Wind turbine pitch control method and system

Abstract

A wind turbine pitch control method and system. The method comprises: acquiring operation parameters of a wind turbine, determining whether current operation of the wind turbine is normal, and if the wind turbine is currently faulty, stopping the operation of the wind turbine; and acquiring first pitch parameters of a first wind turbine that receives wind, and on the basis of horizontal coordinate parameters, sending second pitch parameters to a wind turbine adjacent to the first wind turbine that receives wind. By this method, the first wind turbine that receives wind can be used to collect parameters, and the parameters are processed by using positional relationships between wind turbines and then sent to all wind turbines in the entire section, so that the wind turbines can make pre-pitch adjustments before the wind arrives, thereby saving pitch adjustment time, enabling the wind turbines to be in an optimal pitch state, and further improving power generation capacity.

Description

A wind turbine variable pitch control method and system TECHNICAL FIELD

[0001] The present application relates to the technical field of wind power generation, in particular to a wind turbine variable pitch control method and system. BACKGROUND

[0002] With the rapid development of China's economy, the high-speed growth of energy consumption, the contradiction between supply and demand of energy is increasingly prominent, and establishing a clean, low-carbon, safe and reliable energy system is an inevitable choice to achieve sustainable development. With the continuous increase of wind power installed capacity, the single machine capacity of wind turbine is also increasing. In order to capture high-quality wind energy at high altitude, reduce the cost of wind power generation, and improve competitiveness, wind turbine tends to be large, light, low noise and low failure rate.

[0003] The wind turbine variable pitch technology is a technology for adjusting the angle of the wind turbine blades. The wind turbine captures wind energy through the rotation of the blades and converts it into mechanical energy, and then into electrical energy. The variable pitch technology can adjust the angle of the blades according to the changes of wind speed and direction, so that the wind turbine can efficiently convert wind energy into electrical energy under different wind speed and direction conditions. This can improve the power generation efficiency of the wind turbine and make it run stably under different wind conditions.

[0004] However, the current variable pitch technology generally reacts only when receiving wind, and performs variable pitch. The variable pitch needs a process and time, and the wind reaches the variable pitch, which may miss the best power generation time, thereby losing the opportunity to further improve the power generation energy.

[0005] SUMMARY

[0006] The purpose of the present application is to provide a wind turbine variable pitch control method and system to solve the problem of untimely wind turbine variable pitch in the prior art.

[0007] The embodiments of the present application are implemented by the following technical solutions:

[0008] In a first aspect, the present application improves a wind turbine variable pitch control method, comprising:

[0009] Obtaining the operating parameters of the wind turbine, determining whether the current wind turbine operation is normal, and stopping the operation of the wind turbine if the current wind turbine operation is faulty;

[0010] If the wind turbine is operating normally, a spatial coordinate system is established, the positioning coordinate parameters of all wind turbines are obtained, and the horizontal coordinate parameters in the horizontal direction of the spatial coordinate system are selected;

[0011] A first pitch parameter of a first wind turbine receiving wind force is acquired, and a second pitch parameter is sent by a wind turbine adjacent to the first wind turbine receiving wind force according to a horizontal coordinate parameter;

[0012] The wind turbine receiving the second pitch parameter calculates a predicted wind turbine absorbed power and performs a pre-pitch operation;

[0013] A power deviation threshold is set, and after the remaining wind turbines except the first wind turbine receiving wind force receive wind force, the actual wind turbine absorbed power is calculated;

[0014] If the difference between the predicted wind turbine absorbed power and the actual wind turbine absorbed power is within the power deviation threshold, no change is made, and if it is not within the power deviation threshold, the pitch correction is performed again according to the actual wind turbine absorbed power.

[0015] In an embodiment of the present application, the judgment of whether the current wind turbine is running normally comprises:

[0016] Collect data fault samples of the pitch variable multiple sensors, establish source domain data set and target domain data set, and perform data preprocessing and overlapping sampling;

[0017] The 1D-CNN network model is input, and the convolution layer is initialized weight;

[0018] High-level features are obtained in the GAP network layer, and the output of the training data set is predicted;

[0019] The errors of the cross-entropy loss function and the maximum average difference loss function are calculated respectively, and the total loss Loss error of the two is constructed;

[0020] The model is trained by the BP neural network, and whether the maximum iteration number is reached is judged, if not, the above steps are repeated;

[0021] If yes, the training model is obtained, the data of the current pitch variable multiple sensors are collected as target domain data, the target domain data is input into the training model, and the fault judgment result is obtained.

