Wind turbine blade pitch adjustment method and device based on wind direction turbulence intensity

Abstract

The present invention discloses a method and device for adjusting the blade pitch of a wind turbine set based on the wind direction turbulence intensity, belonging to the technical field of wind power generation. The method calculates the wind direction turbulence intensity according to the historical wind speed and the historical wind direction; uses the optimal pitch angle calculation model to calculate the pitch angle of the optimal output power under the current wind field conditions according to the unit operation data of the wind turbine set and the wind direction turbulence intensity; predicts the dynamic blade pitch angle of the wind turbine set in a specified period according to the change of wind field conditions through the pitch angle prediction model; sends a blade pitch angle adjustment instruction to the wind turbine set according to the predicted dynamic blade pitch angle of the wind turbine set, and verifies and corrects the prediction result of the blade pitch angle through a feedback mechanism, so as to achieve the optimization of the power output of the wind turbine set. The present invention takes into account the influence of wind direction turbulence on the dynamic load of the wind turbine, has strong adaptability, realizes the optimal control under different wind conditions, and can flexibly cope with complex wind condition changes.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind power generation, and in particular relates to a method and device for adjusting the pitch of wind turbine blades based on wind direction turbulence intensity. Background Art

[0002] At present, in the process of wind power generation, the pitch angle adjustment of wind turbine blades is one of the key factors affecting power generation efficiency and equipment life.

[0003] At present, wind turbine control systems usually only focus on wind speed and average wind direction, but lack consideration of the dynamic fluctuations in wind direction, namely the wind turbulence intensity. Wind turbulence is particularly significant when the wind speed is high. This turbulence effect directly affects the aerodynamic characteristics of the blades, causing a sharp change in the force on the blades and increasing fatigue loss of the blades and the main shaft. The existing technology does not fully consider the volatility caused by the wind turbulence intensity, making it impossible for the blade pitch angle to adapt to complex wind direction changes, resulting in unstable output power and increased equipment wear.

[0004] In addition, the current wind turbine pitch systems usually rely on simple real-time wind speed and wind direction data to adjust the blade angle, which makes it difficult to effectively predict drastic changes in wind conditions. Traditional control systems react slowly to sudden turbulence, especially in wind conditions with high turbulence intensity. They cannot predict rapid changes in wind direction in advance, resulting in the control system being unable to adjust the pitch angle in time, and it is difficult to achieve optimal power output. Pitch angle adjustment in the prior art is often based on preset parameters, lacks adaptability, and cannot be intelligently adjusted according to actual wind conditions, making it difficult to achieve optimal control under different wind conditions. This non-intelligent control mode results in excessive equipment load or low power output efficiency, and cannot flexibly respond to complex changes in wind conditions. Summary of the invention

[0005] To this end, the present invention provides a method and device for adjusting the pitch of wind turbine blades based on wind direction turbulence intensity, which solves the problems that the prior art fails to consider the impact of wind direction turbulence on the dynamic load of the wind turbine, lacks adaptability, cannot be intelligently adjusted according to actual wind conditions, is difficult to achieve optimal control under different wind conditions, and cannot flexibly respond to complex wind condition changes.

[0006] In order to achieve the above object, the present invention provides the following technical solution: a method for adjusting the pitch of wind turbine blades based on wind direction turbulence intensity, comprising:

[0007] S1. Obtain designated historical data of the wind farm where the wind turbine is located, wherein the designated historical data includes historical wind speed and historical wind direction; and calculate the wind direction turbulence intensity according to the historical wind speed and the historical wind direction;

[0008] S2. constructing an optimal pitch angle calculation model, wherein the optimal pitch angle calculation model calculates the pitch angle of the optimal output power under the current wind field conditions according to the unit operation data of the wind turbine unit and the wind direction turbulence intensity;

[0009] S3, constructing a pitch angle prediction model, and using the pitch angle prediction model to predict the pitch angle of the dynamic blades of the wind turbine in a specified period according to changes in wind field conditions, so as to respond to the impending turbulent fluctuations and adjust the pitch angle of the wind turbine to the optimal value in real time;

[0010] S4. Send a blade pitch angle adjustment instruction to the wind turbine according to the predicted dynamic blade pitch angle of the wind turbine, and verify and correct the predicted result of the blade pitch angle through a feedback mechanism to optimize the power output of the wind turbine.

