Maximum wind energy capture control method and system applied to wind turbine generator

Abstract

The invention provides a maximum wind energy capture control method and system applied to a wind turbine generator, and relates to the field of wind power generation, and the method comprises the steps: determining a plurality of key wind speed detection positions; establishing a multi-target tip speed ratio optimization function; based on the plurality of key wind speed detection positions, acquiring a real-time wind speed matrix, performing feature extraction, and generating a real-time wind speed feature matrix; generating a blade tip speed ratio value range and a reference blade tip speed ratio based on the real-time wind speed characteristic matrix through a blade tip speed ratio optimization model; generating a plurality of sampling tip speed ratios based on the tip speed ratio value range; calculating an optimized value of each sampling tip speed ratio through finite element analysis, a multi-target tip speed ratio optimization function and a reference tip speed ratio; the optimal tip speed ratio of the wind turbine generator is determined based on the optimal value of each sampling tip speed ratio through a genetic algorithm; according to the optimal tip speed ratio of the wind turbine generator, the wind turbine generator is controlled to capture wind energy, and the method has the advantage of improving the wind energy capture efficiency of the wind turbine generator.

Description

Technical Field

[0001] The present invention relates to the field of wind power generation, and in particular to a maximum wind energy capture control method and system applied to a wind turbine generator set. Background Art

[0002] The efficiency of wind turbines in capturing energy from natural wind is essentially determined by three major factors: the rotation rate of the wind rotor, the incoming wind speed, and the pitch angle of the blades. Among them, the core function of the variable pitch control mechanism is to dynamically adjust and limit the impeller speed to avoid mechanical failures or excessive aerodynamic noise pollution that may be caused by excessive speed. When the wind speed does not reach the rated threshold, the variable pitch system usually remains in an inactive state. At this time, the power conversion efficiency of the wind turbine is closely related to only a single variable, the tip speed ratio. Specifically, for any wind speed condition below the rated wind speed, there is an optimal impeller speed value that matches it, which can maximize the conversion efficiency of wind energy to electrical energy. Therefore, the core goal of the maximum wind energy capture control of the wind turbine is to guide the impeller speed to gradually approach this theoretically optimal speed value by accurately controlling the electromagnetic torque of the generator, thereby maximizing the wind energy capture efficiency.

[0003] The core of the existing tip speed ratio control method is to calculate the reference speed of the wind rotor based on the real-time measured wind speed data. However, in practical applications, the layout of wind speed sensors is often limited to a single measuring point such as the top of the nacelle. This limitation makes it difficult to fully capture the complex characteristics of the wind field. Factors such as wind shear effect, wake interference, turbulent characteristics of wind speed, and the dynamic response delay of the anemometer itself will significantly affect the accuracy of wind speed measurement. In addition, due to the measurement deviation caused by different installation positions, the wind speed data of a single measuring point is often difficult to truly reflect the effective wind speed distribution within the swept surface of the wind rotor, resulting in low wind energy capture efficiency of wind turbines.

[0004] Therefore, it is necessary to provide a maximum wind energy capture control method and system applied to a wind turbine generator set, so as to improve the wind energy capture efficiency of the wind turbine generator set. Summary of the invention

[0005] The present invention provides a maximum wind energy capture control method applied to a wind turbine, including: determining a plurality of key wind speed detection positions; establishing a multi-objective tip speed ratio optimization function; based on the plurality of key wind speed detection positions, obtaining a real-time wind speed matrix, wherein the real-time wind speed matrix includes a plurality of real-time wind speed vectors, one real-time wind speed vector corresponds to one key wind speed detection position, and the real-time wind speed vector includes the wind speeds of the corresponding key wind speed detection position at a plurality of time points; performing feature extraction on the real-time wind speed matrix to generate a real-time wind speed feature matrix; through a tip speed ratio optimization model, based on the real-time wind speed feature matrix, generating a tip speed ratio value range and a reference tip speed ratio; based on the tip speed ratio value range, generating a plurality of sampled tip speed ratios; through finite element analysis, the multi-objective tip speed ratio optimization function and the reference tip speed ratio, calculating the optimization value of each sampled tip speed ratio; through a genetic algorithm, based on the optimization value of each sampled tip speed ratio, determining the optimal tip speed ratio of the wind turbine; according to the optimal tip speed ratio of the wind turbine, controlling the wind turbine to capture wind energy.

[0006] Further, determining a plurality of key wind speed detection positions includes: determining a plurality of wind speed detection positions to be screened; obtaining the wind speeds of each wind speed detection position to be screened at a plurality of test time periods; based on a hill climbing search algorithm, obtaining the target tip speed ratio of the wind turbine at a plurality of test time periods; for each wind speed detection position to be screened, based on the wind speeds of the wind speed detection position to be screened at a plurality of test time periods and the target tip speed ratio of the wind turbine at a plurality of test time periods, calculating the influence coefficient of the wind speed detection position to be screened on the tip speed ratio of the wind turbine; according to the influence coefficient of each wind speed detection position to be screened on the tip speed ratio of the wind turbine, determining a plurality of key wind speed detection positions.

[0007] Further, according to the influence coefficient of each wind speed detection position to be screened on the tip speed ratio of the wind turbine, determining a plurality of key wind speed detection positions includes: according to the influence coefficient of each wind speed detection position to be screened on the tip speed ratio of the wind turbine, determining a plurality of first target wind speed detection positions from the plurality of wind speed detection positions to be screened; for any two first target wind speed detection positions, calculating the wind speed correlation coefficient of the two first target wind speed detection positions according to the wind speeds of the two first target wind speed detection positions at a plurality of test time periods; through a clustering algorithm, according to the wind speed correlation coefficient of any two first target wind speed detection positions, determining a plurality of key wind speed detection positions.

[0008] Further, through a clustering algorithm, multiple key wind speed detection positions are determined according to the wind speed correlation coefficients between any two first target wind speed detection positions, including: through a first clustering algorithm, clustering multiple first target wind speed detection positions according to the wind speed correlation coefficients between any two first target wind speed detection positions to determine multiple first position clusters, and determining multiple second target wind speed detection positions based on the cluster centers of each first position cluster; through a second clustering algorithm, clustering multiple second target wind speed detection positions according to the spatial distances between any two second target wind speed detection positions to determine multiple second position clusters; for each second position cluster, determining the key wind speed detection position corresponding to the second position cluster according to the spatial coordinates of the second target wind speed detection positions included in the second position cluster.

