Wind turbine variable pitch control method, device, terminal and medium

Abstract

The embodiment of the application relates to the field of wind power control, and provides a variable pitch control method, device, terminal and medium of a wind turbine, the method comprising: obtaining safety operation system information of a target wind turbine, and obtaining a to-be-deployed variable pitch control model of the target wind turbine; adjusting the to-be-deployed variable pitch control model according to the safety operation system information to obtain a target variable pitch control model; obtaining current operation information and current wind speed information of the target wind turbine; performing control parameter calculation by using the target variable pitch control model, the current operation information and the current wind speed information to obtain a variable pitch control parameter of the target wind turbine; and performing variable pitch control on the target wind turbine by using the variable pitch control parameter, so that the variable pitch control parameter can be determined by using the deployed variable pitch control model, real-time variable pitch adjustment suitable for a current operation environment is realized, the accuracy during variable pitch control is improved, a bottleneck of matching between original load and power generation performance is broken, and power generation capacity is significantly improved.

Description

Technical Field

[0001] This application relates to the field of wind power control technology, specifically to a pitch control method, device, terminal, and medium for wind turbine generators. Background Technology

[0002] With the widespread application of renewable energy, wind energy, as an important clean energy source, has experienced rapid development globally. As the primary equipment for wind energy conversion, the operating efficiency of wind turbines directly impacts the overall power generation of wind farms. Wind power generation plays a crucial role in the global energy transition due to its environmentally friendly characteristics. However, the randomness and instability of wind speeds pose challenges to the operation of wind turbines. Pitch control is a vital component of wind turbine control systems, effectively controlling generator speed and output power by adjusting the angle of the blades relative to the wind direction. Adjusting the blade angle adapts to different wind speed conditions, ensuring stable operation of the unit and maximizing energy capture. While traditional PID controllers are simple and easy to use, they have limitations in handling complex and variable wind conditions, resulting in lower accuracy in pitch control of wind turbines. Summary of the Invention

[0003] This application provides a pitch control method, device, terminal, and medium for wind turbine generators. It can determine pitch control parameters using a deployed pitch control model and perform pitch control using the determined pitch control parameters, thereby improving the accuracy of pitch control.

[0004] A first aspect of this application provides a pitch control method for a wind turbine generator, the method comprising:

[0005] Obtain the safety operation system information of the target wind turbine, and obtain the pitch control model of the target wind turbine to be deployed;

[0006] The pitch control model to be deployed is adjusted according to the safety operation system information to obtain the target pitch control model;

[0007] Obtain the current operating information and current wind speed information of the target wind turbine;

[0008] The target pitch control model, the current operating information, and the current wind speed information are used to calculate the control parameters to obtain the pitch control parameters of the target wind turbine.

[0009] The pitch control parameters are used to perform pitch control on the target wind turbine.

[0010] In this example, by acquiring the safety operation system information of the target wind turbine and the pitch control model to be deployed for the target wind turbine, the pitch control model to be deployed is adjusted according to the safety operation system information to obtain the target pitch control model. The current operation information and current wind speed information of the target wind turbine are acquired. The target pitch control model, the current operation information, and the current wind speed information are used to calculate control parameters to obtain the pitch control parameters of the target wind turbine. The pitch control parameters are then used to perform pitch control on the target wind turbine. Therefore, the pitch control parameters can be determined using the deployed pitch control model, and the determined pitch control parameters can be used for pitch control, thus improving the accuracy of pitch control.

[0011] A second aspect of this application provides a pitch control device for a wind turbine generator, the device comprising:

[0012] The acquisition unit is used to acquire the safety operation system information of the target wind turbine and the pitch control model to be deployed for the target wind turbine.

[0013] The adjustment unit is used to adjust the pitch control model to be deployed according to the safety operation system information to obtain the target pitch control model;

[0014] The second acquisition unit is used to acquire the current operating information and current wind speed information of the target wind turbine.

[0015] The calculation unit is used to perform control parameter calculations using the target pitch control model, the current operating information, and the current wind speed information to obtain the pitch control parameters of the target wind turbine.

[0016] The control unit is used to perform pitch control on the target wind turbine using the pitch control parameters.