[0011] As a preferred solution of the wind turbine blade pitch adjustment method based on wind direction turbulence intensity, the formula for calculating the wind direction turbulence intensity according to the historical wind speed and the historical wind direction is:

[0012] ;

[0013] In the formula, It indicates the wind turbulence intensity, which is a quantitative representation of wind direction fluctuations; represents the number of samples; Indicates The change in wind direction per time step; Indicates The change in wind direction per time step; Indicates The change in wind direction per time step; Indicates instantaneous wind speed; Represents the average wind speed in historical data.

[0014] As a preferred solution of the wind turbine blade pitch adjustment method based on wind direction turbulence intensity, the expression formula of the optimal pitch angle calculation model is:

[0015] ;

[0016] In the formula, Indicates the optimal pitch angle; is the wind direction turbulence intensity influence coefficient; is the power influence coefficient; is the historical power generation data; Indicates the offset.

[0017] As a preferred solution of the wind turbine blade pitch adjustment method based on wind direction turbulence intensity, the pitch angle prediction model is expressed as:

[0018] ;

[0019] In the formula, Indicates the future The predicted pitch angle possible at any moment; Represents the wind direction turbulence change rate coefficient, which is used to enhance the sensitivity of pitch response; Indicates the instantaneous change in turbulence intensity; Represents the average value of turbulence intensity.

[0020] As a preferred solution of the wind turbine blade pitch adjustment method based on wind direction turbulence intensity, it also includes training the characteristics of the pitch angle prediction model in combination with a multi-layer neural network model. The structure of the trained pitch angle prediction model is:

[0021] ;

[0022] In the formula, Responsible for inputting features, Including wind direction turbulence intensity, wind speed change rate, and power generation fluctuation amplitude in historical data to form a feature vector set; Use activation function (ReLU) for nonlinear transformation; is the optimal pitch angle for the final output.

[0023] As a preferred solution for the wind turbine blade pitch adjustment method based on wind direction turbulence intensity, the predicted results of blade pitch angle are verified and corrected through a feedback mechanism, including:

[0024] The output power of the wind turbine is monitored in real time and compared with the theoretical optimal value. If the deviation exceeds the set threshold, the coefficient of the optimal pitch angle calculation model is adjusted. , , Parameters are modified;

[0025] If the wind direction turbulence intensity fluctuation exceeds the threshold, the wind direction turbulence change rate coefficient, which is the sensitivity index of pitch adjustment, is increased. .

[0026] The present invention also provides a wind turbine blade pitch adjustment device based on wind direction turbulence intensity, comprising:

[0027] A wind direction turbulence intensity analysis module is used to obtain designated historical data of the wind farm where the wind turbine is located, wherein the designated historical data includes historical wind speed and historical wind direction; and calculate the wind direction turbulence intensity according to the historical wind speed and the historical wind direction;

[0028] A current pitch angle analysis module is used to construct an optimal pitch angle calculation model, wherein the optimal pitch angle calculation model calculates the pitch angle of the optimal output power under the current wind field conditions according to the unit operation data of the wind turbine unit and the wind direction turbulence intensity;

[0029] The pitch angle dynamic prediction module is used to construct a pitch angle prediction model, through which the pitch angle prediction model is used to predict the dynamic blade pitch angle of the wind turbine in a specified period according to the change of wind field conditions, so as to respond to the impending turbulent fluctuations and adjust the pitch angle of the wind turbine to the optimal value in real time;

[0030] The pitch angle instruction adjustment module is used to send a blade pitch angle adjustment instruction to the wind turbine according to the predicted dynamic blade pitch angle of the wind turbine, and verify and correct the predicted result of the blade pitch angle through a feedback mechanism to achieve the optimization of the power output of the wind turbine.