[0009] Further, feature extraction is performed on the real-time wind speed matrix to generate a real-time wind speed feature matrix, including: for each real-time wind speed vector, performing variational mode decomposition on the real-time wind speed vector to generate multiple frequency-modulated and amplitude-modulated signal components corresponding to the real-time wind speed vector, extracting the component features of each frequency-modulated and amplitude-modulated signal component, and generating a real-time wind speed feature sub-matrix corresponding to the real-time wind speed vector, where a row vector of the real-time wind speed feature sub-matrix represents the component feature of a frequency-modulated and amplitude-modulated signal component, and the real-time wind speed feature matrix includes the real-time wind speed feature sub-matrices corresponding to each real-time wind speed vector.

[0010] Further, the multi-objective tip speed ratio optimization function is at least related to the tip speed ratio difference, the mechanical vibration of the generator, and the power fluctuation.

[0011] Further, the optimization value of each sampled tip speed ratio is calculated through finite element analysis, the multi-objective tip speed ratio optimization function, and the reference tip speed ratio, including: based on the sampled tip speed ratio, calculating the impeller speed corresponding to the sampled tip speed ratio; through finite element analysis, generating a mechanical vibration simulation result of the generator corresponding to the sampled tip speed ratio based on the impeller speed corresponding to the sampled tip speed ratio; based on the sampled tip speed ratio, calculating the power fluctuation of the wind turbine corresponding to the sampled tip speed ratio; calculating the optimization value of the sampled tip speed ratio according to the multi-objective tip speed ratio optimization function, the sampled tip speed ratio, the reference tip speed ratio, the mechanical vibration simulation result of the generator corresponding to the sampled tip speed ratio, and the power fluctuation.

[0012] Further, through finite element analysis, generating a mechanical vibration simulation result of the generator corresponding to the sampled tip speed ratio based on the impeller speed corresponding to the sampled tip speed ratio, including: establishing a finite element model of the generator; applying boundary conditions and loads to the finite element model of the generator based on the impeller speed corresponding to the sampled tip speed ratio; solving the finite element model of the generator to generate a mechanical vibration simulation result of the generator corresponding to the sampled tip speed ratio.

[0013] Further, based on the optimized values of each sampled tip speed ratio through the genetic algorithm, the optimal tip speed ratio of the wind turbine is determined, including: S11. Selecting, crossing, and mutating multiple sampled tip speed ratios based on the optimized values of each sampled tip speed ratio, the tip speed ratio value range, and the tip speed ratio difference between each sampled tip speed ratio and the reference tip speed ratio to generate multiple sampled tip speed ratios for the current iteration round; S12. Calculating the optimized value of each sampled tip speed ratio for the current iteration round through finite element analysis, the multi-objective tip speed ratio optimization function, and the reference tip speed ratio; S13. Based on the optimized values of each sampled tip speed ratio for the current iteration round, determining whether the preset conditions are met. If not, execute S14; if so, execute S15; S14. Selecting, crossing, and mutating multiple sampled tip speed ratios for the current iteration round based on the optimized values of each sampled tip speed ratio for the current iteration round, the tip speed ratio value range, and the tip speed ratio difference between each sampled tip speed ratio for the current iteration round and the reference tip speed ratio to generate multiple sampled tip speed ratios for the next iteration round, taking the multiple sampled tip speed ratios for the next iteration round as the multiple sampled tip speed ratios for the current iteration round, and execute S12; S15. Based on the optimized values of each sampled tip speed ratio for the current iteration round, determining the optimal tip speed ratio of the wind turbine.

[0014] The present invention provides a maximum wind energy capture control system applied to a wind turbine, including: a position determination module for determining multiple key wind speed detection positions; a function establishment module for establishing a multi-objective tip speed ratio optimization function; a wind speed monitoring module for obtaining a real-time wind speed matrix based on the multiple key wind speed detection positions, where the real-time wind speed matrix includes multiple real-time wind speed vectors, one real-time wind speed vector corresponds to one key wind speed detection position, the real-time wind speed vector includes the wind speeds at multiple time points of the corresponding key wind speed detection position, and performing feature extraction on the real-time wind speed matrix to generate a real-time wind speed feature matrix; an operation optimization module for generating a tip speed ratio value range and a reference tip speed ratio based on the real-time wind speed feature matrix through a tip speed ratio optimization model, generating multiple sampled tip speed ratios based on the tip speed ratio value range; calculating the optimized value of each sampled tip speed ratio through finite element analysis, the multi-objective tip speed ratio optimization function, and the reference tip speed ratio, determining the optimal tip speed ratio of the wind turbine based on the optimized value of each sampled tip speed ratio through the genetic algorithm, and controlling the wind turbine to capture wind energy according to the optimal tip speed ratio of the wind turbine.

[0015] Compared with the prior art, the maximum wind energy capture control method and system applied to a wind turbine provided by the present invention at least have the following beneficial effects: 1. By using a multi-objective optimization function, a balance is achieved among multiple objectives such as wind energy capture efficiency, mechanical stress, and power fluctuation, rather than simply pursuing a single objective, thus avoiding mechanical overload (such as gearbox damage) or grid impact (such as severe power fluctuation) caused by the pursuit of efficiency. For example, under strong wind conditions, part of the efficiency can be sacrificed, but by reducing the pitch angle or rotational speed, the mechanical stress can be significantly reduced, and the equipment lifespan can be extended. Through multi-position wind speed detection (such as at different heights of the blade and different distances in front of the wind turbine) and feature extraction, the wind speed change can be sensed in advance. In a non-uniform wind field (such as wind shear and turbulence), traditional methods may get trapped in local optima, while the genetic algorithm can explore a wider solution space, adapt to dynamic wind conditions, and smooth the power output.

[0016] 2. By calculating the influence coefficient of the wind speed detection position to be screened on the tip speed ratio of the wind turbine, the positions that have the greatest impact on the performance of the wind turbine can be screened out. The wind speed data at these positions can better represent the wind speed change in the actual operating environment of the wind turbine. Avoid arranging sensors at positions where the wind speed change is not significant or has a small impact on the performance of the wind turbine, thereby reducing redundant data and improving the efficiency of data processing. By calculating the influence coefficient of the wind speed detection position to be screened on the tip speed ratio of the wind turbine, the influence degree of the wind speed at different positions on the tip speed ratio can be quantified. This helps to more accurately adjust the control parameters of the wind turbine to achieve more precise tip speed ratio control. Controlling based on the wind speed data at the key wind speed detection positions can reduce the control error caused by inaccurate wind speed measurement or improper position selection, and improve the power generation efficiency and stability of the wind turbine.