[0022] In an embodiment of the present application, the 1D-CNN network model comprises a convolution layer, a pooling layer, an attention mechanism layer, a global average pooling layer and a softmax classifier;

[0023] The convolution layer is used to extract features through multiple networks and filters;

[0024] The pooling layer is used to reduce the dimension of data and represent high-level features to extract features;

[0025] The attention mechanism layer is used to adaptively weight different signal features, filter information and suppress invalid features;

[0026] The global average pooling layer is configured to integrate local information with class distinction in the convolutional layer or the pooling layer.

[0027] The softmax classifier is configured to perform fault classification.

[0028] In an embodiment of the present application, the global average pooling layer comprises:

[0029] wherein, i.e., a value obtained by the lth layer network through the global average pooling layer, f1 l is a feature value, and c is a channel number.

[0030] In an embodiment of the present application, the cross-entropy loss function comprises:

[0031] wherein, n s is a source domain training sample number, y i is a label of the source domain sample, and N c is a sample number.

[0032] The maximum mean discrepancy loss function comprises:

[0033] wherein, and are two data sets, and the posterior probabilities of the two data sets are not identical, φ is a linear mapping function, H is a reproducing kernel space, and n t is a target domain training sample number.

[0034] In an embodiment of the present application, the attention mechanism layer comprises:

[0035] obtaining a feature sequence of each channel output of the convolutional network;

[0036] transmitting the feature sequence to a fully connected network layer to obtain an attention weight of the channel;

[0037] multiplying the attention weight with the original feature sequence to obtain a feature sequence after screening by the attention mechanism.

[0038] In an embodiment of the present application, the first variable pitch parameter of the first wind turbine receiving wind comprises:

[0039] obtaining a wind speed by the following formula:

[0040] wherein, P is a power absorbed by the wind turbine, ρ is air density, R is a radius of a wind wheel blade, v is a current wind speed, Cp is a wind energy utilization coefficient, λ is a tip speed ratio, and β is a blade pitch angle.

[0041] In an embodiment of the present application, the second variable pitch parameter is sent by the wind turbine adjacent to the first wind turbine receiving the wind force according to the horizontal coordinate parameter.

[0042] The second variable pitch parameter is calculated by the wind speed of the first variable pitch parameter.

[0043] In the formula, v1 is the wind speed of the first wind turbine receiving the wind force, x1 and y1 are the horizontal and vertical coordinate values of the first wind turbine receiving the wind force, x2 and y2 are the horizontal and vertical coordinate values of the wind turbine receiving the second variable pitch parameter, and v2 is the calculated wind speed of the wind turbine receiving the second variable pitch parameter.

[0044] In a second aspect, the present application further provides a wind turbine variable pitch control system, comprising:

[0045] The fault diagnosis module is configured to obtain the operating parameters of the wind turbine, determine whether the wind turbine is currently operating normally, and stop the operation of the wind turbine if the wind turbine is currently operating abnormally.

[0046] The calculation module is configured to, if the wind turbines are operating normally, establish a spatial coordinate system, obtain the positioning coordinate parameters of all wind turbines, and select the horizontal coordinate parameters in the horizontal direction of the spatial coordinate system; obtain the first variable pitch parameter of the first wind turbine receiving the wind force, send the second variable pitch parameter by the wind turbine adjacent to the first wind turbine receiving the wind force according to the horizontal coordinate parameter; receive the wind turbine receiving the second variable pitch parameter, calculate the predicted wind turbine absorbed power, and perform the pre-variable pitch operation.

[0047] The judgment module sets a power deviation threshold, calculates the actual wind turbine absorbed power after the remaining wind turbines receiving the wind force except the first wind turbine receiving the wind force; if the difference between the wind turbine absorbed power and the actual wind turbine absorbed power is within the power deviation threshold, no change is made, and if the difference is not within the power deviation threshold, the variable pitch correction is performed again according to the actual wind turbine absorbed power.

[0048] In a third aspect, the present application further provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is executed by a processor to implement the wind turbine variable pitch control method.