[0017] A third aspect of this application provides a terminal including a processor, an input device, an output device, and a memory, wherein the processor, input device, output device, and memory are interconnected, wherein the memory is used to store a computer program, the computer program including program instructions, and the processor is configured to invoke the program instructions to execute the step instructions as described in the first aspect of this application.

[0018] A fourth aspect of this application provides a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in the first aspect of this application.

[0019] A fifth aspect of this application provides a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of this application. The computer program product may be a software installation package. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0021] Figure 1 This application provides a schematic flowchart of pitch control for a wind turbine.

[0022] Figure 2 This application provides a schematic diagram of output pitch under a first operating condition.

[0023] Figure 3 This application provides a schematic diagram of output pitch under a second operating condition.

[0024] Figure 4 This application provides a schematic diagram of output pitch under a third operating condition.

[0025] Figure 5 This application provides a power comparison curve between the target pitch control model and the unadjusted pitch control model for embodiments of the present application;

[0026] Figure 6 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application;

[0027] Figure 7 This application provides a schematic diagram of the structure of a pitch control device for a wind turbine. Detailed Implementation

[0028] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0029] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0030] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application can be combined with other embodiments.

[0031] To better understand the business product determination method provided in this application embodiment, the following is a brief introduction to the application scenario of this business product determination method. When a user sells company products to a customer, the following actions are typically involved: the user meets with the customer to collect the customer's product requirements, which may include business requirements, budget, etc.; the user manually selects a suitable product manufacturing plan and formulates the business product offline based on the product requirements; and then the user schedules another appointment with the customer to explain the business product plan. The entire process is time-consuming, especially the manual selection of a suitable product manufacturing plan and formulation of the business product. Due to the diversity of product requirements, the efficiency of manually selecting a suitable product manufacturing plan and formulating the business product is low. This application embodiment aims to solve the problem of low efficiency in determining business products by providing a business product determination method. This method can automatically generate target business products through product requirement information, thereby improving the efficiency of determining target business products.

[0032] Please see Figure 1 , Figure 1 This application provides a schematic flowchart of a pitch control method for a wind turbine generator. Figure 1 As shown, the method includes:

[0033] 101. Obtain the safety operation system information of the target wind turbine, and obtain the pitch control model to be deployed for the target wind turbine.

[0034] The safety operation system information includes the operating boundary conditions of the wind turbine, such as pitch angle, wind speed, and torque limits, to ensure the safe operation of the wind turbine. Specifically, in practical applications, the following limits apply: Pitch angle limit: The maximum and minimum pitch angles must meet the safe operation requirements of the wind turbine to avoid blade damage under extreme wind speeds; Wind speed limit: When the wind speed exceeds the set limit value, the system should trigger shutdown protection to prevent the wind turbine from operating under severe weather conditions; Torque limit: When the torque exceeds the set limit value, the system should trigger torque protection to limit the torque within the limit value; Operating condition limit: Control is only applied to operating condition 1.X, and other operating conditions are not used for the time being, continuing the original control logic.

[0035] One method to obtain the pitch control model to be deployed is to adjust the initial pitch control model using the original sample dataset to obtain a reference pitch control model, and then adjust the reference pitch control model again using real-time simulated sample data to obtain the pitch control model to be deployed. This allows for joint training to obtain the pitch control model to be deployed, improving the accuracy of determining the pitch control model to be deployed.

[0036] 102. Adjust the pitch control model to be deployed according to the safety operation system information to obtain the target pitch control model.

[0037] During the adjustment process, the control effect of the pitch control model to be deployed was first tested under low wind speed and power-limited conditions. Wind speed conditions were gradually increased to improve the adaptability of the pitch control model under different operating conditions. Through continuous optimization and testing, the optimal control effect was ultimately achieved.

[0038] The specific adjustments will be made in three stages, as follows:

[0039] Adjustment Phase 1: First Operating Condition (DLC1.0 Operating Condition)

[0040] Under the initial standard operating condition (DLC1.0), the pitch control model to be deployed is trained online. If the model's output pitch angle deviates too much from the expected value, the offline training steps in Part 1 are returned to re-optimize the model parameters until the pitch control model to be deployed can effectively control the pitch. A schematic diagram of the output pitch at this stage is shown below. Figure 2 As shown.