[0031] As a preferred solution of a wind turbine blade pitch adjustment device based on wind direction turbulence intensity, in the wind direction turbulence intensity analysis module, the formula for calculating the wind direction turbulence intensity according to the historical wind speed and the historical wind direction is:

[0032] ;

[0033] In the formula, It indicates the wind turbulence intensity, which is a quantitative representation of wind direction fluctuations; represents the number of samples; Indicates The change in wind direction per time step; Indicates The change in wind direction per time step; Indicates The change in wind direction per time step; Indicates instantaneous wind speed; Represents the average wind speed in historical data.

[0034] As a preferred solution of the wind turbine blade pitch adjustment device based on wind direction turbulence intensity, in the current pitch angle analysis module, the expression formula of the optimal pitch angle calculation model is:

[0035] ;

[0036] In the formula, Indicates the optimal pitch angle; is the wind direction turbulence intensity influence coefficient; is the power influence coefficient; is the historical power generation data; Indicates the offset.

[0037] As a preferred solution of the wind turbine blade pitch adjustment device based on wind direction turbulence intensity, in the pitch angle dynamic prediction module, the pitch angle prediction model is expressed as follows:

[0038] ;

[0039] In the formula, Indicates the future The predicted pitch angle possible at any moment; Represents the wind direction turbulence change rate coefficient, which is used to enhance the sensitivity of pitch response; Indicates the instantaneous change in turbulence intensity; represents the average value of turbulence intensity;

[0040] The pitch angle dynamic prediction module is also used to train the characteristics of the pitch angle prediction model in combination with a multi-layer neural network model. The structure of the pitch angle prediction model after training is:

[0041] ;

[0042] In the formula, Responsible for inputting features, Including wind direction turbulence intensity, wind speed change rate, and power generation fluctuation amplitude in historical data to form a feature vector set; Use activation function (ReLU) for nonlinear transformation; is the optimal pitch angle for the final output.

[0043] As a preferred solution of the wind turbine blade pitch adjustment device based on wind direction turbulence intensity, in the pitch angle instruction adjustment module, the prediction result of the blade pitch angle is verified and corrected through a feedback mechanism, including:

[0044] The output power of the wind turbine is monitored in real time and compared with the theoretical optimal value. If the deviation exceeds the set threshold, the coefficient of the optimal pitch angle calculation model is adjusted. , , Parameters are modified;

[0045] If the wind direction turbulence intensity fluctuation exceeds the threshold, the wind direction turbulence change rate coefficient, which is the sensitivity index of pitch adjustment, is increased. .

[0046] The present invention has the following advantages:

[0047] The present invention introduces wind direction turbulence intensity as a control parameter for pitch angle adjustment to quantify the influence of wind direction volatility on pitch angle; by calculating wind direction turbulence intensity and combining it with the operation data of the wind turbine, it is possible to identify the impact of turbulence on blades and dynamically adjust the pitch angle to adapt to different turbulence conditions; it overcomes the problem that the prior art fails to consider the influence of wind direction turbulence on the dynamic load of the wind turbine, and enables the wind turbine to maintain a stable output power under high turbulence intensity;

[0048] The present invention can predict the optimal pitch angle under future wind conditions based on the laws of wind turbulence in historical data, and adjust it in advance; it overcomes the shortcomings of the prior art that only relies on real-time data and is difficult to respond to wind condition changes in real time, making pitch control more intelligent and forward-looking, and greatly improving the power output stability of wind turbines;

[0049] The present invention can correct the predicted value of the variable pitch angle through a feedback mechanism based on the real-time collection of wind speed and wind direction data, making the variable pitch angle more in line with the current wind conditions, significantly improving the system's adaptability and control accuracy, reducing equipment losses and improving power output efficiency, and solving the problem that the prior art is difficult to achieve optimal control under different wind conditions and cannot flexibly respond to complex wind condition changes. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0051] Figure 1 A schematic flow chart of a method for adjusting the pitch of wind turbine blades based on wind direction turbulence intensity provided in an embodiment of the present invention;

[0052] Figure 2 The predicted value of the pitch angle during the simulation verification process of the wind turbine blade pitch adjustment method based on wind direction turbulence intensity provided in the embodiment of the present invention;