[0049] The technical solution of the embodiment of the present application has at least the following advantages and beneficial effects:

[0050] The method of the application mainly comprises obtaining the operation parameters of the wind turbine, judging whether the wind turbine is currently operating normally, stopping the operation of the wind turbine if the wind turbine is currently operating in failure, obtaining the first pitch parameter of the wind turbine that first receives the wind, and sending the second pitch parameter from the wind turbine adjacent to the wind turbine that first receives the wind according to the horizontal coordinate parameter. Through the method, the wind turbine that first receives the wind can collect the parameters, the parameters are processed according to the positional relationship between the wind turbines, and the processed parameters are sent to all the wind turbines in the whole area, so that the wind turbine can be pre-pitched before the wind arrives, the time for pitching is saved, if the sent parameters are correct, the wind turbine does not need to be adjusted, if the sent parameters have errors, the wind turbine only needs to be adjusted in a small range, so that the wind turbine is in the best pitch state as much as possible when the wind arrives, and the power generation capacity is further improved. BRIEF DESCRIPTION OF DRAWINGS

[0051] In order to more clearly illustrate the technical solutions of the embodiments of the application, the following will briefly introduce the drawings needed to be used in the embodiments. It should be understood that the following drawings only show some of the embodiments of the application, and therefore should not be regarded as a limitation to the scope. For those skilled in the art, other related drawings can also be obtained without creative labor.

[0052] Fig. 1 is a flowchart of the application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the embodiments of the application more clear, the following will combine the drawings in the embodiments of the application to clearly and completely describe the technical solutions in the embodiments of the application. Obviously, the described embodiments are some of the embodiments of the application, but not all the embodiments. The components of the embodiments of the application described and shown in the drawings can be arranged and designed in various different configurations.

[0054] The independently described modules or sub-modules can be physically separated or not physically separated, can be software implemented or hardware implemented, and part of the modules or sub-modules can be implemented by software, the function of the part of the modules or sub-modules is called by the processor, and the other part of the modules or sub-modules is implemented by hardware, for example, by hardware circuit. In addition, part or all of the modules can be selected according to actual needs to achieve the purpose of the application scheme.

[0055] Please refer to Fig. 1, the application improves a wind turbine pitch control method, which comprises;

[0056] S101: obtaining the operation parameters of the wind turbine, judging whether the wind turbine is currently operating normally, stopping the operation of the wind turbine if the wind turbine is currently operating in failure;

[0057] When performing pitch control, the present invention needs to verify in advance whether the wind turbine is operating normally. The specific judgment process will be described in detail below.

[0058] S102: Several wind turbines are operating normally. Establish a spatial coordinate system, obtain the positioning coordinate parameters of all wind turbines, and select the horizontal coordinate parameters in the horizontal direction of the spatial coordinate system.

[0059] The spatial coordinate system can be obtained from the global positioning of the wind turbine, resulting in a three-dimensional coordinate axis data. However, the height difference between each wind turbine has a weak impact on the horizontal distance difference. Therefore, this embodiment only considers the distance on the horizontal plane and does not consider the distance in height to simplify the calculation steps and process.

[0060] S103: Obtain the first pitch parameter of the first wind turbine that receives wind power, and send the second pitch parameter to the wind turbine adjacent to the first wind turbine that receives wind power according to the horizontal coordinate parameter;

[0061] The first pitch parameter includes the basic parameters of the wind turbine, such as the wind turbine's absorbed power, air density, rotor blade radius, and wind speed. The second pitch parameter mainly consists of the blade pitch angle, which is the final angle that the pitch needs to rotate, and is calculated using a formula.

[0062] S104: The wind turbine receives the second pitch parameter, calculates the predicted wind turbine absorption power, and performs the pre-pitch operation;

[0063] S105: Set the power deviation threshold. After the first wind turbine receives wind power, the actual power absorbed by the remaining wind turbines is calculated.

[0064] S106: If the difference between the wind turbine's absorbed power and the actual wind turbine absorbed power is within the power deviation threshold, no change will be made. If it is not within the power deviation threshold, pitch correction will be performed again based on the actual wind turbine absorbed power.

[0065] The method of the application mainly comprises obtaining the operation parameters of the fan, judging whether the current fan operation is normal, stopping the operation of the fan if the current fan operation is faulty, obtaining the first pitch parameter of the fan that first receives the wind, and sending the second pitch parameter from the fan adjacent to the fan that first receives the wind according to the horizontal coordinate parameter.