[0017] 3. By calculating the influence coefficient of the wind speed detection position to be screened on the tip speed ratio of the wind turbine, the positions with an influence coefficient greater than the first threshold (positive number) or less than the second threshold (negative number) are used as the first target wind speed detection positions. The wind speed change at these positions has a significant impact on the performance of the wind turbine and can more accurately reflect the wind speed change in the actual operating environment of the wind turbine. By clustering the detection positions through the wind speed correlation coefficient, the positions with similar wind speed fluctuation patterns are grouped into the same cluster. Avoid selecting redundant positions with high correlation. The most representative cluster center positions are screened out from the original large number of positions, reducing the subsequent calculation amount. In a wind farm, if the wind speeds of multiple wind turbines change synchronously due to terrain influence, only retaining the cluster center wind turbines can represent the wind speed characteristics of the area. For the cluster center positions screened in the first stage, further clustering is performed according to the spatial distance, and the clusters with geographically adjacent positions are merged. The areas with spatially adjacent and similar wind speed patterns are merged to avoid over-concentration of key positions. Ensure the uniform distribution of key positions in the wind farm to enhance the spatial representativeness. Description of the Drawings

[0018] This specification will be further described by way of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not restrictive. In these embodiments, the same reference numerals represent the same structures, where: Figure 1 is a schematic flow chart of a maximum wind energy capture control method applied to a wind turbine according to some embodiments of this specification; Figure 2 is a schematic flow chart of determining multiple key wind speed detection positions according to some embodiments of this specification; Figure 3 is a schematic flow chart of determining the optimal tip speed ratio of a wind turbine according to some embodiments of this specification; Figure 4 is a schematic module diagram of a maximum wind energy capture control system applied to a wind turbine according to some embodiments of this specification. Detailed implementation manners

[0019] To more clearly illustrate the technical solutions of the embodiments of this specification, the accompanying drawings required for the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings in the following description are only some examples or embodiments of this specification. For those of ordinary skill in the art, without creative efforts, this specification can also be applied to other similar scenarios according to these drawings. Unless obvious from the language context or otherwise stated, the same reference numerals in the figures represent the same structures or operations.

[0020] Figure 1 is a schematic flow chart of a maximum wind energy capture control method applied to a wind turbine according to some embodiments of this specification, as Figure 1 shown, the maximum wind energy capture control method applied to a wind turbine may include the following processes.

[0021] Step 110, determine multiple key wind speed detection positions.

[0022] Figure 2 is a schematic flow chart of determining multiple key wind speed detection positions according to some embodiments of this specification, as Figure 2 shown, step 110 specifically includes: Determine multiple wind speed detection positions to be screened; Obtain the wind speed at each wind speed detection position to be screened in multiple test time periods, where the wind speed at a wind speed detection position to be screened in a certain test time period may include the wind speeds at multiple test time points in this test time period; Based on the hill climbing search algorithm, obtain the target tip speed ratio of the wind turbine in multiple test time periods; For each wind speed detection position to be screened, based on the wind speed at the wind speed detection position to be screened in multiple test time periods and the target tip speed ratio of the wind turbine in multiple test time periods, calculate the influence coefficient of the wind speed detection position to be screened on the tip speed ratio of the wind turbine; Determine multiple key wind speed detection positions according to the influence coefficient of each wind speed detection position to be screened on the tip speed ratio of the wind turbine.

[0023] Specifically, multiple wind speed detection positions to be screened need to cover the key spatial characteristics of the wind field around the wind turbine, including: 1. Height coverage: Include the hub height (typical value: 80 - 120m) and a certain range above and below (such as ±20m) to capture the vertical wind shear effect.

[0024] 2. Horizontal distribution: Cover the upstream (such as 1D - 5D, where D is the impeller diameter), lateral, and downstream areas of the unit to reflect the effects of wind field turbulence, wake, etc.

[0025] 3. Terrain correlation: In complex terrains (such as mountains and hills), points need to be arranged at typical positions such as ridges, valleys, and windward slopes.

[0026] Example: Horizontal direction: Arrange one wind speed detection position to be screened at 2D, 3D, and 4D upstream of the unit respectively.

[0027] Vertical direction: Arrange wind speed detection positions to be screened at the hub height, hub height + 10m, and hub height - 15m.

[0028] The positions to be screened need to meet the requirements of the wind turbine operation safety and data reliability: 1. No occlusion: Avoid occlusion by buildings, trees, etc. to ensure accurate wind speed measurement.

[0029] 2. Away from interference sources: At least 3D away from the wake area of other units to avoid wake effect interference.

[0030] 3. Mechanical accessibility: Facilitate the installation and maintenance of wind speed sensors (such as lidar, ultrasonic anemometer).

[0031] Principle of the Hill-Climbing Search method: By continuously disturbing the impeller speed and observing the change in output power, gradually approach the maximum power point.

[0032] Implementation method of the Hill-Climbing Search method: Periodically apply small disturbances (increase or decrease the speed) to the impeller speed.

[0033] Observe the change in output power: If the power increases, continue to perturb the rotational speed in the same direction.

[0034] If the power decreases, perturb the rotational speed in the reverse direction.

[0035] Repeat the above process until the difference between the output power and the maximum power point is less than the preset power difference, and then back-calculate the target tip speed ratio based on the impeller rotational speed at this time.

[0036] For example, the target tip speed ratio can be back-calculated according to the following formula: , where, is the target tip speed ratio, is the impeller rotational speed, is the impeller radius, is the average wind speed at the t-th test time point, which can be the mean value of the wind speeds at multiple wind speed detection positions to be screened at the t-th test time point.

[0037] For each test time period, the standard deviation of the wind speed at the wind speed detection position to be screened in this test time period can be calculated according to the wind speed at the wind speed detection position to be screened at this test time point. The standard deviation of the target tip speed ratio in this test time period can be calculated according to the target tip speed ratio of the wind turbine in this test time period. According to the calculation formula of the non-linear correlation coefficient (such as the maximum information coefficient, distance correlation coefficient, Spearman rank correlation coefficient, etc.), the non-linear correlation coefficient between the wind speed at the wind speed detection position to be screened in multiple test time periods and the standard deviation of the target tip speed ratio is calculated as the influence coefficient of the wind speed at the wind speed detection position to be screened on the target tip speed ratio of the wind turbine.