[0053] Figure 3 The blade pitch angle comparison before and after optimization of the simulation verification process of the wind turbine blade pitch adjustment method based on wind direction turbulence intensity provided in an embodiment of the present invention;

[0054] Figure 4 Schematic diagram of the architecture of a wind turbine blade pitch adjustment device based on wind direction turbulence intensity provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Example 1

[0057] See also Figure 1 The embodiment of the present invention provides a method for adjusting the pitch of wind turbine blades based on wind direction turbulence intensity, comprising the following steps:

[0058] S1. Obtain designated historical data of the wind farm where the wind turbine is located, wherein the designated historical data includes historical wind speed and historical wind direction; and calculate the wind direction turbulence intensity according to the historical wind speed and the historical wind direction;

[0059] S2. constructing an optimal pitch angle calculation model, wherein the optimal pitch angle calculation model calculates the pitch angle of the optimal output power under the current wind field conditions according to the unit operation data of the wind turbine unit and the wind direction turbulence intensity;

[0060] S3, constructing a pitch angle prediction model, and using the pitch angle prediction model to predict the pitch angle of the dynamic blades of the wind turbine in a specified period according to changes in wind field conditions, so as to respond to the impending turbulent fluctuations and adjust the pitch angle of the wind turbine to the optimal value in real time;

[0061] S4. Send a blade pitch angle adjustment instruction to the wind turbine according to the predicted dynamic blade pitch angle of the wind turbine, and verify and correct the predicted result of the blade pitch angle through a feedback mechanism to optimize the power output of the wind turbine.

[0062] In this embodiment, in step S1, the historical data of the wind farm where the wind turbine is located is first analyzed, and the fluctuation of wind direction is extracted by processing the sampling data of historical wind speed and historical wind direction. The fluctuation of wind direction is characterized by the index of wind direction turbulence intensity. The formula for calculating wind direction turbulence intensity based on the historical wind speed and the historical wind direction is:

[0063] ;

[0064] In the formula, It indicates the wind turbulence intensity, which is a quantitative representation of wind direction fluctuations; represents the number of samples; Indicates The change in wind direction per time step; Indicates The change in wind direction per time step; Indicates The change in wind direction per time step; Indicates instantaneous wind speed; Represents the average wind speed in historical data.

[0065] Specifically, the wind turbulence intensity It expresses the rate of change of wind direction and the influence of wind speed. This formula is used to quantify the turbulence intensity of wind direction, amplify the turbulence effect through the quadratic term of wind direction change, and capture the influence of wind direction turbulence intensity under different wind speeds in combination with the weighted proportion of instantaneous wind speed, so as to provide a basis for subsequent pitch angle calculation.

[0066] In this embodiment, in step S2, an optimal pitch angle calculation model is constructed by comprehensively analyzing the historical power generation of the unit, the pitch angle and the wind speed to adapt to the conditions of different wind direction turbulence intensities. Specifically, the expression formula of the optimal pitch angle calculation model is:

[0067] ;

[0068] In the formula, Indicates the optimal pitch angle; is the wind direction turbulence intensity influence coefficient, which reflects the direct influence of wind direction turbulence intensity on the pitch angle; is the power influence coefficient, which reflects the correction effect of power generation on the pitch angle; It is the historical power generation data, which is used to reflect the impact of wind turbulence intensity on power output; Indicates the offset, which adjusts the pitch angle through environmental adaptability.

[0069] The optimal pitch angle calculation model calculates a pitch angle that can output the best power under the current wind field conditions by weighting the wind turbulence intensity and power output. , , Equal coefficients can adapt to the environmental characteristics of different wind farms and the power requirements of units. Provides feedback from turbulence on blade adjustment. The optimal combination of wind speed, turbulence intensity and power output is achieved based on the optimal pitch angle at the balance between wind speed and power generation.

[0070] In this embodiment, in step S3, in order to improve the real-time response capability of pitch adjustment, the pitch angle that may be implemented is predicted in combination with the wind direction and wind speed in the future, wherein the expression formula of the pitch angle prediction model is:

[0071] ;

[0072] In the formula, Indicates the future The predicted pitch angle possible at any moment; Represents the wind direction turbulence change rate coefficient, which is used to enhance the sensitivity of pitch response; Indicates the instantaneous change in turbulence intensity; Represents the average value of turbulence intensity.