[0041] Adjustment Phase 2: Second Operating Condition (DLC1.2 Operating Condition)

[0042] After training in DLC1.0, the pitch control model to be deployed enters a more complex operating condition (DLC1.2), where wind speed varies significantly. At this point, the pitch control model needs to be adjusted online to cope with wind speed fluctuations and changes in external conditions. The schematic diagram of the output pitch at this stage is shown below. Figure 3 As shown.

[0043] Adjustment Phase 3: Third Operating Condition (DLC1.3 Operating Condition)

[0044] Under extreme conditions of sudden wind speed changes (DLC1.3), the pitch control model to be deployed implements real-time pitch control based on current environmental parameters to ensure the stable operation of the wind turbine under complex conditions. A schematic diagram of the pitch output at this stage is shown below. Figure 4 As shown.

[0045] After obtaining the target pitch control model, this target pitch control model shows a significant performance improvement compared to the existing pitch control model without adjustment. A detailed comparison can be made as follows: Figure 5 As shown, Figure 5 The power comparison curves between the target pitch control model and the existing pitch control model without adjustment are shown.

[0046] 103. Obtain the current operating information and current wind speed information of the target wind turbine.

[0047] The current operating information includes torque, pitch angle, etc.

[0048] 104. Using the target pitch control model, the current operating information, and the current wind speed information, control parameters are calculated to obtain the pitch control parameters of the target wind turbine.

[0049] The current operating information and current wind speed information are input into the target pitch control model to calculate the control parameters, thereby obtaining the pitch control parameters of the target wind turbine.

[0050] 105. The target wind turbine is controlled by pitch control using the pitch control parameters.

[0051] Using these pitch control parameters for pitch control of the target wind turbine can improve the reliability and accuracy of pitch control of the target wind turbine.

[0052] In one specific implementation, a method for obtaining the pitch control model of a target wind turbine to be deployed includes:

[0053] A1. Obtain the initial pitch control model and sample dataset;

[0054] A2. Construct the loss function of the initial pitch control model to obtain the first loss function;

[0055] A3. Adjust the initial pitch control model using sample data from the sample dataset, and obtain a reference pitch control model when the first loss function converges.

[0056] A4. Obtain real-time simulated sample data sent by the simulated wind turbine platform;

[0057] A5. Construct the loss function of the reference pitch control model to obtain the second loss function;

[0058] A6. The reference pitch control model is adjusted using the real-time simulated sample data, and the pitch control model to be deployed is obtained when the second loss function converges.

[0059] The sample dataset can originate from the Bladed simulation platform for wind turbines, containing operational status data such as turbine speed, torque, pitch angle, wind speed, wind direction, and output power. To improve model accuracy, this data is normalized to ensure that features of different dimensions maintain similar numerical ranges during training. The following normalization formula can be used for normalization:

[0060]

[0061] in, This is the original data. and These are the minimum and maximum values ​​of the feature data, respectively. This is the normalized sample data.

[0062] The initial pitch control model can be a constructed offline LSTM model, which includes an input layer, multiple hidden layers, and an output layer.

[0063] Input layer: The input sample data is a normalized sample dataset. The sample data is represented by input vectors, and the dimension of the input vectors is n. This represents the data at time step t. The input vector for each time step is:

[0064]

[0065] in, This refers to the fan speed; This refers to the fan torque; For variable pitch angle; Wind speed; This refers to the output power of the fan. The wind direction.

[0066] Hidden Layer: Each LSTM unit consists of several gates (input gate, forget gate, output gate), which determine the data flow based on the input and state. The calculation formula for the hidden layer is as follows:

[0067] Forgotten Gate Used to determine the state at the current moment. Whether to retain the item at the current time t. The formula for calculation is:

[0068]

[0069] in, Here is the weight matrix for the forget gate. This is the output from the previous time step. For the bias term of the forget gate, This is the Sigmoid activation function.

[0070] Input Gate: and candidate states This is used to determine the update level of the current input information. The calculation formulas are as follows:

[0071]

[0072]

[0073] in, and These are the weight matrices for the input gate and the candidate state, respectively. and For the corresponding bias term.