[0038] It can be understood that by calculating the influence coefficient of the wind speed at the wind speed detection position to be screened on the target tip speed ratio of the wind turbine, the positions with the greatest influence on the performance of the wind turbine can be screened out. The wind speed data at these positions can better represent the wind speed changes in the actual operating environment of the wind turbine. Avoid arranging sensors at positions where the wind speed change is not significant or the influence on the performance of the wind turbine is small, thereby reducing redundant data and improving the efficiency of data processing. By calculating the influence coefficient of the wind speed at the wind speed detection position to be screened on the target tip speed ratio of the wind turbine, the influence degree of the wind speed at different positions on the tip speed ratio can be quantified. This helps to more accurately adjust the control parameters of the wind turbine to achieve more precise control of the tip speed ratio. Controlling based on the wind speed data at the key wind speed detection positions can reduce the control error caused by inaccurate wind speed measurement or improper position selection, and improve the power generation efficiency and stability of the wind turbine.

[0039] Preferably, multiple key wind speed detection positions are determined according to the influence coefficient of the wind speed at each wind speed detection position to be screened on the target tip speed ratio of the wind turbine, including: According to the tip speed ratio influence coefficients of each wind speed detection position to be screened on the wind turbine, multiple first target wind speed detection positions are determined from multiple wind speed detection positions to be screened. For example, the wind speed detection positions to be screened with tip speed ratio influence coefficients greater than the first threshold or less than the second threshold are used as the first target wind speed detection positions, where the first threshold is a positive number and the second threshold is a negative number; For any two first target wind speed detection positions, according to the wind speeds of the two first target wind speed detection positions in multiple test time periods, the wind speed correlation coefficient between the two first target wind speed detection positions is calculated; Through a clustering algorithm, multiple key wind speed detection positions are determined according to the wind speed correlation coefficients of any two first target wind speed detection positions.

[0040] Specifically, for any two first target wind speed detection positions, through the calculation formula of the non - linear correlation coefficient (such as the maximum information coefficient, distance correlation coefficient, Spearman rank correlation coefficient, etc.), according to the standard deviations of the wind speeds of the two first target wind speed detection positions in multiple test time periods, the non - linear correlation coefficient of the wind speeds of the two first target wind speed detection positions is calculated as the wind speed correlation coefficient between the two first target wind speed detection positions.

[0041] Preferably, through a clustering algorithm, multiple key wind speed detection positions are determined according to the wind speed correlation coefficients of any two first target wind speed detection positions, including: Through the first clustering algorithm (such as K - Means, agglomerative hierarchical clustering algorithm, etc.), according to the wind speed correlation coefficients of any two first target wind speed detection positions, the multiple first target wind speed detection positions are clustered to determine multiple first position clusters. Based on the cluster centers of each first position cluster, multiple second target wind speed detection positions are determined. For example, the first target wind speed detection position corresponding to the cluster center of the first position cluster can be used as the second target wind speed detection position; Through the second clustering algorithm (such as K - Means, agglomerative hierarchical clustering algorithm, etc.), according to the spatial distances of any two second target wind speed detection positions, the multiple second target wind speed detection positions are clustered to determine multiple second position clusters; For each second position cluster, according to the spatial coordinates of the second target wind speed detection positions included in the second position cluster, the key wind speed detection position corresponding to the second position cluster is determined. For example, the mean value of the spatial coordinates of the second target wind speed detection positions included in the second position cluster can be calculated as the key wind speed detection position corresponding to the second position cluster.

[0042] It can be understood that by calculating the influence coefficient of the tip speed ratio of the wind turbine at the wind speed detection positions to be screened, the positions where the influence coefficient is greater than the first threshold (positive number) or less than the second threshold (negative number) are used as the first target wind speed detection positions. The wind speed changes at these positions have a significant impact on the performance of the wind turbine and can more accurately reflect the wind speed changes in the actual operating environment of the wind turbine. By clustering the detection positions through the wind speed correlation coefficient, the positions with similar wind speed fluctuation patterns are grouped into the same cluster. Redundant positions with high correlation are avoided. The most representative cluster center positions are selected from the original large number of positions to reduce the subsequent calculation amount. In a wind farm, if the wind speeds of multiple wind turbines change synchronously due to terrain effects, only the cluster center wind turbines need to be retained to represent the wind speed characteristics of the area. For the cluster center positions screened in the first stage, they are further clustered according to the spatial distance, and the clusters with adjacent geography are merged. The regions with adjacent space and similar wind speed patterns are merged to avoid over-concentration of key positions. Ensure that the key positions are evenly distributed in the wind farm to enhance the spatial representativeness.

[0043] Step 120, establish a multi-objective tip speed ratio optimization function.

[0044] Preferably, the multi-objective tip speed ratio optimization function is at least related to the tip speed ratio difference, the mechanical vibration of the generator, and the power fluctuation.

[0045] Step 130, based on multiple key wind speed detection positions, obtain a real-time wind speed matrix.

[0046] Among them, the real-time wind speed matrix includes multiple real-time wind speed vectors. One real-time wind speed vector corresponds to one key wind speed detection position, and the real-time wind speed vector includes the wind speeds of the corresponding key wind speed detection position at multiple time points.

[0047] Step 140, perform feature extraction on the real-time wind speed matrix to generate a real-time wind speed feature matrix.

[0048] Specifically, it includes: For each real-time wind speed vector, perform variational mode decomposition on the real-time wind speed vector to generate multiple frequency-modulated and amplitude-modulated signal components corresponding to the real-time wind speed vector, extract the component features of each frequency-modulated and amplitude-modulated signal component, and generate a real-time wind speed feature sub-matrix corresponding to the real-time wind speed vector. Among them, one row vector of the real-time wind speed feature sub-matrix represents the component features of a frequency-modulated and amplitude-modulated signal component, and the real-time wind speed feature matrix includes the real-time wind speed feature sub-matrices corresponding to each real-time wind speed vector.

[0049] Specifically, variational mode decomposition is an adaptive signal decomposition method that can decompose a complex signal into multiple frequency-modulated and amplitude-modulated intrinsic mode functions (frequency-modulated and amplitude-modulated signal components). Its core idea is to determine the center frequency and bandwidth of each frequency-modulated and amplitude-modulated signal component by iteratively searching for the optimal solution of the variational model, so as to achieve the frequency-domain dissection and effective separation of the signal.

[0050] Non - recursive and adaptive: Variational mode decomposition determines the center frequencies and bandwidths of the frequency - modulated and amplitude - modulated signal components through iterative optimization, avoiding the mode mixing problem in empirical mode decomposition.