[0073] The method further includes training the characteristics of the pitch angle prediction model in combination with a multi-layer neural network model. The structure of the pitch angle prediction model after training is:

[0074] ;

[0075] In the formula, Responsible for inputting features, Including wind direction turbulence intensity, wind speed change rate, and power generation fluctuation amplitude in historical data to form a feature vector set; Use activation function (ReLU) for nonlinear transformation; is the optimal pitch angle for the final output.

[0076] Specifically, the formula of the pitch angle prediction model provides dynamic pitch angle prediction according to the changes in wind field conditions, and combines a multi-layer neural network to train the model and optimize the predicted blade pitch angle. By monitoring the changes in wind turbulence intensity and feeding it back to real-time control, it is possible to respond to impending turbulence fluctuations in advance and adjust the wind turbine pitch angle to the optimal value in real time. The turbulence change ratio term in the formula Reflects the suddenness and amplitude of turbulence, and the adjustment factor This enables the system to respond quickly to fluctuations in wind conditions and optimizes the stability of output power.

[0077] In this embodiment, in step S4, based on the predicted pitch angle, the control system sends an adjustment instruction to the pitch controller of the wind turbine, and verifies and corrects the prediction result through a feedback mechanism to form a closed-loop control system to achieve optimization of power output.

[0078] Specifically, the prediction results of blade pitch angle are verified and corrected through the feedback mechanism, including:

[0079] The output power of the wind turbine is monitored in real time and compared with the theoretical optimal value. If the deviation exceeds the set threshold, the coefficient of the optimal pitch angle calculation model is adjusted. , , Parameters are modified;

[0080] If the wind direction turbulence intensity fluctuation exceeds the threshold, the wind direction turbulence change rate coefficient, which is the sensitivity index of pitch adjustment, is increased. .

[0081] See also Figure 2 , select 1 hour of historical data as the data set for training and prediction. Combine the multi-layer neural network model to train the features and predict the pitch angle in the future. At the same time, based on the wind direction turbulence emphasis, comprehensively analyze the historical pitch data and the predicted pitch data, and use this as a reference to optimize the pitch control parameters. The blade pitch position after the pitch control parameters are optimized is compared with the original strategy. The results are as follows Figure 3 It can be seen that the optimized pitch angle is relatively stable and the variation is small, which can effectively reduce the wear of the unit equipment and reduce the power consumption of pitch angle.

[0082] To summarize, the embodiments of the present invention obtain designated historical data of the wind farm where the wind turbine is located, wherein the designated historical data includes historical wind speed and historical wind direction; the wind direction turbulence intensity is calculated according to the historical wind speed and the historical wind direction; an optimal pitch angle calculation model is constructed, wherein the optimal pitch angle calculation model calculates the pitch angle of the optimal output power under the current wind farm conditions according to the unit operation data of the wind turbine and the wind direction turbulence intensity; a pitch angle prediction model is constructed, and the dynamic blade pitch angle of the wind turbine in a specified period of time is predicted according to the changes in wind farm conditions through the pitch angle prediction model, so as to respond to the impending turbulent fluctuations and adjust the pitch angle of the wind turbine to the optimal in real time; a blade pitch angle adjustment instruction is sent to the wind turbine according to the predicted dynamic blade pitch angle of the wind turbine, and the prediction result of the blade pitch angle is verified and corrected through a feedback mechanism, so as to achieve the optimization of the power output of the wind turbine. The present invention introduces wind direction turbulence intensity as a control parameter for pitch angle adjustment to quantify the influence of wind direction volatility on pitch angle; by calculating wind direction turbulence intensity and combining with the operation data of wind turbine, the impact of turbulence on blades can be identified, and the pitch angle can be dynamically adjusted to adapt to different turbulence conditions; the problem that the prior art fails to consider the influence of wind direction turbulence on the dynamic load of the wind turbine is overcome, so that the wind turbine maintains a stable output power under high turbulence intensity; the present invention can predict the optimal pitch angle under future wind conditions according to the law of wind direction turbulence in historical data, and adjust it in advance; the shortcomings of the prior art that only relies on real-time data and is difficult to respond to wind condition changes in real time are overcome, so that pitch control is more intelligent and forward-looking, and the power output stability of the wind turbine is greatly improved; the present invention can correct the predicted value of the pitch angle through a feedback mechanism based on the real-time collection of wind speed and wind direction data; the pitch angle is more in line with the current wind condition requirements, significantly improving the adaptability and control accuracy of the system, reducing equipment loss and improving the efficiency of power output, and solving the problem that the prior art is difficult to achieve optimal control under different wind conditions and cannot flexibly respond to complex wind condition changes.

