Dynamic correction method and device for aerodynamic load of wind turbine generator, medium and equipment

Abstract

The invention relates to the technical field of wind power generation, and provides a dynamic correction method and device for the aerodynamic load of a wind turbine generator, a medium and equipment, and the method comprises the steps that sensing data about a target wind turbine generator are collected based on a sensor preset in the target wind turbine generator; performing reverse calculation on the pneumatic thrust and torque of each blade element by utilizing the blade finite element model and the blade inherent frequency of the target wind turbine generator in combination with the structural load data to generate an aerodynamic force time sequence; inputting the aerodynamic force time sequence, the environmental parameter data and the operation state data into a trained correction coefficient prediction model, and predicting a correction coefficient set based on the model to obtain a predicted correction coefficient set; and configuring the prediction correction coefficient set to a standard leaf element momentum theoretical model, and determining an aerodynamic load result after dynamic correction based on the model after coefficient configuration and the sensing data. According to the method, dynamic correction of the aerodynamic load under the complex working condition is achieved, and the operation safety and the power generation efficiency of the wind turbine generator are improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of wind power generation, and in particular to a method, device, medium and equipment for dynamically correcting aerodynamic loads of a wind turbine generator set. Background Art

[0002] Momentum-Blade Element Theory (BEMT) is a core model for predicting wind turbine aerodynamic loads. It predicts aerodynamic loads by calculating the velocity-induced factor (VIF) of wind turbine blades. Since its introduction, the theory has become a crucial tool for wind turbine design and operational analysis, particularly in aerodynamic performance assessment and load prediction during the wind turbine design phase. The BEMT method uses repeated iterative calculations to gradually determine the VIF of wind turbine blades, thereby calculating the wind turbine loads.

[0003] In related technologies, although BEMT provides a theoretical basis for predicting wind turbine aerodynamic loads, its prediction accuracy is heavily dependent on a large number of empirical correction coefficients, such as tip loss correction, hub loss correction, and Glauert correction. These correction coefficients are usually determined through wind tunnel tests or calibration under static conditions. However, due to the influence of factors such as turbulence, yaw, and stall in complex wind field environments, traditional correction methods are difficult to adapt to dynamic changes in actual operation, resulting in large deviations in load prediction. In addition, most correction coefficients are set as fixed values ​​or piecewise functions, which cannot respond to dynamic factors such as sudden changes in wind speed and blade aging in real time. Moreover, the correction model based on theoretical assumptions lacks data-driven capabilities and cannot fully utilize the big data in wind turbine operation for real-time optimization and adjustment. Summary of the Invention

[0004] The embodiments of the present disclosure at least provide a method, device, medium and equipment for dynamic correction of aerodynamic loads of a wind turbine generator set, which realizes dynamic correction of aerodynamic loads under complex working conditions and improves the operating safety and power generation efficiency of the wind turbine generator set.

[0005] The present disclosure provides a method for dynamically correcting aerodynamic loads of a wind turbine generator set, comprising:

[0006] Collecting sensor data about the target wind turbine generator set based on sensors pre-installed in the target wind turbine generator set; wherein the sensor data includes structural load data, environmental parameter data and operating status data;

[0007] Using the blade finite element model and the blade natural frequency of the target wind turbine, combined with the structural load data, the aerodynamic thrust and torque of each blade element are reversely calculated to generate an aerodynamic time series;

[0008] Inputting the aerodynamic time series, the environmental parameter data, and the operating status data into a trained correction coefficient prediction model, and predicting a correction coefficient set based on the trained correction coefficient prediction model to obtain a predicted correction coefficient set;

[0009] The prediction correction coefficient set is configured to a standard blade element momentum theoretical model, and a dynamically corrected aerodynamic load result is determined based on the standard blade element momentum theoretical model after the coefficient configuration, the sensor data, and the aerodynamic force time series.

[0010] The embodiment of the present disclosure provides a dynamic correction device for aerodynamic loads of a wind turbine generator set, comprising:

[0011] A data acquisition module, configured to collect sensor data about a target wind turbine generator set based on sensors pre-installed in the target wind turbine generator set; wherein the sensor data includes structural load data, environmental parameter data, and operating status data;

[0012] a sequence generation module for inversely calculating the aerodynamic thrust and torque of each blade element using a blade finite element model and the blade natural frequency of the target wind turbine in combination with the structural load data to generate an aerodynamic time series;

[0013] a coefficient prediction module, configured to input the aerodynamic time series, the environmental parameter data, and the operating status data into a trained correction coefficient prediction model, and predict a correction coefficient set based on the trained correction coefficient prediction model to obtain a predicted correction coefficient set;

[0014] The result correction module is used to configure the prediction correction coefficient set to the standard blade element momentum theoretical model, and determine the dynamically corrected aerodynamic load result based on the standard blade element momentum theoretical model after the coefficient configuration, the sensor data and the aerodynamic force time series.

[0015] An embodiment of the present disclosure provides a computer device, comprising: a processor, a memory, and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the computer device is running, the processor and the memory communicate via the bus, and when the machine-readable instructions are executed by the processor, a method for dynamically correcting the aerodynamic load of a wind turbine set as described in any of the possible embodiments described above is performed.

[0016] An embodiment of the present disclosure provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for dynamically correcting the aerodynamic load of a wind turbine generator set as described in any of the above possible embodiments is implemented.

[0017] The methods, devices, media and equipment for dynamic correction of aerodynamic loads of wind turbines provided in the embodiments of the present disclosure specifically collect sensor data about the target wind turbine based on sensors pre-installed in the target wind turbine; use the blade finite element model and the blade natural frequency of the target wind turbine, combined with structural load data, to reversely calculate the aerodynamic thrust and torque of each blade element to generate an aerodynamic time series; input the aerodynamic time series, environmental parameter data and operating status data into a trained correction coefficient prediction model, predict the correction coefficient set based on the trained correction coefficient prediction model, and obtain a predicted correction coefficient set; configure the predicted correction coefficient set to a standard blade element momentum theoretical model, and determine the aerodynamic load result after dynamic correction based on the standard blade element momentum theoretical model after coefficient configuration and the sensor data.

[0018] In this way, the present invention obtains a correction coefficient set by utilizing sensor data and a trained correction coefficient prediction model, and dynamically corrects the aerodynamic load of the wind turbine based on the correction coefficient set and the standard blade element momentum theoretical model, so as to continuously optimize the performance of the turbine in complex environments and different operating conditions, thereby improving the operating safety and power generation efficiency of the wind turbine.

[0019] In order to make the above-mentioned objectives, features and advantages of the present disclosure more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the following briefly introduces the drawings that need to be cited in the embodiments. The drawings herein are incorporated into and constitute a part of the specification. These drawings illustrate embodiments consistent with the present disclosure and, together with the specification, are used to illustrate the technical solutions of the present disclosure. It should be understood that the following drawings only illustrate certain embodiments of the present disclosure and should not be regarded as limiting the scope. For those of ordinary skill in the art, other relevant drawings can be obtained based on these drawings without inventive effort.