[0066] In an embodiment of the application, the judging whether the current fan operation is normal comprises:

[0067] The data fault samples of the variable-pitch sensors are collected, the source domain data set and the target domain data set are established, and data preprocessing and overlap sampling are performed; the 1D-CNN network model is input, and the convolution layer is initialized with weights; high-level features are obtained in the GAP network layer, and the output of the training data set is predicted; the errors of the cross-entropy loss function and the maximum average difference loss function are calculated respectively, and the total loss Loss error of the two is constructed; the model is trained through the BP neural network, and whether the maximum iteration number is reached is judged, if not, the above steps are repeated; if yes, the training model is obtained, the current data of the variable-pitch sensors are collected as the target domain data, the target domain data are input into the training model, and the fault judgment result is obtained.

[0068] Specifically, in the embodiment, the 1D-CNN network model comprises a convolution layer, a pooling layer, an attention mechanism layer, a global average pooling layer and a softmax classifier.

[0069] The convolution layer is used for feature extraction through multiple networks and filters. l =σ(w l x l-1 +b l )

[0070] In the formula, x l is the output vector of the lth layer, sigma is an activation function, x l-1 is the input vector of the lth layer, w l is a matrix composed of all connection unit weights between the (l-1)th layer and the lth layer, and b l is a bias.

[0071] The pooling layer is used to reduce the information redundancy of the features, reduce the dimension of the data, and then extract the features. Generally, a max pooling operation is used, a window size and a step size are set, and the obtained local maximum value is taken as the reserved feature. l(i，j) = max{a l(i，j)}(j-1)w+1≤t≤jw

[0072] In the formula, p l(i,j) is the correlation value after the l-layer neuron pooling operation, a l(i,j) is the value of the tth neuron in the ith structure in the lth layer, (j-1)w+1≤t≤jw is the threshold value of t, and w is the pooling width.

[0073] The attention mechanism layer is used for adaptively weighting different signal features, filtering information, and suppressing invalid features.

[0074] Specifically, the attention mechanism layer includes: obtaining a feature sequence V=[v1, v2, v3…, v N N is the length of the sequence, the feature sequence V is transmitted to a fully connected network layer to obtain a channel attention weight S=[s1, s2, s3…, s N The attention weight S is multiplied by the original feature sequence to obtain a feature sequence after filtering by the attention mechanism.

[0075] The global average pooling layer is used to integrate local information with class distinction in the convolutional layer or the pooling layer.

[0076] In the formula, is the value obtained by the lth network through the global average pooling layer, f1 l is a feature value, and c is the number of channels.

[0077] In this embodiment, Softmax is a classifier for performing a multi-class classification task, and in this document, the classification of faults is performed according to the size of the Softmax value.

[0078] In an embodiment of the present application, the cross-entropy loss function is used to minimize the empirical classification error of the source label data, and the cross-entropy loss function includes:

[0079] In the formula, n s is the number of source domain training samples, y i is the label of the source domain sample, and N c is the number of samples.

[0080] The maximum average difference loss function is used to measure the difference between the source domain and the target domain with different distributions, and the value tends to 0, which is equivalent to the higher the matching degree of the two data distributions, and includes:

[0081] wherein, and are two data sets, and the posterior probabilities of the two data sets are not identical, φ is a linear mapping function, H is a reproducing kernel space, n t is the number of target domain training samples.

[0082] The following example illustrates a practical example of the above neural network module:

[0083] The CUDA11.3 and pytorch1.10.1 deep learning framework is used to realize fault diagnosis, the model uses the minimum cost function SGD optimizer to update the training parameters, the learning efficiency parameter is 0.01, the iteration batch number is 50, and the size of each batch is 30.

[0084] First, the method provided by the present scheme is used for multi-sensor fault diagnosis of the variable pitch system under different switching modes, and is compared with the traditional signal processing methods SVM+EMD+Hibert envelope spectrum, BPNN+EMD+Hibert, envelope spectrum, ResNet and traditional methods, to verify the fault diagnosis performance under different modes without noise influence, and the present scheme reaches 99% under constant gain-constant deviation and constant deviation-constant gain mode switching, which is greatly improved in accuracy compared with the traditional diagnosis method; The traditional signal processing method has low diagnosis accuracy under different modes, that is, it cannot realize fault diagnosis under different mode switching; The fault diagnosis accuracy of the method provided in the present scheme is higher, and the diagnosis effect is better.