[0083] Example 2

[0084] See also Figure 4 Embodiment 2 of the present invention further provides a wind turbine blade pitch adjustment device based on wind direction turbulence intensity, comprising:

[0085] The wind direction turbulence intensity analysis module 100 is used to obtain the specified historical data of the wind farm where the wind turbine is located, wherein the specified historical data includes the historical wind speed and the historical wind direction; and calculate the wind direction turbulence intensity according to the historical wind speed and the historical wind direction;

[0086] The current pitch angle analysis module 200 is used to construct an optimal pitch angle calculation model, wherein the optimal pitch angle calculation model calculates the pitch angle of the optimal output power under the current wind field conditions according to the unit operation data of the wind turbine unit and the wind direction turbulence intensity;

[0087] The pitch angle dynamic prediction module 300 is used to construct a pitch angle prediction model, through which the pitch angle prediction model is used to predict the dynamic blade pitch angle of the wind turbine in a specified period according to the change of wind field conditions, so as to respond to the upcoming turbulent fluctuations and adjust the pitch angle of the wind turbine to the optimal value in real time;

[0088] The pitch angle instruction adjustment module 400 is used to send a blade pitch angle adjustment instruction to the wind turbine according to the predicted dynamic blade pitch angle of the wind turbine, and verify and correct the predicted result of the blade pitch angle through a feedback mechanism to achieve the optimization of the power output of the wind turbine.

[0089] In this embodiment, in the wind direction turbulence intensity analysis module 100, the formula for calculating the wind direction turbulence intensity according to the historical wind speed and the historical wind direction is:

[0090] ;

[0091] In the formula, It indicates the wind turbulence intensity, which is a quantitative representation of wind direction fluctuations; represents the number of samples; Indicates The change in wind direction per time step; Indicates The change in wind direction per time step; Indicates The change in wind direction per time step; Indicates instantaneous wind speed; Represents the average wind speed in historical data.

[0092] In this embodiment, in the current pitch angle analysis module 200, the expression formula of the optimal pitch angle calculation model is:

[0093] ;

[0094] In the formula, Indicates the optimal pitch angle; is the wind direction turbulence intensity influence coefficient; is the power influence coefficient; is the historical power generation data; Indicates the offset.

[0095] In this embodiment, the pitch angle dynamic prediction module 300, the pitch angle prediction model is expressed as follows:

[0096] ;

[0097] In the formula, Indicates the future The predicted pitch angle possible at any moment; Represents the wind direction turbulence change rate coefficient, which is used to enhance the sensitivity of pitch response; Indicates the instantaneous change in turbulence intensity; represents the average value of turbulence intensity;

[0098] The pitch angle dynamic prediction module 300 is also used to train the characteristics of the pitch angle prediction model in combination with a multi-layer neural network model. The structure of the pitch angle prediction model after training is:

[0099] ;

[0100] In the formula, Responsible for inputting features, Including wind direction turbulence intensity, wind speed change rate, and power generation fluctuation amplitude in historical data to form a feature vector set; Use activation function (ReLU) for nonlinear transformation; is the optimal pitch angle for the final output.

[0101] In this embodiment, in the pitch angle command adjustment module 400, verifying and correcting the prediction result of the blade pitch angle through the feedback mechanism includes:

[0102] The output power of the wind turbine is monitored in real time and compared with the theoretical optimal value. If the deviation exceeds the set threshold, the coefficient of the optimal pitch angle calculation model is adjusted. , , Parameters are modified;

[0103] If the wind direction turbulence intensity fluctuation exceeds the threshold, the wind direction turbulence change rate coefficient, which is the sensitivity index of pitch adjustment, is increased. .