[0021] Figure 1 A flow chart showing a method for dynamically correcting aerodynamic loads of a wind turbine generator set provided by an embodiment of the present disclosure is shown;

[0022] Figure 2 A flow chart of a method for calculating aerodynamic time series provided by an embodiment of the present disclosure is shown;

[0023] Figure 3 A flow chart of a method for determining a trained correction coefficient prediction model provided by an embodiment of the present disclosure is shown;

[0024] Figure 4A flowchart of a method for training a correction coefficient prediction model provided by an embodiment of the present disclosure is shown;

[0025] Figure 5 A flow chart of a model optimization method provided by an embodiment of the present disclosure is shown;

[0026] Figure 6 A schematic structural diagram of a dynamic correction device for aerodynamic loads of a wind turbine generator set provided by an embodiment of the present disclosure is shown;

[0027] Figure 7 A schematic structural diagram of another device for dynamically correcting aerodynamic loads of a wind turbine generator set provided by an embodiment of the present disclosure is shown;

[0028] Figure 8 A schematic structural diagram of a computer device provided by an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0029] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. The components of the embodiments of the present disclosure generally described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present disclosure provided in the drawings is not intended to limit the scope of the disclosure for which protection is sought, but merely represents selected embodiments of the present disclosure. Based on the embodiments of the present disclosure, all other embodiments obtained by those skilled in the art without making creative work are within the scope of protection of the present disclosure.

[0030] It should be noted that similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined or explained in subsequent drawings.

[0031] The term "and / or" herein simply describes an association relationship, indicating that three relationships can exist. For example, A and / or B can represent the existence of A alone, the simultaneous existence of A and B, and the existence of B alone. In addition, the term "at least one" herein refers to any combination of at least two of any one or more of a plurality of items. For example, "at least one of A, B, and C" can represent any one or more elements selected from the set consisting of A, B, and C.

[0032] Momentum-Blade Element Theory (BEMT) is a core method widely used to predict aerodynamic loads on wind turbines. This method analyzes the interaction between the rotational motion of wind turbine blades and air flow, using the momentum theorem and energy balance equation to predict the aerodynamic loads on wind turbine blades in a wind field. BEMT uses repeated iterative calculations to determine the velocity induction factor of the wind turbine blades, thereby solving for the loads on the wind turbine. This method is advantageous due to its simplicity and relatively high computational efficiency, making it suitable for wind turbine design and preliminary aerodynamic performance assessment.

[0033] However, with the increase in wind turbine scale and the complexity of the working environment, the BEMT method faces the problems of slow calculation speed and large computational workload. Especially in the actual working conditions where wind turbine operating conditions are complex and changeable, the repeated iterations of the calculation process will significantly reduce the real-time performance.

[0034] Research has found that the prediction accuracy of BEMT depends on a series of empirical correction coefficients, such as tip loss correction, hub loss correction and Glauert correction. These correction coefficients usually need to be set through wind tunnel experiments or calibration of static working conditions, so their application in complex wind farm environments has great limitations. Dynamic factors such as turbulence, yaw and stall in the wind farm will affect the aerodynamic performance of the blades, resulting in the inability of traditional correction coefficients to effectively cope with sudden changes in wind speed and blade aging. In addition, the correction coefficients are generally set as fixed values ​​or piecewise functions, which cannot respond to factors such as wind speed changes and equipment aging in real time, thereby leading to deviations in wind turbine load predictions, which not only affects the service life of the unit, but may also affect the power generation efficiency of the wind farm. Since the theoretical basis of the existing model mainly relies on assumptions and empirical corrections, it lacks the ability to dynamically optimize based on real-time data, and cannot effectively use real-time data from wind turbine operation for parameter optimization.

[0035] Based on the above research, a method, device, medium and equipment for dynamic correction of the aerodynamic load of a wind turbine are provided in an embodiment of the present disclosure. Specifically, sensor data about the target wind turbine is collected based on sensors pre-installed in the target wind turbine; the aerodynamic thrust and torque of each blade element are inversely calculated using the blade finite element model and the blade natural frequency of the target wind turbine, combined with the structural load data, to generate an aerodynamic time series; the aerodynamic time series, environmental parameter data and operating status data are input into a trained correction coefficient prediction model, and the correction coefficient set is predicted based on the trained correction coefficient prediction model to obtain a predicted correction coefficient set; the predicted correction coefficient set is configured to a standard blade element momentum theoretical model, and based on the standard blade element momentum theoretical model after coefficient configuration and the sensor data, the dynamically corrected aerodynamic load result is determined.

[0036] In the disclosed embodiment, a correction coefficient set is obtained by utilizing sensor data and a trained correction coefficient prediction model, and the aerodynamic load of the wind turbine is dynamically corrected based on the correction coefficient set and a standard blade element momentum theoretical model, so as to continuously optimize the performance of the turbine in complex environments and under different operating conditions, thereby improving the operating safety and power generation efficiency of the wind turbine.

[0037] To facilitate understanding of this embodiment, the execution subject of the dynamic correction method for the aerodynamic load of a wind turbine provided by the embodiment of the present disclosure is first introduced in detail. The execution subject of the dynamic correction method for the aerodynamic load of a wind turbine provided by the embodiment of the present disclosure is a computer device. The computer device may be a terminal device or a server. Among them, the terminal device may also be a mobile device, a user terminal, a terminal, a handheld device, a computing device, a vehicle-mounted device, a wearable device, etc. The server may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud storage, big data and artificial intelligence platforms. Optionally, the method may also be applied to an implementation environment composed of a computer device and a server.

[0038] The following describes in detail the dynamic correction method for the aerodynamic load of a wind turbine provided by the embodiment of the present application in conjunction with the accompanying drawings. Figure 1 FIG. 1 is a flow chart of a method for dynamically correcting aerodynamic loads of a wind turbine generator system according to an embodiment of the present disclosure. The method includes the following steps S101 to S104:

[0039] S101 , collecting sensor data about a target wind turbine generator set based on sensors pre-installed in the target wind turbine generator set.

[0040] It is understood that the various sensors pre-installed in the target wind turbine are primarily used to monitor the wind turbine's operation in real time, ensuring accurate real-time data. The sensor data includes structural load data, environmental parameter data, and operating status data. Structural load data can include blade root bending moment and tower vibration acceleration, environmental parameter data can include wind speed and turbulence intensity, and operating status data can include yaw angle.

[0041] Specifically, structural load data reflects the magnitude and direction of the forces acting on various components of a wind turbine. For example, strain gauge sensors installed at the root of a blade are a common device used to measure blade root bending moments. When a blade bends and deforms under wind force, the strain gauge produces a corresponding change in resistance. By measuring this resistance change and performing a series of conversions and calculations, the magnitude of the blade root bending moment can be determined. Blade root bending moment is an important indicator of blade stress. Excessive bending moment can cause cracks or even breakage in the blade. For another example, the tower, as the supporting structure of a wind turbine, vibrates under wind force. Accelerometers at the base of the tower can measure the tower's acceleration in different directions in real time. By analyzing this vibration acceleration data, the tower's vibration acceleration can be indirectly inferred. The magnitude and frequency of the tower's vibration acceleration reflect the tower's stress state and stability. Excessive vibration acceleration or abnormal frequency may indicate structural problems or excessive external forces acting on the tower, requiring prompt action to prevent serious accidents such as collapse. Structural load data can also include hub torque and blade torque.