[0051] Construction of variational problem: Assume that each frequency - modulated and amplitude - modulated signal component is a finite - bandwidth signal with different center frequencies. By minimizing the sum of the bandwidths of all frequency - modulated and amplitude - modulated signal components and the error between them and the original signal, a variational problem is constructed.

[0052] Optimization and solution: Use optimization algorithms such as the alternating direction method of multipliers to solve the variational problem, continuously update the parameters of the frequency - modulated and amplitude - modulated signal components (such as center frequency, amplitude, and phase), and gradually approach the optimal solution.

[0053] The variational mode decomposition can be performed on the real - time wind speed vector according to the following steps to generate multiple frequency - modulated and amplitude - modulated signal components corresponding to the real - time wind speed vector, and extract the component features of each frequency - modulated and amplitude - modulated signal component: S21. Data preparation: Obtain the real - time wind speed vector data to ensure the integrity and continuity of the data.

[0054] S22. Setting of variational mode decomposition parameters: Number of modes: Determines the number of frequency - modulated and amplitude - modulated signal components decomposed, and needs to be reasonably set according to the complexity of the wind speed signal.

[0055] Penalty parameter: Controls the bandwidth of the frequency - modulated and amplitude - modulated signal components and balances the separation degree between modes.

[0056] Convergence criterion tolerance: Sets the conditions for stopping the iteration, such as reaching the maximum number of iterations or the residual signal energy being lower than the threshold.

[0057] S23. Variational mode decomposition: Input the real - time wind speed vector into the variational mode decomposition algorithm and decompose it into K frequency - modulated and amplitude - modulated signal components through iterative optimization. Each frequency - modulated and amplitude - modulated signal component represents a specific frequency component in the wind speed signal and has frequency - modulated and amplitude - modulated characteristics.

[0058] S24. Extraction of component features For each frequency - modulated and amplitude - modulated signal component obtained by decomposition, extract the following features to describe its time - frequency characteristics: 1. Center frequency: Definition: The main frequency component of the frequency - modulated and amplitude - modulated signal component in the frequency domain.

[0059] Significance: Reflects the distribution of different frequency components in the wind speed signal.

[0060] 2. Bandwidth: Definition: The frequency range of the frequency modulation and amplitude modulation signal components in the frequency domain.

[0061] Significance: Describes the fluctuation range of different frequency components in the wind speed signal.

[0062] 3. Instantaneous amplitude: Definition: The amplitude change of the frequency modulation and amplitude modulation signal components in the time domain.

[0063] Significance: Reflects the intensity change of different frequency components in the wind speed signal.

[0064] 4. Instantaneous frequency: Definition: The frequency change of the frequency modulation and amplitude modulation signal components in the time domain.

[0065] Significance: Describes the time-varying characteristics of different frequency components in the wind speed signal.

[0066] 5. Energy: Definition: The energy magnitude of the frequency modulation and amplitude modulation signal components in the time domain or frequency domain.

[0067] Significance: Quantifies the energy contribution of different frequency components in the wind speed signal.

[0068] It can be understood that variational mode decomposition can effectively separate different frequency components (such as turbulence, gusts, etc.) in the wind speed signal, facilitating subsequent analysis. By adaptively determining the center frequency and bandwidth of the mode components, variational mode decomposition can provide higher time-frequency resolution and more accurately describe the dynamic characteristics of the wind speed signal. Variational mode decomposition can still accurately identify signal features under noise interference and is suitable for wind speed monitoring in complex environments.

[0069] Step 150, through the tip speed ratio optimization model, based on the real-time wind speed characteristic matrix, generate the tip speed ratio value range and the reference tip speed ratio.

[0070] Among them, the tip speed ratio value range can be the possible value range of the tip speed ratio for the real-time wind speed characteristic matrix, and the reference tip speed ratio can be the tip speed ratio corresponding to the maximum wind energy capture of the real-time wind speed characteristic matrix. The tip speed ratio optimization model can be a Convolutional Neural Networks (CNN) model.

[0071] The model architecture of the tip speed ratio optimization model can include: Input layer: The real-time wind speed characteristic matrix (such as a 32×32 two-dimensional matrix) and the tip speed ratio influence coefficient of each key wind speed detection position on the wind turbine.

[0072] Convolutional layer: Multi-layer convolution (such as a 3x3 convolution kernel) extracts the spatial features of wind speed (such as wind speed gradient, turbulence pattern).

[0073] Pooling layer: Max pooling or average pooling reduces the feature dimension and enhances the robustness of the model.

[0074] Fully connected layer: Maps the convolution features to the range of tip speed ratios and the reference tip speed ratio.

[0075] Output layer: Two output branches: Range of tip speed ratios: The lower and upper limits of the output range.

[0076] Reference tip speed ratio: The tip speed ratio that outputs the maximum wind energy capture corresponding to the current wind condition.

[0077] The tip speed ratio optimization model has the following constraints: 1. Maximum rotational speed constraint: The mechanical strength of the wind turbine blades and the drive system (such as gearbox, generator) is limited. When the rotational speed is too high, the blades may deform or break due to excessive centrifugal force, and the drive system may also be damaged due to overload. The maximum rotational speed is determined by the design parameters of the wind turbine (such as material strength, blade length, mass distribution, etc.) and is a hard constraint for the safe operation of the wind turbine.

[0078] 2. Grid power constraint: The output power of the wind turbine is closely related to the wind speed, tip speed ratio, and pitch angle (β). When the wind speed is too high, the wind turbine may reach the rated power or even exceed the maximum power allowed by the grid. Exceeding the maximum power allowed by the grid may cause grid voltage fluctuations, frequency instability, and even damage to grid equipment.

[0079] 3. Vibration constraint: The vibration of the wind turbine blades and the tower may cause fatigue damage and reduce the equipment life. Excessive vibration will trigger the protection mechanism and even cause shutdown.

[0080] Step 160, generate multiple sampled tip speed ratios based on the range of tip speed ratios.

[0081] For example, randomly extract multiple sampled tip speed ratios from the range of tip speed ratios.

[0082] Step 170, calculate the optimized value of each sampled tip speed ratio through finite element analysis, multi-objective tip speed ratio optimization function, and reference tip speed ratio.

[0083] Specifically include: Based on the sampled tip speed ratio, calculate the impeller rotational speed corresponding to the sampled tip speed ratio; Generate mechanical vibration simulation results of the generator corresponding to the sampled tip speed ratio based on the impeller speed corresponding to the sampled tip speed ratio through finite element analysis; Based on the sampled blade tip speed ratio, the power fluctuation of the wind turbine corresponding to the sampled blade tip speed ratio is calculated; The optimized value of the sampled tip speed ratio is calculated according to the multi-objective tip speed ratio optimization function, the sampled tip speed ratio, the reference tip speed ratio, the mechanical vibration simulation results of the generator corresponding to the sampled tip speed ratio, and the power fluctuation.