[0085] In an embodiment of the present application, the first variable pitch parameter of the wind turbine that first receives wind force includes:

[0086] The wind speed is obtained by the following formula:

[0087] In the formula, P is the power absorbed by the wind turbine, ρ is the air density, R is the radius of the wind turbine blade, v is the current wind speed, Cp is the wind energy utilization coefficient, λ is the tip speed ratio, and β is the blade pitch angle.

[0088] In the above formula, the current wind speed can be directly calculated, and second, the second variable pitch parameter sent by the adjacent wind turbine of the wind turbine that first receives wind force according to the horizontal coordinate parameter includes:

[0089] The second variable pitch parameter is calculated by the wind speed of the first variable pitch parameter;

[0090] In the formula, v1 is the wind speed of the first wind turbine receiving wind force, x1 and y1 are the horizontal and vertical coordinate values of the first wind turbine receiving wind force, x2 and y2 are the horizontal and vertical coordinate values of the wind turbine receiving the second pitch parameter, and v2 is the calculated wind speed of the wind turbine receiving the second pitch parameter.

[0091] The wind force component of the wind turbine receiving the second pitch parameter can be calculated according to the positional relationship between the wind turbines, and the second pitch parameter of the wind turbine receiving the second pitch parameter can be approximately calculated.

[0092] After actually receiving wind force, it is determined whether the power generation power is within the threshold value, and it is determined whether to adjust the current pitch state. At this time, after the pre-pitching, if subsequent pitching is needed again, only a small amount of fine tuning is required.

[0093] In a second aspect, the application further provides a wind turbine pitch control system, comprising:

[0094] The fault diagnosis module is configured to obtain the operating parameters of the wind turbine, determine whether the current wind turbine operation is normal, and stop the operation of the wind turbine if the current wind turbine operation is faulty;

[0095] The calculation module is configured to, if the wind turbines are operating normally, establish a spatial coordinate system, obtain the positioning coordinate parameters of all wind turbines, and select the horizontal coordinate parameters in the horizontal direction of the spatial coordinate system; obtain the first pitch parameter of the first wind turbine receiving wind force, send the second pitch parameter to the wind turbine adjacent to the first wind turbine receiving wind force according to the horizontal coordinate parameter; receive the second pitch parameter of the wind turbine, and calculate the pre-judgment wind turbine absorption power to perform the pre-pitching operation;

[0096] The judgment module sets a power deviation threshold value, calculates the actual wind turbine absorption power after the remaining wind turbines receiving wind force except the first wind turbine receiving wind force receive wind force; if the difference between the wind turbine absorption power and the actual wind turbine absorption power is within the power deviation threshold value, no change is made, and if the difference is not within the power deviation threshold value, the pitch correction is performed again according to the actual wind turbine absorption power.

[0097] If the integrated unit is realized in the form of a software function unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer software product stored in a storage medium includes a plurality of instructions for causing 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 of each embodiment of the application. The aforementioned storage medium includes a U disk, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk, and various media that can store program codes.

[0098] The preferred embodiments of the present application have been described above with the intent to enable those skilled in the art to make and use it. Various modifications to the embodiments described in this disclosure will be readily apparent to those skilled in the art, and the generic principles defined herein can be applied to other embodiments without departing from the spirit or scope of the application. Accordingly, the true scope of the present application is not limited to the embodiments described herein but is only limited to the scope of the claims together with the full range of equivalents to which such claims are entitled.

Claims

1. A method of wind turbine variable pitch control, the method comprising: Comprise; Obtain the operation parameter of the fan, judge whether the current fan operation is normal, if the fan is currently running failure, stop the operation of the fan; If the operation of the fan is normal, establish a space coordinate system, obtain the positioning coordinate parameters of all fans, and select the horizontal coordinate parameters in the horizontal direction of the space coordinate system; Obtain the first variable pitch parameter of the first fan receiving wind force, and send the second variable pitch parameter to the fan adjacent to the first fan receiving wind force according to the horizontal coordinate parameter; The fan receiving the second variable pitch parameter calculates the predicted fan absorbed power and executes the pre variable pitch operation; Set the power deviation threshold, and calculate the actual fan absorbed power after the rest of the first fan receiving wind force receives wind force; If the difference between the fan absorbed power and the actual fan absorbed power is within the power deviation threshold, no change is made, if it is not within the power deviation threshold, the variable pitch correction is performed again according to the actual fan absorbed power.