[0042] Specifically, environmental parameter data describes the external environmental conditions of a wind turbine, which directly impact its operating performance and aerodynamic loads. Wind speed sensors measure wind speed in real time, making it one of the most critical environmental parameters for wind turbine operation. Wind speed determines the amount of wind energy a wind turbine can capture, which in turn affects the turbine's power generation. Wind direction sensors determine wind direction, which is crucial for yaw control of the wind turbine. By adjusting the turbine's yaw angle to ensure the blades always face the wind, wind energy capture efficiency can be maximized. Furthermore, lidar sensors can be used to measure turbulence intensity, which refers to the degree of irregular temporal and spatial variations in wind speed. High turbulence intensity can make the aerodynamic loads on a wind turbine more complex and unstable, increasing the risk of fatigue damage. By emitting a laser beam and measuring the temporal and intensity variations of the reflected light, lidar sensors can accurately measure the three-dimensional distribution of wind speed, thereby calculating turbulence intensity. Environmental parameter data can also include data such as temperature, humidity, and air pressure.

[0043] Specifically, the operating status data records the operating status of the wind turbine itself and reflects the performance of the turbine under different working conditions. The yaw angle is an important parameter in the operating status data, which indicates the deflection angle of the wind turbine nacelle relative to the wind direction. By monitoring the yaw angle in real time, it is possible to understand whether the yaw system of the turbine is working properly and whether the turbine can track wind direction changes in a timely and accurate manner. If the yaw angle is abnormal, the blades may not always face the wind direction, thereby reducing the efficiency of capturing wind energy and may even cause damage to the structure of the turbine. In addition to the yaw angle, the operating status data can also include parameters such as blade speed and pitch angle.

[0044] S102 , using the blade finite element model and the blade natural frequency of the target wind turbine generator set, combined with the structural load data, reversely calculate the aerodynamic thrust and torque of each blade element to generate an aerodynamic time series.

[0045] Here, the blade finite element model is a mathematical model that discretizes the blade into a finite number of units. By dividing the blade into many small units and performing mechanical analysis on each unit, the force conditions of the blade during actual operation can be simulated more accurately. For example, the blade is divided into hundreds of triangular or quadrilateral units, each unit has its own specific material properties, geometric shape and boundary conditions. By calculating the mechanical behavior of these units, the mechanical response of the entire blade can be obtained. The blade natural frequency is an inherent property of the blade itself. When the blade is subjected to external force, it will vibrate near its natural frequency. When the external excitation frequency is close to the blade's natural frequency, resonance may be triggered, causing the blade to be subjected to greater loads.

[0046] It is understandable that, given known structural load data, the aerodynamic thrust and torque of each blade element can be reversely calculated using the blade finite element model and blade natural frequency. A blade element is a tiny segment on a blade and serves as the basic unit for analyzing blade aerodynamic performance. Each blade element is subject to aerodynamic forces, which are generated by the pressure distribution of wind on the blade surface and include lift and drag. Lift is perpendicular to the incoming flow direction, causing the blade to generate a rotational torque, driving the wind turbine to rotate and generate electricity; drag is opposite to the incoming flow direction, consuming some wind energy and reducing the efficiency of the wind turbine. Specifically, by measuring the load data at the blade root (i.e., the blade root bending moment and tower vibration acceleration), combined with the blade finite element model and natural frequency, the aerodynamic thrust and torque acting on the blade element near this location can be calculated. Arranging these calculation results in chronological order generates an aerodynamic time series. Here, the aerodynamic time series can reflect how the aerodynamic forces on the blades change over time. At different time points, the aerodynamic thrust and torque acting on each blade element will change due to changes in environmental factors such as wind speed and direction, as well as the operating status of the wind turbine. For example, when the wind speed suddenly increases, the aerodynamic forces acting on the blades will also increase accordingly; when the wind direction changes, the distribution of aerodynamic forces at different positions on the blades will also change.

[0047] For example, referring to Figure 2 As shown in FIG. 1 , a method for calculating aerodynamic time series proposed in the present disclosure may include the following steps S201 to S202 :

[0048] S201 : establishing a finite element model of blades of the target wind turbine generator set, and performing modal analysis on the blade finite element model to obtain the natural frequency of each blade of the target wind turbine generator set.

[0049] Here, when establishing the blade finite element model, it is necessary to comprehensively consider the actual structural characteristics and material properties of the blade. First, the three-dimensional geometric data of the blade is obtained, including information such as the blade's outline shape and thickness variation. Then, based on the type of material used for the blade, its material property parameters such as elastic modulus, Poisson's ratio, and density are determined. Next, the appropriate element type is selected to discretize the blade, such as high-precision triangular or quadrilateral elements. The element mesh is then rationally divided according to the blade's geometric shape and force characteristics to ensure that the mesh quality and density meet the requirements of calculation accuracy.

[0050] After the model is established, modal analysis is performed. Modal analysis is a method used to determine the natural frequencies and vibration modes of a structure. It solves the vibration equations of the finite element model to obtain the natural frequencies and corresponding vibration modes of the blades at different vibration orders. During the modal analysis, the blade boundary conditions, such as whether the blade root is fixed, must be considered. Modal analysis can determine the natural frequencies of each blade under different vibration modes.

[0051] S202 : performing reverse calculation on the aerodynamic thrust and torque of each blade element based on the natural frequency of each blade, the blade root bending moment, and the tower vibration acceleration to generate the aerodynamic force time series.

[0052] Specifically, after obtaining the natural frequency of each blade, an inverse calculation can be performed, combined with structural load data such as blade root bending moments and tower vibration accelerations measured by sensors. This inverse calculation is a complex iterative process. First, based on initial aerodynamic assumptions, the blade finite element model is used to calculate the blade response, including deformation, stress distribution, and vibration. The calculated blade response is then compared with the measured blade root bending moments and tower vibration accelerations. If there are discrepancies, the assumed aerodynamic force values ​​are adjusted and the calculation is repeated. When adjusting the assumed aerodynamic force values, optimization algorithms such as gradient descent and genetic algorithms can be used to improve computational efficiency and accuracy. Continuous iteration and adjustment are performed until the calculated blade response matches the actual measured data. At this point, the resulting aerodynamic force values ​​can be considered the actual aerodynamic thrust and torque experienced by each blade element at different points in time. Arranging these aerodynamic force values ​​in chronological order generates an aerodynamic force time series.

[0053] In this way, the aerodynamic changes of wind turbines under different operating conditions can be accurately obtained, providing strong support for the performance evaluation and optimization of wind turbines.

[0054] In some possible embodiments, during actual wind turbine operation, blades are subject to various vibration noise interferences, such as random vibrations caused by wind turbulence and vibration transmission from mechanical components. These noises can affect the accuracy of subsequent aerodynamic calculations. Therefore, modal analysis results can be used to filter out these vibration noise interferences. By analyzing the blade's vibration response at different frequencies, it is possible to distinguish between signals caused by natural vibration and signals caused by noise, thereby filtering the measured data and improving the data's signal-to-noise ratio. After filtering out the vibration noise interference, the relationship between strain and bending moment is used to infer the aerodynamic thrust and torque of each blade element.