[0074] State Update: The previous state is updated using the forget gate and the input gate, resulting in the new cell state. The calculation is as follows:

[0075]

[0076] Output gate The value that determines the current state output to the next LSTM unit is calculated using the following formula:

[0077]

[0078] Final output value for:

[0079]

[0080] Output layer: The output is the predicted pitch angle at a future time. The output layer uses a linear activation function to map the final output of the initial pitch control model to the desired prediction result.

[0081] We can minimize the prediction error by using the mean squared error (MSE) as the first loss function, as follows:

[0082]

[0083] Where MSE is the value of the first loss function. For the true value, Let be the predicted value, and n be the number of samples. The optimization algorithm uses the Adam optimizer with an adaptive learning rate, and its parameter update formula is as follows:

[0084] Gradient estimation of the initial pitch control model:

[0085]

[0086]

[0087] in, and These are first-order and second-order momentum, respectively. The first loss function is relative to the parameters The gradient of . Where, This is the first loss function (i.e., the initial pitch control model training phase).

[0088] Parameter updates for the initial pitch control model:

[0089]

[0090] in, and These are the momentum terms after bias correction. For learning rate, To prevent small constants from being divided by zero.

[0091] The initial pitch control model is adjusted using sample data from the aforementioned sample dataset. When the first loss function converges, the resulting reference pitch control model can be:

[0092] Through forward and backward propagation, the weights of the LSTM model are continuously adjusted using the above formula until the model converges, i.e., the loss function converges to a small value. The training results of the model are evaluated through cross-validation to ensure the model's generalization ability.

[0093] When acquiring real-time simulation sample data sent by the simulated wind turbine platform, the simulation platform can interact with the initial pitch control model through a communication protocol, thereby sending the real-time simulation sample data to the initial pitch control model and thus acquiring the real-time simulation sample data.

[0094] The second loss function is characterized by the following formula:

[0095]

[0096] in, This is the value of the second loss function. For the target load value, To predict the load value, n is the number of real-time simulated sample data.

[0097] The reference pitch control model is adjusted using the real-time simulated sample data. When the second loss function converges, the pitch control model to be deployed is obtained. Specifically, the update direction information of the reference pitch control model during adjustment can be acquired; the updated correction matrix during adjustment can be determined; and the parameters of the reference pitch control model can be updated. The correction matrix is ​​used for parameter adjustment of the reference pitch control model, updating the parameters of the reference pitch control model, and ultimately obtaining the pitch control model to be deployed.

[0098] In one specific implementation, the pitch control method for the wind turbine also includes:

[0099] Determine the updated direction information when adjusting the reference pitch control model;

[0100] The determination of the updated direction information when adjusting the reference pitch control model includes:

[0101] The updated direction information when adjusting the reference pitch control model is determined using the method shown in the following formula:

[0102]

[0103] in, To update direction information, The correction matrix is ​​the inverse of the current approximate Hessian matrix in the reference pitch control model; the correction matrix is ​​iteratively updated using the following correction matrix formula. The second loss function is relative to the parameters The gradient.

[0104] In one specific implementation, the pitch control method for the wind turbine also includes:

[0105] Determine the updated correction matrix when adjusting the reference pitch control model;

[0106] The determination of the updated correction matrix during the adjustment of the reference pitch control model includes:

[0107] The correction matrix is ​​determined using the method shown in the following formula:

[0108]

[0109] in, It is the change in position. It is the change in gradient. This is the updated correction matrix. This is the correction matrix before the update. It is an identity matrix.

[0110] The parameters of the reference pitch control model are updated using the method shown in the following formula:

[0111]

[0112] in: These are the updated parameters. It is the step size, usually determined through line search. That's the direction for updates.

[0113] For examples consistent with the above embodiments, please refer to... Figure 6 , Figure 6 This is a schematic diagram of the structure of a terminal provided in an embodiment of this application, such as... Figure 6 As shown, it includes a processor, an input device, an output device, and a memory, which are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to call the program instructions. The program includes instructions for performing the following steps.

[0114] Obtain the safety operation system information of the target wind turbine, and obtain the pitch control model of the target wind turbine to be deployed;

[0115] The pitch control model to be deployed is adjusted according to the safety operation system information to obtain the target pitch control model;

[0116] Obtain the current operating information and current wind speed information of the target wind turbine;

[0117] The target pitch control model, the current operating information, and the current wind speed information are used to calculate the control parameters to obtain the pitch control parameters of the target wind turbine.