[0084] Preferably, the mechanical vibration simulation result of the generator corresponding to the sampled tip speed ratio is generated based on the impeller speed corresponding to the sampled tip speed ratio through finite element analysis, including: Establish a finite element model of the generator; Apply boundary conditions and loads to the finite element model of the generator based on the impeller speed corresponding to the sampled tip speed ratio; The finite element model of the generator is solved to generate the mechanical vibration simulation results of the generator corresponding to the sampled tip speed ratios.

[0085] Specifically, the following processes may be included: S31. Establish the finite element model of the generator Modeling objects: key components of the generator (such as rotor, stator, bearings, gearbox, main shaft, etc.), with special attention paid to structures that may cause vibration (such as rotor imbalance, gear meshing excitation, etc.).

[0086] Modeling method: Use CAD software to build a three-dimensional geometric model of the generator and simplify non-critical structures (such as bolts, small holes, etc.).

[0087] Meshing: Use finite element pre-processing software to mesh and select the appropriate unit type: solid units (such as tetrahedron and hexahedron units) are used for solid structures such as rotors and stators. Shell units are used for thin-walled structures (such as casings). Beam units are used for slender structures such as spindles.

[0088] Mesh density control: Increase mesh density near vibration excitation sources (such as gear meshing surfaces and bearing contact surfaces). Appropriately reduce mesh density in non-critical areas.

[0089] Material property definition: Define the material properties of each component (such as elastic modulus, Poisson's ratio, density, damping ratio, etc.).

[0090] S32. Apply boundary conditions and loads Boundary conditions: Fixed constraint: Apply full constraints (fix all degrees of freedom) to the fixed end of the generator (such as the flange connected to the tower).

[0091] Contact Definition: Define the contact relationship between the bearing and the shaft (such as frictional contact or frictionless contact). Define the contact relationship between the gear meshing surfaces.

[0092] Load Application: Rotational Speed Load: Calculate the rotational speed of the impeller based on the sampled tip speed ratio and convert it to the angular velocity of the rotor. In the finite element model, apply the rotational speed load through rotational boundary conditions or inertial force loading: Rotational Boundary Conditions: Directly apply the angular velocity on the rotor surface.

[0093] Inertial Force Loading: Calculate the centrifugal force generated by the rotor during rotation and apply it as a body load to the rotor elements.

[0094] Unbalance Excitation: Simulate the rotor mass unbalance or directly apply an equivalent periodic force at the rotor mass center.

[0095] Gear Meshing Excitation: Simulate the dynamic loads during gear meshing (such as time-varying mesh stiffness, meshing impact), and achieve it by applying periodic force or displacement excitation.

[0096] Gravity Load: Apply the gravitational acceleration in the vertical direction.

[0097] S33, Solution and Post-processing Solution Settings: Analysis Type: Modal Analysis: Calculate the natural frequencies and vibration modes of the generator, and identify possible resonance frequencies. Harmonic Response Analysis: Analyze the steady-state vibration response (such as displacement, acceleration) of the generator under harmonic excitation. Transient Dynamics Analysis: Analyze the vibration response of the generator under non-steady excitation (such as startup, shutdown, load mutation).

[0098] Solver Selection: Modal Superposition Method.

[0099] Post-processing: Vibration Response Extraction: Extract the vibration displacement, velocity, and acceleration time histories of multiple key nodes of the generator. Extract the frequency response function and analyze the variation of the vibration amplitude with frequency.

[0100] Based on the sampled tip speed ratio, the output power of the wind turbine corresponding to the sampled tip speed ratio can be predicted through the power prediction model. Calculate the standard deviation of the output power of the wind turbine corresponding to the predicted sampled tip speed ratio and the output power of the wind turbine at the previous m consecutive time points as the power fluctuation of the wind turbine corresponding to the sampled tip speed ratio. Specifically, through the power prediction model, based on the sampled tip speed ratio, the output power of the wind turbine corresponding to the sampled tip speed ratio is predicted, denoted as P sample , obtain the m actual output powers of the wind turbine at the previous consecutive time points, denoted asP t−1 , P t−2 ,…, P t−m , which is related to the predicted output power of the wind turbine P sample to form a power sequence P t−1 , P t−2 ,…, P t−m , P sample , calculate the power sequence according to the standard deviation calculation formula P t−1 , P t−2 ,…, P t−m , P sample The standard deviation of is used as the power fluctuation of the wind turbine corresponding to the sampled tip speed ratio. The predicted power corresponding to the sampled tip speed ratio and the output power of the wind turbine at the previous m consecutive time points together form a power sequence. The greater the difference between the individual power values in the power sequence, that is, the higher the degree of dispersion, the greater the calculated standard deviation and the greater the power fluctuation.

[0101] For example only, the multi-objective tip speed ratio optimization function is: , wherein, is the multi-objective tip speed ratio optimization function, , and are weights, , and are greater than 0, , is the sampled tip speed ratio, is the reference tip speed ratio, is the maximum amplitude of the i-th key node of the generator corresponding to the sampled tip speed ratio, is the total number of key nodes, is the power fluctuation of the wind turbine corresponding to the sampled tip speed ratio.

[0102] It can be understood that only optimizing the power coefficient may lead to excessive mechanical stress or excessive power fluctuation. Only controlling the power fluctuation may sacrifice the power generation efficiency. Through the multi-objective tip speed ratio optimization function, a balance point is found among multiple objectives (i.e., efficiency, safety, and stability).

[0103] Step 180: Based on the optimized values of each sampled tip speed ratio, determine the optimal tip speed ratio of the wind turbine by using a genetic algorithm.