[0055] When using the relationship between strain and bending moment to infer the aerodynamic thrust and torque of each blade element, a mathematical relationship can be established between the blade root bending moment and the aerodynamic thrust and torque of each blade element based on the principles of material mechanics and structural mechanics. This requires consideration of multiple factors, including the blade's geometry, material properties, force distribution, and vibration. For example, the airfoil at different locations on the blade varies, responding differently to aerodynamic forces, which affects the distribution of the bending moment. Furthermore, blade vibration alters the effect of aerodynamic forces, in turn affecting the magnitude and direction of the bending moment. Furthermore, this relationship, combined with measured blade root bending moment data, allows inferring the aerodynamic thrust and torque experienced by each blade element. During the inferring process, multiple iterative calculations may be required to continuously refine the estimated aerodynamic thrust and torque, ensuring that the calculated blade root bending moment matches the measured value.

[0056] In some possible embodiments, since the aerodynamic thrust and torque data for each blade element obtained through inverse calculation are raw load data, these data may contain some high-frequency noise components, which may be caused by factors such as measurement errors and environmental interference. In order to ensure that these data can match the subsequent BEMT (Blade Element Momentum Theory) model input, the converted load data needs to be low-pass filtered. Here, low-pass filtering is a signal processing technique that allows low-frequency signals to pass while suppressing high-frequency signals. By selecting an appropriate cutoff frequency, high-frequency noise in the load data can be effectively removed, retaining the low-frequency signal that reflects the true trend of aerodynamic changes. After low-pass filtering, the aerodynamic data forms an aerodynamic time series that matches the BEMT model input requirements.

[0057] S103 , inputting the aerodynamic time series, the environmental parameter data, and the operating status data into a trained correction coefficient prediction model, and predicting a correction coefficient set based on the trained correction coefficient prediction model to obtain a predicted correction coefficient set.

[0058] It is understandable that the set of prediction correction coefficients contains multiple key parameters, which play an important role in accurately describing the aerodynamic characteristics and operating status of wind turbines. Among them, the tip loss correction factor is used to compensate for the aerodynamic losses caused by the airflow around the blade tip. In actual operation, the airflow velocity and pressure distribution at the blade tip are different from those in the middle of the blade. This correction factor can effectively correct the impact of this difference on the overall aerodynamic performance; the critical induction factor threshold of the Glauert correction is an important parameter in the blade element momentum theory. It determines under what induction factor conditions the Glauert correction is required to avoid unreasonable prediction results of the theoretical model under high load conditions; the rotation enhancement coefficient takes into account the enhancement of aerodynamic performance due to factors such as centrifugal force and Coriolis force during the blade rotation process, which is of great significance for accurately evaluating the power output and load characteristics of wind turbines.

[0059] Here, the aerodynamic time series, environmental parameter data and operating status data are input into the trained correction coefficient prediction model, which can predict the correction coefficient set based on the input data.

[0060] Specifically, refer to Figure 3 As shown, the trained correction coefficient prediction model can be obtained through the following steps S301 to S303:

[0061] S301, construct a standard blade element momentum theory model.

[0062] It is understood that the standard blade element momentum theory model is the fundamental theoretical model for analyzing the aerodynamic performance of wind turbines. It divides the blade into multiple blade elements along the span direction, calculates the aerodynamic force on each blade element, and then considers the influence of the wake through momentum theory to obtain the aerodynamic performance of the entire blade. Constructing the standard blade element momentum theory model requires clarifying the blade's geometric parameters (such as airfoil, chord length, twist angle, etc.), aerodynamic parameters (such as lift coefficient, drag coefficient, etc.), and operating parameters (such as wind speed, rotational speed, etc.). The model's calculation function is implemented through mathematical formulas and algorithms.

[0063] S302: Obtain a correction coefficient prediction model to be trained and a training data set.

[0064] Specifically, the correction coefficient prediction model to be trained is usually constructed using machine learning or deep learning algorithms, such as neural networks and support vector machines. The correction coefficient prediction model to be trained can learn the complex relationship between input data and correction coefficients from a large amount of data. Here, the present disclosure adopts a long short-term memory network (LSTM), which can effectively process time series data and capture long-term dependencies in the data. It is suitable for modeling and predicting time series data such as aerodynamic forces, environmental parameters, and operating status. Through the training of the LSTM model, the correction coefficient can be predicted more accurately, thereby optimizing the control strategy of the system.

[0065] The training data set includes multiple training data subsets, each of which contains multiple time series data. Each time series data includes aerodynamic training data, environmental parameter training data, and operating status training data at the corresponding moment.

[0066] S303 : Training the correction coefficient prediction model to be trained based on the training data set and the standard blade element momentum theoretical model to obtain the trained correction coefficient prediction model.

[0067] Here, refer to Figure 4 As shown, the training method of the correction coefficient prediction model may include the following steps S3031 to S3033:

[0068] S3031. For each training data subset, determine a set of training prediction correction coefficients corresponding to the training data subset based on the correction coefficient prediction model to be trained and the training data subset; configure the standard blade element momentum theoretical model based on the training prediction correction coefficient set; and determine a training aerodynamic load result corresponding to the training data subset based on the configured standard blade element momentum theoretical model and the training data subset.

[0069] Specifically, for each training data subset, a training prediction correction coefficient set corresponding to the subset is first determined based on the correction coefficient prediction model to be trained and the training data subset. The correction coefficient prediction model to be trained will output a set of predicted correction coefficients based on the input aerodynamic training data, environmental parameter training data, and operating status training data. These correction coefficients constitute the training prediction correction coefficient set. Then, based on the training prediction correction coefficient set, the standard blade element momentum theory model is configured. Specifically, the predicted correction coefficients are substituted into the standard blade element momentum theory model, and the relevant parameters of the model are adjusted so that the model can better adapt to the operating conditions represented by the current training data subset. Finally, based on the configured standard blade element momentum theory model and the training data subset, the training aerodynamic load results corresponding to the subset are determined. Specifically, the input parameters in the training data subset are input into the configured standard blade element momentum theory model, and the model calculates the corresponding aerodynamic load results, such as the thrust and torque of the blade.

[0070] S3032: Determine a loss value between the training aerodynamic load result corresponding to the training data subset and the sample label corresponding to the training data subset based on a preset loss function, and adjust the model parameters of the correction coefficient prediction model to be trained based on the loss value.

[0071] Specifically, a preset loss function is used to determine the loss between the predicted aerodynamic load results corresponding to a subset of the training data and the sample labels corresponding to that subset. Here, the sample labels are the actual measured aerodynamic load results, which serve as the true values ​​used to evaluate the model's prediction accuracy. The loss function measures the degree of discrepancy between the predicted aerodynamic load results and the sample labels. Common loss functions include mean squared error (MSE) and mean absolute error (MAE). By calculating the loss value, the model's prediction error can be quantified.

[0072] Furthermore, the model parameters of the correction coefficient prediction model to be trained can be adjusted based on the loss value. The goal of adjusting model parameters is to make the model's predictions closer to the true values, thereby reducing the loss value. Common parameter adjustment methods in machine learning and deep learning include gradient descent, stochastic gradient descent, and the Adam optimization algorithm. These methods use the gradient information of the loss function to update the model parameters in a direction that reduces the loss value. Through multiple iterations, the model's performance is gradually optimized.