[0118] The pitch control parameters are used to perform pitch control on the target wind turbine.

[0119] The above mainly describes the solutions of the embodiments of this application from the perspective of the method execution process. It is understood that, in order to achieve the above functions, the terminal includes the corresponding hardware structure and / or software modules for executing each function. Those skilled in the art should readily recognize that, in conjunction with the units and algorithm steps of the various examples described in the embodiments provided herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0120] This application embodiment can divide the terminal into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0121] For those consistent with the above, please refer to Figure 7 , Figure 7 This application provides a schematic diagram of the structure of a pitch control device for a wind turbine generator. For example... Figure 7 As shown, the device includes:

[0122] The acquisition unit 801 is used to acquire the safety operation system information of the target wind turbine and the pitch control model to be deployed for the target wind turbine.

[0123] The adjustment unit 802 is used to adjust the pitch control model to be deployed according to the safety operation system information to obtain the target pitch control model;

[0124] The second acquisition unit 803 is used to acquire the current operating information and current wind speed information of the target wind turbine.

[0125] The calculation unit 804 is used to perform control parameter calculations using the target pitch control model, the current operating information and the current wind speed information to obtain the pitch control parameters of the target wind turbine.

[0126] Control unit 805 is used to perform pitch control on the target wind turbine using the pitch control parameters.

[0127] In one specific implementation, regarding the acquisition of the pitch control model to be deployed for the target wind turbine, the acquisition unit 801 is specifically used for:

[0128] Obtain the initial pitch control model and the sample dataset;

[0129] Construct the loss function of the initial pitch control model to obtain the first loss function;

[0130] The initial pitch control model is adjusted using sample data from the sample dataset, and a reference pitch control model is obtained when the first loss function converges.

[0131] Obtain real-time simulated sample data sent by the simulated wind turbine platform;

[0132] Construct the loss function of the reference pitch control model to obtain the second loss function;

[0133] The reference pitch control model is adjusted using the real-time simulated sample data, and the pitch control model to be deployed is obtained when the second loss function converges.

[0134] In one specific implementation, the second loss function is characterized by the following formula:

[0135]

[0136] in, This is the value of the second loss function. For the target load value, To predict the load value, n is the number of real-time simulated sample data.

[0137] In one specific implementation, the device is further used for:

[0138] Determine the updated direction information when adjusting the reference pitch control model;

[0139] The determination of the updated direction information when adjusting the reference pitch control model includes:

[0140] The updated direction information when adjusting the reference pitch control model is determined using the method shown in the following formula:

[0141] =

[0142] in, To update direction information, The inverse of the current approximate Hessian matrix in the reference pitch control model, i.e., the correction matrix; The second loss function relative to the parameters gradient, This is the second loss function (i.e., during the adjustment phase of the reference pitch control model).

[0143] In one specific implementation, the device is further used for:

[0144] Determine the updated correction matrix when adjusting the reference pitch control model;

[0145] The determination of the updated correction matrix during the adjustment of the reference pitch control model includes:

[0146] The correction matrix is ​​determined using the method shown in the following formula:

[0147]

[0148] in, It is the change in position. It is the change in gradient. This is the updated correction matrix. Let I be the correction matrix before the update, and let I be the identity matrix.

[0149] This application also provides a computer storage medium storing a computer program for electronic data interchange, which causes a computer to perform some or all of the steps of any of the pitch control methods for wind turbines described in the above method embodiments.

[0150] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program that causes a computer to perform some or all of the steps of any of the pitch control methods for wind turbines described in the above method embodiments.

[0151] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0152] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.

[0153] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical or other forms.

[0154] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0155] Furthermore, the functional units in the various embodiments of the application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software program module.

[0156] If the integrated unit is implemented as a software program module and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0157] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage device, which may include: a flash drive, a read-only memory, a random access memory, a magnetic disk, or an optical disk, etc.