2. A method of variable pitch control for a wind turbine according to claim 1, wherein, The judgment of whether the current fan operation is normal comprises: Collecting data fault samples of variable pitch sensors, establishing source domain data set and target domain data set, and carrying out data preprocessing and overlapping sampling; Input 1D-CNN network model, initialize the weight of convolution layer; Obtain high-level features in GAP network layer, and predict the output of training data set; Calculate the error of cross entropy loss function and maximum average difference loss function respectively, and construct the total loss Loss error of the two; Train the model through BP neural network, and judge whether the maximum iteration number is reached, if not, repeat the above steps; If yes, obtain the training model, collect the data of the current variable pitch sensor as the target domain data, input the target domain data into the training model, and obtain the fault judgment result.

3. A method of variable pitch control for a wind turbine according to claim 2, wherein, The 1D-CNN network model comprises convolution layer, pooling layer, attention mechanism layer, global average pooling layer and softmax classifier; The convolution layer is used for feature extraction through multiple networks and filters; The pooling layer is used for dimension reduction of data, and high-level features are used to represent and extract features; The attention mechanism layer is used for adaptive weighting of different signal features, information screening and inhibition of invalid features; The global average pooling layer is used for integrating local information with class distinction in the convolution layer or the pooling layer; The softmax classifier is used for fault classification.

4. A method of variable pitch control for a wind turbine according to claim 3, wherein, The global average pooling layer comprises; In the formulae, i.e. the value obtained by the first layer network via the global average pooling layer, The feature value is f, and c is the number of channels.

5. The method of pitch control of a wind turbine according to claim 3, wherein, The cross-entropy loss function comprises; In the formula, n s is the number of source domain training samples, y i is the label of the source domain sample, N c is the number of samples; The maximum average discrepancy loss function comprises; In the formulae, and For two data sets, and the posterior probabilities of the two data sets are not equal, φ is a linear mapping function, H is a reproducing kernel space, n t is the number of target domain training samples.

6. A method of variable pitch control for a wind turbine according to claim 3, wherein, The attention mechanism layer comprises: Obtain the feature sequence output by each channel of the convolution network; The feature sequence is transmitted to the fully connected network layer to obtain the attention weight of the channel; The attention weight is multiplied by the original feature sequence to obtain the feature sequence after screening by the attention mechanism.

7. The method of claim 1, wherein, The first variable pitch parameter of the first fan receiving wind force comprises: The wind speed is obtained by the following formula: In the formula, P is the power absorbed by the wind turbine; ρ is the air density; R is the radius of the wind wheel blade; v is the current wind speed; Cp is the wind energy utilization coefficient; λ is the tip speed ratio; β is the blade pitch angle.

8. A method of variable pitch control for a wind turbine according to claim 7, wherein, The second variable pitch parameter sent to the fan adjacent to the first fan receiving wind force according to the horizontal coordinate parameter comprises: calculating a second variable pitch parameter from the wind speed by a first variable pitch parameter; In the formula, v1 is the wind speed of the first wind turbine receiving wind force, x1 and y1 are the horizontal and vertical coordinate values of the first wind turbine receiving wind force, x2 and y2 are the horizontal and vertical coordinate values of the second wind turbine receiving wind force, and v2 is the calculated wind speed of the second wind turbine receiving wind force. comprise; 9. A wind turbine variable pitch control system, characterized by, a fault diagnosis module configured to acquire the operating parameters of the wind turbine, determine whether the wind turbine is currently operating normally, and stop the operation of the wind turbine if the wind turbine is currently operating abnormally; a calculation module configured to, if the wind turbines are operating normally, establish a spatial coordinate system, acquire the positioning coordinate parameters of all the wind turbines, and select the horizontal coordinate parameters in the horizontal direction of the spatial coordinate system; acquire the first variable pitch parameter of the first wind turbine receiving wind force, send the second variable pitch parameter to the wind turbines adjacent to the first wind turbine receiving wind force according to the horizontal coordinate parameters; receive the second variable pitch parameter by the wind turbine, calculate the predicted wind turbine absorbed power, and perform the pre-pitch operation; a judgment module configured to set a power deviation threshold, calculate the actual wind turbine absorbed power after the rest of the wind turbines receiving wind force except the first wind turbine receiving wind force receive wind force, and, if the difference between the wind turbine absorbed power and the actual wind turbine absorbed power is within the power deviation threshold, make no changes, and, if the difference is not within the power deviation threshold, perform pitch correction again according to the actual wind turbine absorbed power. The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the wind turbine variable pitch control method according to any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that, ​

Images