[0073] S3033, repeat the above steps S3031 to S3032 until the training results meet the preset requirements, and obtain the trained correction coefficient prediction model.

[0074] Here, steps S3031 and S3032 are repeated to continuously adjust the model parameters of the correction coefficient prediction model to be trained. During the training process, certain preset requirements are required, such as a loss value less than a certain threshold and a model accuracy level on the validation set reaching a certain level. When the training results meet the preset requirements, it indicates that the model has learned a reasonable relationship between the input data and the correction coefficient, and a trained correction coefficient prediction model is obtained.

[0075] For example, in order to further improve the accuracy and adaptability of the correction coefficient prediction model in view of the variability of the complex wind farm environment, the present disclosure also proposes a method for optimizing the model according to different working conditions, which may include the following steps (1) to (4):

[0076] (1) When the wind speed corresponding to the training data subset is higher than a preset wind speed threshold, the training data subset is determined to be in a high wind speed condition, and the optimization weight of the Glauert critical induction factor threshold is increased to suppress the influence of the wake turbulence effect on the load prediction;

[0077] (2) when the yaw angle corresponding to the training data subset is higher than a preset yaw angle threshold, the training data subset is determined to be in a large yaw angle operating condition, the torque deviation caused by the skew flow is compensated by correcting the lateral velocity distribution, and the rotation enhancement coefficient is updated based on the correlation between the blade element position and the rotation speed to optimize the boundary layer stability of the yaw airflow due to the rotation effect;

[0078] (3) When the turbulence intensity corresponding to the training data subset is higher than a preset turbulence intensity threshold, the training data subset is determined to be in a transient strong turbulence condition, a time lag coefficient is introduced to simulate the time-varying effect of the sudden change in angle of attack on the lift coefficient, and the rotation enhancement coefficient is adjusted according to the instantaneous change in turbulence intensity to balance the influence of the rotation mixing effect and the airflow disturbance;

[0079] (4) During the parameter adjustment process, based on the sensitivity of the tip loss correction factor to thrust prediction, the tip loss correction factor is optimized first, and then other correction coefficients are adjusted iteratively.

[0080] Specifically, when the wind speed corresponding to the training data subset is higher than a preset wind speed threshold (such as 12m / s), it can be determined that the training data subset is in a high wind speed condition. Under high wind speed conditions, the wake turbulence effect of the wind turbine will be more obvious, which will have a greater impact on the load prediction. Therefore, increasing the optimization weight of the Glauert critical induction factor threshold makes the model pay more attention to the adjustment of this parameter to suppress the influence of the wake turbulence effect on the load prediction. By adjusting the Glauert critical induction factor threshold, the correction strategy of the model under high load conditions can be changed, thereby improving the accuracy of load prediction.

[0081] At the same time, when the yaw angle corresponding to the training data subset is higher than the preset yaw angle threshold (such as 15°), it can be determined that the training data subset is in a large yaw angle condition. Under large yaw angle conditions, the airflow distribution of the wind turbine will change significantly, resulting in torque deviation. In order to correct this deviation, the torque deviation caused by the skewed flow can be compensated by correcting the lateral velocity distribution. At the same time, the rotation enhancement coefficient is updated based on the correlation between the blade position and the rotation speed. The rotation speed and force conditions at different blade positions are different, and the rotation enhancement coefficient also needs to be adjusted accordingly to optimize the boundary layer stability of the yaw airflow caused by the rotation effect, thereby improving the prediction accuracy of the model under large yaw angle conditions.

[0082] Similarly, when the turbulence intensity corresponding to the training data subset is higher than the preset turbulence intensity threshold (such as 15%), it can be determined that the training data subset is in a transient strong turbulence condition. Under transient strong turbulence conditions, the angle of attack of the airflow will change suddenly, causing the lift coefficient to change with time. In order to simulate this time-varying effect, a time lag coefficient can be introduced. Here, the time lag coefficient can reflect the time delay of the impact of the sudden change in the angle of attack on the lift coefficient, which can enable the model to more accurately predict changes in aerodynamic performance. At the same time, the rotation enhancement coefficient is adjusted according to the instantaneous change in turbulence intensity to balance the effects of rotational mixing and airflow disturbances. In a strong turbulent environment, both rotational mixing and airflow disturbances will have an impact on aerodynamic performance. By dynamically adjusting the rotation enhancement coefficient, the model can better adapt to this complex working condition.

[0083] It should be noted that the above three operating conditions can exist separately or simultaneously, and are not specifically limited here. At the same time, since the tip loss correction factor has a greater impact on the thrust prediction, it can be optimized first to improve the accuracy of the thrust prediction. Specifically, during the parameter adjustment process, based on the sensitivity of the tip loss correction factor to the thrust prediction, the tip loss correction factor is optimized first. Then, other correction coefficients are iteratively adjusted, such as the critical induction factor threshold and rotation enhancement coefficient of the Glauert correction. By optimizing this parameter adjustment sequence, the prediction performance of the model can be gradually improved, so that the model can give accurate correction coefficient prediction results under various operating conditions.

[0084] In addition, in order to ensure the accuracy and physical rationality of the correction coefficient prediction model, the optimization goal of the correction coefficient in this disclosure is defined as minimizing the difference between the BEMT (blade element momentum theory) corrected load and the measured value. It is specifically achieved through a weighted mean square error function, where the thrust and torque error weights are set to 0.6 and 0.4, respectively. The specific weight setting can take into account the importance of thrust and torque in aerodynamic load prediction, so that the model can more reasonably balance the errors of the two during the optimization process. At the same time, to ensure physical rationality, all correction parameters must meet constraints. For example, the tip loss parameter range is limited to between 0 and 3, and the Glauert critical threshold is between 0.3 and 0.5. These constraints can avoid non-physical solutions to the model, ensure that the prediction results of the model conform to actual physical laws, and improve the credibility and reliability of the model.

[0085] In this way, through the above steps and methods, a trained correction coefficient prediction model can be constructed, and the accuracy and adaptability of the model can be further improved through the operating condition model optimization method, thereby providing reliable support for the performance analysis and optimization of wind turbines.

[0086] In some other embodiments, in order to further improve the prediction accuracy and generalization ability of the model, after obtaining the trained correction coefficient prediction model, the model can also be verified, such as by using a spatiotemporal cross-validation method. This method divides the data into a training set, a validation set, and a test set in a ratio of 7:2:1 to ensure a sufficient training process. The validation set and the test set are used to evaluate the performance and stability of the model. In addition, in order to verify the adaptability of the model in different environments and scenarios, independent data sets from different wind turbines can be extracted for verification to further test the generalization ability of the model and avoid the occurrence of overfitting. In addition, in terms of uncertainty analysis, the uncertainty of the input data can be quantified by Monte Carlo simulation methods. Specifically, ±5% noise can be added to the model input and sampled thousands of times to simulate the fluctuation range of the correction coefficient under different noise levels. This simulation process can help evaluate the robustness of the model in the face of data fluctuations and provide a quantitative basis for uncertainty in practical applications.

[0087] S104 , configuring the prediction correction coefficient set to a standard blade element momentum theoretical model, and determining a dynamically corrected aerodynamic load result based on the standard blade element momentum theoretical model after coefficient configuration, the sensor data, and the aerodynamic force time series.