[0104] It should be noted that the information interaction, execution process and other contents between the modules of the above-mentioned device are based on the same concept as the method embodiment in Example 1 of the present application, and the technical effects they bring are the same as those of the method embodiment of the present application. For specific contents, please refer to the description in the method embodiment shown in the previous part of the present application, and will not be repeated here.

[0105] Example 3

[0106] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, in which a program code for a method for adjusting the pitch of wind turbine blades based on wind direction turbulence intensity is stored. The program code includes instructions for executing embodiment 1 or any possible implementation thereof.

[0107] Computer-readable storage media can be any available media that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives, SSDs), etc.

[0108] Example 4

[0109] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0110] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the wind turbine blade pitch adjustment method based on wind direction turbulence intensity of Example 1 or any possible implementation thereof.

[0111] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor implemented by reading software codes stored in a memory. The memory can be integrated in the processor or can be located outside the processor and exist independently.

[0112] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0113] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0114] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A method for adjusting the pitch of wind turbine blades based on wind direction turbulence intensity, characterized in that: include: S1. Obtain designated historical data of the wind farm where the wind turbine is located, wherein the designated historical data includes historical wind speed and historical wind direction; and calculate the wind direction turbulence intensity according to the historical wind speed and the historical wind direction; S2. constructing an optimal pitch angle calculation model, wherein the optimal pitch angle calculation model calculates the pitch angle of the optimal output power under the current wind field conditions according to the unit operation data of the wind turbine unit and the wind direction turbulence intensity; S3, constructing a pitch angle prediction model, and using the pitch angle prediction model to predict the pitch angle of the dynamic blades of the wind turbine in a specified period according to changes in wind field conditions, so as to respond to the impending turbulent fluctuations and adjust the pitch angle of the wind turbine to the optimal value in real time; S4, sending a blade pitch angle adjustment instruction to the wind turbine according to the predicted dynamic blade pitch angle of the wind turbine, and verifying and correcting the predicted result of the blade pitch angle through a feedback mechanism to achieve the optimization of the power output of the wind turbine; The formula for calculating the wind direction turbulence intensity according to the historical wind speed and the historical wind direction is: Where, TKE dir represents the wind turbulence intensity, which is a quantitative representation of wind direction fluctuations; N represents the number of samples; Δθ i represents the change in wind direction at the i-th time step; Δθ i-1 represents the change in wind direction at the i-1th time step; Δθ i+1 Indicates the change in wind direction at the i+1th time step; V i Indicates instantaneous wind speed; V avg Indicates the average wind speed in historical data; The expression formula of the optimal pitch angle calculation model is: In the formula, β opt represents the optimal pitch angle; α is the wind direction turbulence intensity influence coefficient; γ is the power influence coefficient; P turb is the historical power generation data; δ represents the offset; The expression formula of the pitch angle prediction model is: In the formula, β pred (t+Δt) represents the possible predicted pitch angle at the future time t+Δt; κ represents the wind direction turbulence change rate coefficient, which is used to enhance the sensitivity of the pitch response; ΔTKE dir Indicates the instantaneous change in turbulence intensity; TKE dir,avg Represents the average value of turbulence intensity.

2. The method for adjusting the pitch of wind turbine blades based on wind direction turbulence intensity according to claim 1, characterized in that: It also includes training the characteristics of the pitch angle prediction model in combination with a multi-layer neural network model, and the structure of the pitch angle prediction model after training is: β pred =f(Layer1(Layer0(Features))) In the formula, Layer0 is responsible for inputting features, including wind direction turbulence intensity, wind speed change rate, and power generation fluctuation amplitude in historical data, forming a feature vector set; Layer1 uses activation function (ReLU) for nonlinear transformation; β pred is the optimal pitch angle for the final output.