[0104] Figure 3 is a schematic flow chart for determining the optimal tip speed ratio of a wind turbine according to some embodiments of this specification. As shown in Figure 3 As shown, preferably, step 180 specifically includes: S11: Based on the optimized values of each sampled tip speed ratio, the tip speed ratio value range, and the tip speed ratio difference between each sampled tip speed ratio and the reference tip speed ratio, perform selection, crossover, and mutation operations on multiple sampled tip speed ratios to generate multiple sampled tip speed ratios for the current iteration round. Specifically, retain the sampled tip speed ratios with better performance according to the optimized values (such as roulette wheel selection, tournament selection). Combine two parent sampled tip speed ratios (such as arithmetic crossover, single-point crossover) to generate offspring sampled tip speed ratios. Example: Parent sampled tip speed ratio A = 6, Parent sampled tip speed ratio B = 10, Offspring tip speed ratio = 8 (arithmetic crossover). Mutation operation: Randomly perturb some of the offspring tip speed ratios (such as adding or subtracting a small amount) to increase population diversity. Example: TSR = 8 → mutated to TSR = 8.2 (random perturbation ±0.2). For each tip speed ratio difference range, the mean value of the optimized values of the sampled tip speed ratios whose tip speed ratio differences are within this tip speed ratio difference range can be calculated. The probability that the sampled tip speed ratios in the tip speed ratio difference range with a larger mean value are retained as parents is greater. It can be understood that by calculating the mean value of the optimized values within the tip speed ratio difference range, the overall performance of the sampled tip speed ratios in different tip speed ratio difference ranges can be quantified. The selection strategy based on statistical information is more objective and accurate, which helps to find the global optimal solution; S12: Calculate the optimized values of the sampled tip speed ratios for each current iteration round through finite element analysis, multi-objective tip speed ratio optimization function, and reference tip speed ratio; S13: Based on the optimized values of the sampled tip speed ratios for each current iteration round, determine whether the preset conditions are met. For example, the change in the optimized value for multiple consecutive generations is less than the threshold, the maximum number of iterations is reached, etc. If not, execute S14; if so, execute S15; S14: Based on the optimized values of the sampled tip speed ratios for each current iteration round, the tip speed ratio value range, and the tip speed ratio difference between each sampled tip speed ratio for the current iteration round and the reference tip speed ratio, perform selection, crossover, and mutation operations on the multiple sampled tip speed ratios for the current iteration round to generate multiple sampled tip speed ratios for the next iteration round. Take the multiple sampled tip speed ratios for the next iteration round as the multiple sampled tip speed ratios for the current iteration round, and execute S12; S15: Based on the optimized values of the sampled tip speed ratios for each current iteration round, determine the optimal tip speed ratio of the wind turbine.

[0105] Step 190: Control the wind turbine to capture wind energy according to the optimal tip speed ratio of the wind turbine.

[0106] Specifically, after determining the optimal tip speed ratio of the wind turbine, it is necessary to coordinately adjust the operating state of the fan through pitch control and variable speed control to make its actual tip speed ratio as close as possible to the optimal tip speed ratio, so as to achieve the multi-objective optimization of wind energy capture efficiency.

[0107] Figure 4 It is a schematic diagram of the modules of the maximum wind energy capture control system applied to a wind turbine shown in some embodiments of this specification. As Figure 4 shown, the maximum wind energy capture control system applied to a wind turbine may include a position determination module, a function establishment module, a wind speed monitoring module, and an operation optimization module.

[0108] The position determination module is used to determine multiple key wind speed detection positions; The function establishment module is used to establish a multi-objective tip speed ratio optimization function; The wind speed monitoring module is used to obtain a real-time wind speed matrix based on multiple key wind speed detection positions. The real-time wind speed matrix includes multiple real-time wind speed vectors. One real-time wind speed vector corresponds to one key wind speed detection position. The real-time wind speed vector includes the wind speeds at multiple time points of the corresponding key wind speed detection position, and performs feature extraction on the real-time wind speed matrix to generate a real-time wind speed feature matrix; The operation optimization module is used to generate a tip speed ratio value range and a reference tip speed ratio based on the real-time wind speed feature matrix through a tip speed ratio optimization model, and generate multiple sampled tip speed ratios based on the tip speed ratio value range; calculate the optimization values of each sampled tip speed ratio through finite element analysis, the multi-objective tip speed ratio optimization function, and the reference tip speed ratio, and determine the optimal tip speed ratio of the wind turbine based on the optimization values of each sampled tip speed ratio through a genetic algorithm, and control the wind turbine to capture wind energy according to the optimal tip speed ratio of the wind turbine.

[0109] The maximum wind energy capture control system applied to a wind turbine can be used to execute the maximum wind energy capture control method applied to a wind turbine, which will not be elaborated here.

[0110] Finally, it should be understood that the embodiments described in this specification are only used to illustrate the principles of the embodiments of this specification. Other deformations may also fall within the scope of this specification. Therefore, as an example rather than a limitation, the alternative configurations of the embodiments of this specification can be regarded as consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments clearly introduced and described in this specification.

Claims

1. A maximum wind energy capture control method applied to a wind turbine, characterized in that Including: Determine multiple key wind speed detection positions; Establish a multi-objective tip speed ratio optimization function; Based on multiple key wind speed detection positions, obtain a real-time wind speed matrix, where the real-time wind speed matrix includes multiple real-time wind speed vectors, one real-time wind speed vector corresponds to one key wind speed detection position, and the real-time wind speed vector includes the wind speeds of the corresponding key wind speed detection position at multiple time points; Extract features from the real-time wind speed matrix to generate a real-time wind speed feature matrix; Through the tip speed ratio optimization model, based on the real-time wind speed feature matrix, generate the tip speed ratio value range and the reference tip speed ratio; Based on the tip speed ratio value range, generate multiple sampled tip speed ratios; Through finite element analysis, the multi-objective tip speed ratio optimization function, and the reference tip speed ratio, calculate the optimization value of each sampled tip speed ratio; Through the genetic algorithm, based on the optimization value of each sampled tip speed ratio, determine the optimal tip speed ratio of the wind turbine; According to the optimal tip speed ratio of the wind turbine, control the wind turbine to capture wind energy.

2. The maximum wind energy capture control method applied to a wind turbine set according to claim 1, characterized in that Determine multiple key wind speed detection positions, including: Determine multiple wind speed detection positions to be screened; Obtain the wind speeds of each wind speed detection position to be screened at multiple test time periods; Based on the hill climbing search algorithm, obtain the target tip speed ratio of the wind turbine at multiple test time periods; For each wind speed detection position to be screened, based on the wind speeds of the wind speed detection position to be screened at multiple test time periods and the target tip speed ratio of the wind turbine at multiple test time periods, calculate the influence coefficient of the wind speed detection position to be screened on the tip speed ratio of the wind turbine; According to the influence coefficient of each wind speed detection position to be screened on the tip speed ratio of the wind turbine, determine multiple key wind speed detection positions.