[0088] Understandably, while the standard blade element momentum theoretical model provides a fundamental framework for aerodynamic load calculations in wind turbine aerodynamic performance analysis, its assumptions often lead to deviations in the complex and changing operating environments of actual operations. By assigning a set of predicted correction coefficients to the standard blade element momentum theoretical model, the present disclosure enables targeted correction and optimization of the model, making the wind turbine aerodynamic load calculations more realistic, thereby yielding more accurate aerodynamic load results (i.e., dynamically corrected aerodynamic load results).

[0089] Here, parameters such as the tip loss correction factor, the Glauert-corrected critical induction factor threshold, and the rotation enhancement coefficient in the prediction correction coefficient set can be used to correct the standard blade element momentum theory model from different perspectives. The tip loss correction factor compensates for the aerodynamic losses caused by airflow around the blade tip, making the model's assessment of the overall aerodynamic performance of the blade more accurate. The Glauert-corrected critical induction factor threshold adjusts the model's correction strategy under high load conditions, avoiding unreasonable predictions from the theoretical model. The rotation enhancement coefficient accounts for the enhanced aerodynamic performance caused by factors such as centrifugal force and Coriolis force during blade rotation, further improving the model's prediction accuracy. By assigning these correction coefficients to the standard blade element momentum theory model, the model can dynamically adjust the calculation parameters according to different operating conditions and environmental conditions, thereby achieving dynamic correction of aerodynamic loads.

[0090] Specifically, the dynamically corrected aerodynamic load results can provide an important basis for subsequent wind turbine performance evaluation, optimized design, and health monitoring. In terms of performance evaluation, accurate aerodynamic load results can more accurately reflect the output power, efficiency, and other performance indicators of wind turbines under different environments and operating conditions, and can help operators understand the actual operating status of the turbine. In the optimization design phase, based on accurate aerodynamic load results, the blade geometry, material selection, etc. can be optimized to improve the aerodynamic performance and power generation efficiency of the wind turbine. In terms of health monitoring, through real-time monitoring and analysis of the dynamically corrected aerodynamic load results, potential fault hazards of wind turbines, such as blade fatigue and bearing wear, can be discovered in a timely manner, so that corresponding maintenance measures can be taken to ensure the efficient operation of wind turbines in different environments and operating conditions, extend the service life of the turbine, and reduce operation and maintenance costs.

[0091] For example, in order to further improve the accuracy and adaptability of the correction coefficient prediction model, the present disclosure also proposes a model optimization method, referring to Figure 5 As shown, the following steps S501 to S502 may be included:

[0092] S501, obtaining a real result corresponding to the sensor data and having the same time length as the dynamically corrected aerodynamic load result, and constructing a model optimization sample set based on the environmental parameter data, the operating status data, the aerodynamic time series and the real result.

[0093] Specifically, a real result corresponding to the sensor data and spanning the same time period as the dynamically corrected aerodynamic load result is obtained. Here, the real result is the actual value of the measured aerodynamic load. Simultaneously, a model optimization sample set is constructed by combining previously acquired environmental parameter data, operating status data, and aerodynamic time series. By correlating and integrating this data with the real results, the constructed model optimization sample set can more comprehensively reflect the actual operation of the wind turbine under different operating conditions, providing strong data support for the optimization training of the correction coefficient prediction model.

[0094] S502 : Optimizing and training the correction coefficient prediction model based on the model optimization sample set and the standard blade element momentum theoretical model, so as to predict a new correction coefficient set using the optimized and trained correction coefficient prediction model.

[0095] Specifically, the correction coefficient prediction model is optimized and trained based on the model optimization sample set and the standard blade element momentum theoretical model. During the optimization training process, data from the model optimization sample set is input into the correction coefficient prediction model, which then outputs a set of predicted correction coefficients. These predicted correction coefficients are then applied to the standard blade element momentum theoretical model to obtain predicted aerodynamic load results. The predicted aerodynamic load results are then compared with the actual results from the model optimization sample set, and the error between the two is calculated using a preset loss function.

[0096] It is understood that, based on the magnitude of the error, optimization algorithms (such as gradient descent and the Adam optimization algorithm) are used to adjust the parameters of the correction coefficient prediction model, gradually bringing the model's predictions closer to the true results. After multiple iterations of training, until the model's prediction accuracy meets the preset requirements, an optimized and trained correction coefficient prediction model is obtained. Using this optimized and trained correction coefficient prediction model, new sets of correction coefficients can be predicted, further improving the accuracy and reliability of wind turbine aerodynamic load predictions.

[0097] In some possible implementations, to meet real-time requirements, a collaborative architecture between edge computing and the cloud can be employed. A lightweight correction coefficient prediction model is deployed at the edge computing layer. Using real-world results from a past period (e.g., ten minutes), corresponding environmental parameter data, and aerodynamic time series as input, the lightweight correction coefficient prediction model can quickly predict the correction coefficient for the next moment. This real-time prediction can provide a basis for timely adjustments to the wind turbine control strategy, improving the turbine's adaptability to environmental changes.

[0098] Here, the cloud platform aggregates edge data every 24 hours. This edge data contains a wealth of actual operational information and prediction results. The cloud platform uses this rich data to retrain the full-parameter model. The full-parameter model has a more complex structure and stronger learning capabilities, further exploring potential patterns in the data. After training is complete, the optimized model parameters are synchronized to the local device via wireless updates, forming a collaborative architecture of "real-time response at the edge and deep optimization in the cloud." This architecture ensures the system's real-time performance while fully leveraging the cloud's powerful computing power and abundant data resources to continuously improve the performance of the correction coefficient prediction model.

[0099] In some other embodiments, during the engineering deployment phase, the optimized correction coefficients are stored in a three-dimensional lookup table, categorized by wind speed, yaw angle, and turbulence intensity. Independent parameter groups are configured for each 1 m / s wind speed interval. This tiered storage method allows for a more detailed description of the correction coefficients under different operating conditions, improving the model's adaptability to various operating conditions. The dynamic coefficient table is integrated into the wind turbine master control system via the Modbus / TCP protocol, enabling seamless integration with the wind turbine control system and providing real-time guidance for pitch and yaw control strategies.

[0100] For example, under sudden wind speed changes, the edge model can automatically lower the Glauert critical threshold and increase the correction strength upon detecting a sudden increase in wind speed. This adjustment can reduce thrust prediction errors, trigger pitch protection earlier, and prevent damage to the wind turbine due to excessive thrust. During continuous yaw, the lateral inflow correction model can compress torque prediction deviations, allowing the wind turbine to more accurately adjust pitch and yaw angles, improving power generation efficiency and achieving efficient and stable operation of the wind turbine.

[0101] The method, device, medium and equipment for dynamic correction of the aerodynamic load of a wind turbine provided in the embodiments of the present disclosure obtain a correction coefficient set by utilizing sensor data and a trained correction coefficient prediction model, and dynamically correct the aerodynamic load of the wind turbine based on the correction coefficient set and a standard blade element momentum theoretical model, so as to continuously optimize the performance of the turbine in complex environments and different operating conditions, thereby improving the operating safety and power generation efficiency of the wind turbine.

