the processor 51, which can be connected to the processor 51 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0088] The one or more modules are stored in the memory 52, and when executed by the processor 51, they perform the following: Figures 1 to 3 The pitch angle control method in the illustrated embodiment.

[0089] For specific details regarding the aforementioned electronic devices, please refer to the relevant documentation. Figures 1 to 4 The relevant descriptions and effects in the illustrated embodiments are for understanding purposes only and will not be repeated here.

[0090] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0091] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for controlling propeller pitch angle, characterized in that, include: Obtain real-time operating data of the wind turbine; The location information of the current maximum wind speed point is obtained based on the real-time operating data. Acquire pitch angle adjustment signal and blade i azimuth signal; According to the pitch angle adjustment signal, the blade i The blade is obtained from the azimuth signal and the azimuth information of the current maximum wind speed point. i The pitch angle adjustment signal; Obtain a unified pitch signal; Based on the unified pitch signal and the blade i The blade is obtained from the pitch angle adjustment signal. i The pitch angle control signal; The acquisition of the pitch angle adjustment signal includes: Obtain generator power; The generator power is input into a bandpass filter to obtain the nP component of the generator power; where nP is an integer multiple of the impeller rotation frequency. The pitch angle adjustment signal is obtained by fine-tuning the nP component of the generator power. The blades are adjusted according to the pitch angle signal. i The blade is obtained from the azimuth angle signal and the azimuth information of the current maximum wind speed point. i The pitch angle adjustment signals include: Using the blade i The angle difference is obtained by subtracting the azimuth information of the current maximum wind speed point from the azimuth signal; Calculate the trigonometric function value of the angle difference; The blade is obtained using the trigonometric function value of the pitch angle adjustment signal and the angle difference. i The pitch angle adjustment signal; The method based on the unified pitch signal and the blade i The blade is obtained from the pitch angle adjustment signal. i The pitch angle control signals include: Using the unified pitch signal plus the blade i The blade is obtained from the pitch angle adjustment signal. i The pitch angle control signal; The specific expression is: ， in, This represents the pitch angle control signal for blade i. Indicates a unified pitch signal. This indicates the pitch angle adjustment signal for blade i. This indicates the pitch angle adjustment signal. This represents the azimuth angle signal of blade i. This indicates the location information of the point with the current maximum wind speed.

2. The method according to claim 1, characterized in that, The acquisition of the unified pitch signal includes: Obtain the generator speed and speed reference value respectively; Calculate the difference between the generator speed and the speed reference value; The unified pitch signal is obtained based on the difference.

3. The method according to claim 1, characterized in that, The step of obtaining the azimuth information of the current maximum wind speed point based on the real-time operating data includes: Obtain a training dataset, which includes multiple sets of training data. Each set of training data includes historical operating data of wind turbines at the same time and directional information of the historical maximum wind speed point. The orientation solution model is trained using the aforementioned training dataset; The real-time operating data is input into the trained azimuth solving model to obtain the azimuth information of the current maximum wind speed point.

4. The method according to claim 3, characterized in that, The step of training the orientation solution model using the training dataset includes: Obtain historical environment information for each set of training data; Based on the historical environmental information of each group of training data, the training dataset is divided into multiple sub-training datasets with different environmental information ranges. The orientation solution model is trained using each sub-training dataset to obtain multiple trained orientation solution models.

5. The method according to claim 4, characterized in that, The real-time operating data is input into a pre-trained azimuth calculation model to obtain the azimuth information of the current maximum wind speed point, including: Obtain actual environmental information and determine the environmental information range to which the actual environmental information belongs; Search among multiple trained orientation solution models for an orientation solution model that corresponds to the environmental information range to which the actual environmental information belongs. The real-time operating data is input into the found azimuth solution model to obtain the azimuth information of the current maximum wind speed point.

6. A pitch angle control device, characterized in that, include: The azimuth calculation module is used to acquire real-time operating data and obtain the azimuth information of the current maximum wind speed point based on the real-time operating data; The pitch angle fine-tuning increment module is used to acquire the pitch angle adjustment signal; An azimuth angle adjustment module is used to acquire the azimuth angle signal of blade i, and to obtain the blade pitch angle adjustment signal of blade i based on the pitch angle adjustment signal, the azimuth angle signal of blade i, and the azimuth information of the current maximum wind speed point. A unified pitch signal determination module is used to acquire the unified pitch signal; The pitch angle control signal determination module is used to obtain the pitch angle control signal of blade i based on the unified pitch signal and the pitch angle adjustment signal of blade i. The pitch angle fine-tuning increment module is specifically used for: acquiring generator power; inputting the generator power into a bandpass filter to obtain the nP component of the generator power; where nP is an integer multiple of the impeller rotation frequency; and fine-tuning the nP component of the generator power to obtain the pitch angle adjustment signal. The azimuth adjustment module is specifically used for: utilizing the blade i The azimuth angle signal is subtracted from the azimuth information of the current maximum wind speed point to obtain the angle difference; the trigonometric function value of the angle difference is calculated; the blade is obtained using the pitch angle adjustment signal and the trigonometric function value of the angle difference. i The pitch angle adjustment signal; The pitch angle control signal determination module is specifically used to: utilize the unified pitch signal plus the blade... i The blade is obtained from the pitch angle adjustment signal. i The pitch angle control signal; The specific expression is: ， in, This represents the pitch angle control signal for blade i. Indicates a unified pitch signal. This indicates the pitch angle adjustment signal for blade i. This indicates the pitch angle adjustment signal. This represents the azimuth angle signal of blade i. This indicates the location information of the point with the current maximum wind speed.

7. An electronic device, characterized in that, include: A memory and a processor are interconnected, the memory stores computer instructions, and the processor executes the pitch angle control method of any one of claims 1 to 5 by executing the computer instructions.

8. A wind turbine generator set, characterized in that, Includes the electronic device as described in claim 7.

Images