[0158] The embodiments of this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The description of the above embodiments is only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A pitch control method for a wind turbine generator, characterized in that, The method includes: Obtain the safety operation system information of the target wind turbine, wherein the safety operation system information includes the operating boundary conditions of the wind turbine; The process of obtaining a pitch control model to be deployed for a target wind turbine includes: obtaining an initial pitch control model and a sample dataset; constructing a loss function for the initial pitch control model to obtain a first loss function; adjusting the initial pitch control model using sample data from the sample dataset, and obtaining a reference pitch control model when the first loss function converges; obtaining real-time simulated sample data sent by a simulated wind turbine platform; constructing a loss function for the reference pitch control model to obtain a second loss function; adjusting the reference pitch control model using the real-time simulated sample data, and obtaining the pitch control model to be deployed when the second loss function converges. The pitch control model to be deployed is adjusted according to the safety operation system information. Specifically, the control effect of the pitch control model to be deployed is first debugged under low wind speed and power limitation conditions. Then, the wind speed conditions are gradually increased to debug the pitch control model to be deployed in order to improve the adaptability of the pitch control model to be deployed under different operating conditions. Finally, the target pitch control model is obtained. Obtain the current operating information and current wind speed information of the target wind turbine; The target pitch control model, the current operating information, and the current wind speed information are used to calculate the control parameters to obtain the pitch control parameters of the target wind turbine. The pitch control parameters are used to perform pitch control on the target wind turbine.

2. The pitch control method for wind turbine generators according to claim 1, characterized in that, The second loss function is characterized by the following formula: in, This is the value of the second loss function. For the target load value, To predict load values, To simulate the amount of sample data in real time.

3. The pitch control method for wind turbines according to claim 2, characterized in that, The method further includes: Determine the updated direction information when adjusting the reference pitch control model; The determination of the updated direction information when adjusting the reference pitch control model includes: The updated direction information when adjusting the reference pitch control model is determined using the method shown in the following formula: in, To update direction information, To reference the inverse of the current approximate Hessian matrix in the pitch control model, The second loss function is relative to the reference pitch control model parameters. The gradient.

4. The pitch control method for wind turbine generators according to claim 3, characterized in that, The method further includes: Determine the updated correction matrix when adjusting the reference pitch control model; The determination of the updated correction matrix during the adjustment of the reference pitch control model includes: The correction matrix is ​​determined using the method shown in the following formula: in, It is the change in position. It is the change in gradient. This is the updated correction matrix. Let I be the correction matrix before the update, and let I be the identity matrix.

5. A pitch control device for a wind turbine generator, characterized in that, The device includes: The acquisition unit is used to acquire the safety operation system information of the target wind turbine and the pitch control model to be deployed for the target wind turbine. The adjustment unit is used to adjust the pitch control model to be deployed according to the safety operation system information to obtain the target pitch control model; The second acquisition unit is used to acquire the current operating information and current wind speed information of the target wind turbine. The calculation unit is used to perform control parameter calculations using the target pitch control model, the current operating information, and the current wind speed information to obtain the pitch control parameters of the target wind turbine. A control unit is used to perform pitch control on the target wind turbine using the pitch control parameters; The device can perform the steps of the pitch control method for wind turbines as described in claim 1.

6. The pitch control device for a wind turbine generator according to claim 5, characterized in that, In acquiring the pitch control model to be deployed for the target wind turbine, the acquisition unit is specifically used for: Obtain the initial pitch control model and the sample dataset; Construct the loss function of the initial pitch control model to obtain the first loss function; The initial pitch control model is adjusted using sample data from the sample dataset, and a reference pitch control model is obtained when the first loss function converges. Obtain real-time simulated sample data sent by the simulated wind turbine platform; Construct the loss function of the reference pitch control model to obtain the second loss function; The reference pitch control model is adjusted using the real-time simulated sample data, and the pitch control model to be deployed is obtained when the second loss function converges.

7. The pitch control device for a wind turbine generator according to claim 6, characterized in that, The second loss function is characterized by the following formula: in, This is the value of the second loss function. For the target load value, To predict the load value, n is the number of real-time simulated sample data.

8. A terminal, characterized in that, The system includes a processor, an input device, an output device, and a memory, which are interconnected. The memory is used to store a computer program, which includes program instructions. The processor is configured to invoke the program instructions to perform the method as described in any one of claims 1-4.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a processor, cause the processor to perform the method as described in any one of claims 1-4.

Images