3. The maximum wind energy capture control method applied to a wind turbine according to claim 2, characterized in that According to the influence coefficient of each wind speed detection position to be screened on the tip speed ratio of the wind turbine, determine multiple key wind speed detection positions, including: According to the influence coefficient of each wind speed detection position to be screened on the tip speed ratio of the wind turbine, determine multiple first target wind speed detection positions from multiple wind speed detection positions to be screened; For any two first target wind speed detection positions, according to the wind speeds of the two first target wind speed detection positions at multiple test time periods, calculate the wind speed correlation coefficient of the two first target wind speed detection positions; Through the clustering algorithm, according to the wind speed correlation coefficient of any two first target wind speed detection positions, determine multiple key wind speed detection positions.

4. The maximum wind energy capture control method applied to a wind turbine set according to claim 3, characterized in that Through the clustering algorithm, according to the wind speed correlation coefficient of any two first target wind speed detection positions, determine multiple key wind speed detection positions, including: Through the first clustering algorithm, according to the wind speed correlation coefficient of any two first target wind speed detection positions, cluster multiple first target wind speed detection positions to determine multiple first position clusters, and based on the cluster center of each first position cluster, determine multiple second target wind speed detection positions; Through the second clustering algorithm, according to the spatial distance of any two second target wind speed detection positions, cluster multiple second target wind speed detection positions to determine multiple second position clusters; For each second position cluster, according to the spatial coordinates of the second target wind speed detection positions included in the second position cluster, determine the key wind speed detection position corresponding to the second position cluster.

5. The maximum wind energy capture control method applied to a wind turbine unit according to any one of claims 1-4, characterized in that, Extract features from the real-time wind speed matrix to generate a real-time wind speed feature matrix, including: For each real-time wind speed vector, perform variational mode decomposition on the real-time wind speed vector to generate multiple frequency-modulated and amplitude-modulated signal components corresponding to the real-time wind speed vector, extract the component features of each frequency-modulated and amplitude-modulated signal component, and generate a real-time wind speed feature sub-matrix corresponding to the real-time wind speed vector. Among them, a row vector of the real-time wind speed feature sub-matrix represents the component features of a frequency-modulated and amplitude-modulated signal component, and the real-time wind speed feature matrix includes the real-time wind speed feature sub-matrices corresponding to each real-time wind speed vector.

6. The maximum wind energy capture control method applied to a wind turbine according to any one of claims 1-4, characterized in that The multi-objective tip speed ratio optimization function is at least related to the tip speed ratio difference, the mechanical vibration of the generator, and the power fluctuation.

7. The maximum wind energy capture control method applied to a wind turbine according to claim 6, wherein Calculate the optimized value of each sampled tip speed ratio through finite element analysis, the multi-objective tip speed ratio optimization function, and the reference tip speed ratio, including: Based on the sampled tip speed ratio, calculate the impeller speed corresponding to the sampled tip speed ratio; Through finite element analysis based on the impeller speed corresponding to the sampled tip speed ratio, generate the mechanical vibration simulation result of the generator corresponding to the sampled tip speed ratio; Based on the sampled tip speed ratio, calculate the power fluctuation of the wind turbine corresponding to the sampled tip speed ratio; According to the multi-objective tip speed ratio optimization function, the sampled tip speed ratio, the reference tip speed ratio, the mechanical vibration simulation result of the generator corresponding to the sampled tip speed ratio, and the power fluctuation, calculate the optimized value of the sampled tip speed ratio.

8. The maximum wind energy capture control method applied to a wind turbine according to claim 7, characterized in that, Through finite element analysis based on the impeller speed corresponding to the sampled tip speed ratio, generate the mechanical vibration simulation result of the generator corresponding to the sampled tip speed ratio, including: Establish a finite element model of the generator; Based on the impeller speed corresponding to the sampled tip speed ratio, apply boundary conditions and loads to the finite element model of the generator; Solve the finite element model of the generator to generate the mechanical vibration simulation result of the generator corresponding to the sampled tip speed ratio.

9. The maximum wind energy capture control method applied to a wind turbine according to claim 6, characterized in that, Determine the optimal tip speed ratio of the wind turbine through the genetic algorithm based on the optimized value of each sampled tip speed ratio, including: S11. Based on the optimized value of each sampled tip speed ratio, the tip speed ratio value range, and the tip speed ratio difference between each sampled tip speed ratio and the reference tip speed ratio, perform selection, crossover, and mutation operations on multiple sampled tip speed ratios to generate multiple sampled tip speed ratios for the current iteration round; S12. Calculate the optimized value of each sampled tip speed ratio for the current iteration round through finite element analysis, the multi-objective tip speed ratio optimization function, and the reference tip speed ratio; S13. Based on the optimized value of each sampled tip speed ratio for the current iteration round, determine whether the preset condition is satisfied. If not, execute S14; if so, execute S15; S14. Based on the optimized value of each sampled tip speed ratio for the current iteration round, the tip speed ratio value range, and the tip speed ratio difference between each sampled tip speed ratio for the current iteration round and the reference tip speed ratio, perform selection, crossover, and mutation operations on multiple sampled tip speed ratios for the current iteration round to generate multiple sampled tip speed ratios for the next iteration round, and use the multiple sampled tip speed ratios for the next iteration round as the multiple sampled tip speed ratios for the current iteration round, and execute S12; S15. Determine the optimal tip speed ratio of the wind turbine based on the optimized value of the sampled tip speed ratio for each current iteration round.

10. The maximum wind energy capture control system applied to a wind turbine, characterized in that, Apply the maximum wind energy capture control method for a wind turbine according to any one of claims 1-9, including: A position determination module for determining a plurality of key wind speed detection positions; A function establishment module for establishing a multi-objective tip speed ratio optimization function; A wind speed monitoring module for obtaining a real-time wind speed matrix based on a plurality of key wind speed detection positions, wherein the real-time wind speed matrix includes a plurality of real-time wind speed vectors, one real-time wind speed vector corresponds to one key wind speed detection position, the real-time wind speed vector includes the wind speeds at a plurality of time points at the corresponding key wind speed detection position, and perform feature extraction on the real-time wind speed matrix to generate a real-time wind speed feature matrix; An operation optimization module for generating a tip speed ratio value range and a reference tip speed ratio based on the real-time wind speed feature matrix through a tip speed ratio optimization model, generating a plurality of sampled tip speed ratios based on the tip speed ratio value range; calculating the optimized value of each sampled tip speed ratio through finite element analysis, the multi-objective tip speed ratio optimization function and the reference tip speed ratio, determining the optimal tip speed ratio of the wind turbine based on the optimized value of each sampled tip speed ratio through a genetic algorithm, and controlling the wind turbine to capture wind energy according to the optimal tip speed ratio of the wind turbine.

Images