[0102] Those skilled in the art will understand that in the above-mentioned method of the specific implementation method, the writing order of each step does not mean a strict execution order and does not constitute any limitation on the implementation process. The specific execution order of each step should be determined by its function and possible internal logic.

[0103] Based on the same inventive concept, the embodiment of the present disclosure also provides a dynamic correction device for the aerodynamic load of a wind turbine set corresponding to the dynamic correction method for the aerodynamic load of a wind turbine set. Since the principle of solving the problem by the device in the embodiment of the present disclosure is similar to the dynamic correction method for the aerodynamic load of a wind turbine set in the above-mentioned embodiment of the present disclosure, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0104] Reference Figure 6 FIG. 1 is a schematic diagram of a dynamic correction device 600 for aerodynamic loads of a wind turbine provided by an embodiment of the present disclosure, the device comprising:

[0105] The data acquisition module 601 is configured to collect sensor data about the target wind turbine generator system based on sensors pre-installed in the target wind turbine generator system; wherein the sensor data includes structural load data, environmental parameter data, and operating status data;

[0106] A sequence generation module 602 is configured to perform reverse calculation of the aerodynamic thrust and torque of each blade element using the blade finite element model and the blade natural frequency of the target wind turbine in combination with the structural load data to generate an aerodynamic time series;

[0107] A coefficient prediction module 603 is configured to input the aerodynamic time series, the environmental parameter data, and the operating status data into a trained correction coefficient prediction model, and predict a correction coefficient set based on the trained correction coefficient prediction model to obtain a predicted correction coefficient set;

[0108] The result correction module 604 is configured to configure the predicted correction coefficient set to the standard blade element momentum theoretical model, and determine a dynamically corrected aerodynamic load result based on the coefficient-configured standard blade element momentum theoretical model, the sensor data, and the aerodynamic force time series.

[0109] In some possible embodiments, the structural load data includes blade root bending moment and tower vibration acceleration; the environmental parameter data includes wind speed and turbulence intensity; and the operating status data includes yaw angle.

[0110] In some possible embodiments, the sequence generation module 602 is specifically configured to:

[0111] Establishing a finite element model of blades of the target wind turbine generator set, and performing modal analysis on the blade finite element model to obtain the natural frequency of each blade of the target wind turbine generator set;

[0112] The aerodynamic thrust and torque of each blade element are inversely calculated based on the natural frequency of each blade, the bending moment at the blade root, and the tower vibration acceleration to generate the aerodynamic force time series.

[0113] In some possible embodiments, reference Figure 7 As shown, the device also includes:

[0114] A model building module 605 is used to build a standard blade element momentum theory model;

[0115] A data acquisition module 606 is configured to acquire a correction coefficient prediction model to be trained and a training data set; wherein the training data set includes multiple training data subsets, each training data subset includes multiple time series data, and each time series data includes aerodynamic force training data, environmental parameter training data, and operating status training data at a corresponding moment;

[0116] The model training module 607 is configured to train the correction coefficient prediction model to be trained based on the training data set and the standard blade element momentum theoretical model to obtain the trained correction coefficient prediction model.

[0117] In some possible embodiments, the model training module 607 is specifically used to:

[0118] For each training data subset, determining a training prediction correction coefficient set corresponding to the training data subset based on the correction coefficient prediction model to be trained and the training data subset; configuring the standard blade element momentum theoretical model based on the training prediction correction coefficient set; and determining a training aerodynamic load result corresponding to the training data subset based on the configured standard blade element momentum theoretical model and the training data subset;

[0119] Determining a loss value between the training aerodynamic load result corresponding to the training data subset and the sample label corresponding to the training data subset based on a preset loss function, and adjusting model parameters of the correction coefficient prediction model to be trained based on the loss value;

[0120] Repeat the above steps until the training results meet the preset requirements, and obtain the trained correction coefficient prediction model.

[0121] In some possible embodiments, the model training module 607 is specifically used to:

[0122] When the wind speed corresponding to the training data subset is higher than a preset wind speed threshold, the training data subset is determined to be in a high wind speed condition, and the optimization weight of the Glaurus critical induction factor threshold is increased to suppress the influence of the wake turbulence effect on the load prediction;

[0123] When the yaw angle corresponding to the training data subset is higher than a preset yaw angle threshold, the training data subset is determined to be in a large yaw angle operating condition, the torque deviation caused by the skew flow is compensated by modifying the lateral velocity distribution, and the rotation enhancement coefficient is updated based on the correlation between the blade element position and the rotation speed to optimize the boundary layer stability of the yaw airflow due to the rotation effect;

[0124] When the turbulence intensity corresponding to the training data subset is higher than a preset turbulence intensity threshold, the training data subset is determined to be in a transient strong turbulence condition, a time lag coefficient is introduced to simulate the time-varying effect of a sudden change in the angle of attack on the lift coefficient, and the rotation enhancement coefficient is adjusted according to the instantaneous change in turbulence intensity to balance the effects of the rotational mixing effect and the airflow disturbance;

[0125] During the parameter adjustment process, based on the sensitivity of the tip loss correction factor to the thrust prediction, the tip loss correction factor is optimized first, and then other correction coefficients are adjusted iteratively.

[0126] In some possible embodiments, the result correction module 604 is further configured to:

[0127] Acquire a real result corresponding to the sensor data and having the same time length as the dynamically corrected aerodynamic load result, and construct a model optimization sample set based on the environmental parameter data, the operating status data, the aerodynamic force time series, and the real result;

[0128] The correction coefficient prediction model is optimized and trained based on the model optimization sample set and the standard blade element momentum theoretical model, so as to realize the prediction of a new correction coefficient set by using the correction coefficient prediction model after optimization training.

[0129] Based on the same technical concept, the embodiment of the present disclosure also provides a computer device. Figure 8 800 according to an embodiment of the present disclosure, including a processor 801, a memory 802, and a bus 803. The memory 802 is used to store execution instructions and includes a memory 8021 and an external memory 8022. The memory 8021 is also referred to as internal memory and is used to temporarily store calculation data in the processor 801 and data exchanged with an external memory 8022, such as a hard disk. The processor 801 exchanges data with the external memory 8022 through the memory 8021.

[0130] In the embodiment of the present application, the memory 802 is specifically used to store application code for executing the solution of the present application, and the execution is controlled by the processor 801. That is, when the computer device 800 is running, the processor 801 communicates with the memory 802 via the bus 803, so that the processor 801 executes the application code stored in the memory 802, thereby performing the method described in any of the aforementioned embodiments.

[0131] Among them, the memory 802 can be, but is not limited to, random access memory (RAM), read only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), etc.

[0132] The processor 801 may be an integrated circuit chip with signal processing capabilities. The above-mentioned processor may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention can be implemented or executed. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0133] It should be understood that the structure illustrated in the embodiments of the present application does not constitute a specific limitation on the computer device 800. In other embodiments of the present application, the computer device 800 may include more or fewer components than shown, or may combine or separate certain components, or arrange the components differently. The components shown in the illustrations may be implemented in hardware, software, or a combination of software and hardware.

[0134] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon. When executed by a processor, the computer program executes the steps of the method for dynamically correcting aerodynamic loads on a wind turbine as described in the above method embodiment. The storage medium may be a volatile or non-volatile computer-readable storage medium.