3. The method for adjusting the pitch of wind turbine blades based on wind direction turbulence intensity according to claim 2, characterized in that: The feedback mechanism verifies and corrects the predicted results of blade pitch angle, including: The output power of the wind turbine is monitored in real time, and compared with a theoretical optimal value. If the deviation exceeds a set threshold, the coefficients α, γ, and δ parameters of the optimal pitch angle calculation model are corrected; If the wind direction turbulence intensity fluctuation exceeds the threshold, the wind direction turbulence change rate coefficient κ, which is the sensitivity index of pitch adjustment, is increased.

4. A wind turbine blade pitch adjustment device based on wind direction turbulence intensity, characterized in that: include: A wind direction turbulence intensity analysis module is used to obtain designated historical data of the wind farm where the wind turbine is located, wherein the designated historical data includes historical wind speed and historical wind direction; and calculate the wind direction turbulence intensity according to the historical wind speed and the historical wind direction; A current pitch angle analysis module is used to construct an optimal pitch angle calculation model, wherein the optimal pitch angle calculation model calculates the pitch angle of the optimal output power under the current wind field conditions according to the unit operation data of the wind turbine unit and the wind direction turbulence intensity; The pitch angle dynamic prediction module is used to construct a pitch angle prediction model, through which the pitch angle prediction model is used to predict the dynamic blade pitch angle of the wind turbine in a specified period according to the change of wind field conditions, so as to respond to the impending turbulent fluctuations and adjust the pitch angle of the wind turbine to the optimal value in real time; A pitch angle command adjustment module is used to send a blade pitch angle adjustment command to the wind turbine according to the predicted dynamic blade pitch angle of the wind turbine, and verify and correct the predicted result of the blade pitch angle through a feedback mechanism to achieve the optimization of the power output of the wind turbine; In the wind direction turbulence intensity analysis module, the formula for calculating the wind direction turbulence intensity according to the historical wind speed and the historical wind direction is: Where, TKE dir represents the wind turbulence intensity, which is a quantitative representation of wind direction fluctuations; N represents the number of samples; Δθ i represents the change in wind direction at the i-th time step; Δθ i-1 represents the change in wind direction at the i-1th time step; Δθ i+1 Indicates the change in wind direction at the i+1th time step; V i Indicates instantaneous wind speed; V avg Indicates the average wind speed in historical data; In the current pitch angle analysis module, the expression formula of the optimal pitch angle calculation model is: In the formula, β opt represents the optimal pitch angle; α is the wind direction turbulence intensity influence coefficient; γ is the power influence coefficient; P turb is the historical power generation data; δ represents the offset; In the pitch angle dynamic prediction module, the pitch angle prediction model is expressed as: In the formula, β pred (t+Δt) represents the possible predicted pitch angle at the future time t+Δt; κ represents the wind direction turbulence change rate coefficient, which is used to enhance the sensitivity of the pitch response; ΔTKE dir Indicates the instantaneous change in turbulence intensity; TKE dir,avg Represents the average value of turbulence intensity.

5. The wind turbine blade pitch adjustment device based on wind direction turbulence intensity according to claim 4 is characterized in that: The pitch angle dynamic prediction module is also used to train the characteristics of the pitch angle prediction model in combination with a multi-layer neural network model. The structure of the pitch angle prediction model after training is: β pred =f(Layer1(Layer0(Features))) In the formula, Layer0 is responsible for inputting features, including wind direction turbulence intensity, wind speed change rate, and power generation fluctuation amplitude in historical data, forming a feature vector set; Layer1 uses activation function (ReLU) for nonlinear transformation; β pred is the optimal pitch angle for the final output.

6. The wind turbine blade pitch adjustment device based on wind direction turbulence intensity according to claim 5, characterized in that: In the pitch angle command adjustment module, verifying and correcting the predicted result of the blade pitch angle through the feedback mechanism includes: The output power of the wind turbine is monitored in real time, and compared with a theoretical optimal value. If the deviation exceeds a set threshold, the coefficients α, γ, and δ parameters of the optimal pitch angle calculation model are corrected; If the wind direction turbulence intensity fluctuation exceeds the threshold, the wind direction turbulence change rate coefficient κ, which is the sensitivity index of pitch adjustment, is increased.

Images