[0135] An embodiment of the present disclosure also provides a computer program product, which carries program code. The instructions included in the program code can be used to execute the steps of the dynamic correction method of the aerodynamic load of the wind turbine set described in the above method embodiment. For details, please refer to the above method embodiment and will not be repeated here.

[0136] The computer program product may be implemented in hardware, software, or a combination thereof. In one embodiment, the computer program product is implemented as a computer storage medium. In another embodiment, the computer program product is implemented as a software product, such as a software development kit (SDK).

[0137] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present disclosure, it should be understood that the disclosed system and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0138] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0139] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0140] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present disclosure, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present disclosure. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0141] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present disclosure, which are used to illustrate the technical solutions of the present disclosure, rather than to limit them. The scope of protection of the present disclosure is not limited thereto. Although the present disclosure has been described in detail with reference to the above-described embodiments, those skilled in the art should understand that any person skilled in the art can modify or easily conceive of changes to the technical solutions described in the above-described embodiments within the technical scope disclosed in the present disclosure, or replace some of the technical features therein with equivalents. Such modifications, changes, or replacements do not deviate from the spirit and scope of the technical solutions of the embodiments of the present disclosure, and should be included in the scope of protection of the present disclosure. Therefore, the scope of protection of the present disclosure shall be subject to the scope of protection of the claims.

Claims

1. A method for dynamic correction of aerodynamic load of a wind turbine generator set, characterized in that: include: Collecting sensor data about the target wind turbine generator set based on sensors pre-installed in the target wind turbine generator set; wherein the sensor data includes structural load data, environmental parameter data and operating status data; Using the blade finite element model and the blade natural frequency of the target wind turbine, combined with the structural load data, the aerodynamic thrust and torque of each blade element are reversely calculated to generate an aerodynamic time series; Inputting the aerodynamic time series, the environmental parameter data, and the operating status data into a trained correction coefficient prediction model, and predicting a correction coefficient set based on the trained correction coefficient prediction model to obtain a predicted correction coefficient set; The prediction correction coefficient set is configured to a standard blade element momentum theoretical model, and a dynamically corrected aerodynamic load result is determined based on the standard blade element momentum theoretical model after the coefficient configuration, the sensor data, and the aerodynamic force time series.

2. The method according to claim 1, characterized in that The structural load data includes blade root bending moment and tower vibration acceleration; the environmental parameter data includes wind speed and turbulence intensity; and the operating status data includes yaw angle.

3. The method according to claim 2, characterized in that The reverse calculation of the aerodynamic thrust and torque of each blade element using the blade finite element model and the blade natural frequency of the target wind turbine in combination with the structural load data includes: Establishing a finite element model of blades of the target wind turbine generator set, and performing modal analysis on the blade finite element model to obtain the natural frequency of each blade of the target wind turbine generator set; The aerodynamic thrust and torque of each blade element are inversely calculated based on the natural frequency of each blade, the bending moment at the blade root, and the tower vibration acceleration to generate the aerodynamic force time series.

4. The method according to claim 2, characterized in that The correction coefficient prediction model is trained by the following steps: Construct a standard blade element momentum theory model; Obtaining a correction coefficient prediction model to be trained and a training data set; wherein the training data set includes multiple training data subsets, each training data subset includes multiple time series data, and each time series data includes aerodynamic training data, environmental parameter training data, and operating status training data at a corresponding moment; The correction coefficient prediction model to be trained is trained based on the training data set and the standard blade element momentum theoretical model to obtain the trained correction coefficient prediction model.

5. The method according to claim 4, characterized in that The training of the correction coefficient prediction model to be trained based on the training data set and the standard blade element momentum theoretical model includes: For each training data subset, determining a training prediction correction coefficient set corresponding to the training data subset based on the correction coefficient prediction model to be trained and the training data subset; configuring the standard blade element momentum theoretical model based on the training prediction correction coefficient set; and determining a training aerodynamic load result corresponding to the training data subset based on the configured standard blade element momentum theoretical model and the training data subset; Determining a loss value between the training aerodynamic load result corresponding to the training data subset and the sample label corresponding to the training data subset based on a preset loss function, and adjusting model parameters of the correction coefficient prediction model to be trained based on the loss value; Repeat the above steps until the training results meet the preset requirements, and obtain the trained correction coefficient prediction model.

6. The method according to claim 5, characterized in that The adjusting the model parameters of the correction coefficient prediction model to be trained based on the loss value includes: When the wind speed corresponding to the training data subset is higher than a preset wind speed threshold, the training data subset is determined to be in a high wind speed condition, and the optimization weight of the Glaurus critical induction factor threshold is increased to suppress the influence of the wake turbulence effect on the load prediction; When the yaw angle corresponding to the training data subset is higher than a preset yaw angle threshold, the training data subset is determined to be in a large yaw angle operating condition, the torque deviation caused by the skew flow is compensated by modifying the lateral velocity distribution, and the rotation enhancement coefficient is updated based on the correlation between the blade element position and the rotation speed to optimize the boundary layer stability of the yaw airflow due to the rotation effect; When the turbulence intensity corresponding to the training data subset is higher than a preset turbulence intensity threshold, the training data subset is determined to be in a transient strong turbulence condition, a time lag coefficient is introduced to simulate the time-varying effect of a sudden change in the angle of attack on the lift coefficient, and the rotation enhancement coefficient is adjusted according to the instantaneous change in turbulence intensity to balance the effects of the rotational mixing effect and the airflow disturbance; During the parameter adjustment process, based on the sensitivity of the tip loss correction factor to the thrust prediction, the tip loss correction factor is optimized first, and then other correction coefficients are adjusted iteratively.

7. The method according to claim 1, characterized in that After determining the dynamically corrected aerodynamic load result based on the coefficient-configured standard blade element momentum theoretical model, the sensor data, and the aerodynamic force time series, the method further includes: Acquire a real result corresponding to the sensor data and having the same time length as the dynamically corrected aerodynamic load result, and construct a model optimization sample set based on the environmental parameter data, the operating status data, the aerodynamic force time series, and the real result; The correction coefficient prediction model is optimized and trained based on the model optimization sample set and the standard blade element momentum theoretical model, so as to realize the prediction of a new correction coefficient set by using the correction coefficient prediction model after optimization training.

8. A dynamic correction device for aerodynamic load of a wind turbine, characterized in that: include: A data acquisition module, configured to collect sensor data about a target wind turbine generator set based on sensors pre-installed in the target wind turbine generator set; wherein the sensor data includes structural load data, environmental parameter data, and operating status data; a sequence generation module for inversely calculating the aerodynamic thrust and torque of each blade element using a blade finite element model and the blade natural frequency of the target wind turbine in combination with the structural load data to generate an aerodynamic time series; a coefficient prediction module, configured to input the aerodynamic time series, the environmental parameter data, and the operating status data into a trained correction coefficient prediction model, and predict a correction coefficient set based on the trained correction coefficient prediction model to obtain a predicted correction coefficient set; The result correction module is used to configure the prediction correction coefficient set to the standard blade element momentum theoretical model, and determine the dynamically corrected aerodynamic load result based on the standard blade element momentum theoretical model after the coefficient configuration, the sensor data and the aerodynamic force time series.

9. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

10. A computer device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 7 is implemented.

Images