Wind power blade adjusting method, device and equipment based on blade root load and medium

Abstract

The invention relates to the technical field of wind turbine generators, in particular to a wind turbine blade adjusting method, device and equipment based on blade root loads and a medium, and aims to solve the technical problems that when the wind speed or the wind direction changes rapidly, the pitch angle cannot be adjusted in time, the blade loads are sharply increased, and then blades are damaged. In order to achieve the purpose, the method comprises the steps that blade root loads and blade parameters are obtained; inputting the blade load and the blade parameters into a load prediction model to obtain a predicted load; obtaining a pitch angle according to the predicted load; and according to the pitch angle, the wind power blade is adjusted.

Description

Technical Field

[0001] The present application relates to the technical field of wind turbines, and specifically provides a method, device, equipment and medium for adjusting a wind turbine blade based on root load. Background Art

[0002] Currently, with the development of wind turbines towards large-scale, the load borne by the root of the blade has increased sharply. Moreover, during the operation of the wind turbine blade, dynamic loads are generated under the action of the airflow, and this dynamic load will cause the blade to flap and wave.

[0003] In the prior art, the pitch angles of all blades of a wind turbine are usually adjusted uniformly according to a unified pitch control method, that is, the controller of the wind turbine obtains the optimal blade pitch angle based on environmental parameters such as wind speed, wind direction, temperature and the operating state of the wind turbine, and adjusts the current blade pitch angles of all blades to the optimal blade pitch angle. However, when the wind speed or wind direction changes rapidly, the pitch angle cannot be adjusted in time, resulting in a sharp increase in the blade load, and further leading to the technical problem of blade damage.

[0004] Correspondingly, there is a need in the art for a new method for adjusting a wind turbine blade based on root load to solve the above problems. Summary of the Invention

[0005] In order to overcome the above defects, the present application is proposed to provide a solution to solve or at least partially solve the technical problem in the prior art that when the wind speed or wind direction changes rapidly, the pitch angle of the blade cannot be adjusted in time, resulting in a sharp increase in the blade load and further leading to blade damage.

[0006] In a first aspect, the present application provides a method for adjusting a wind turbine blade based on root load, including: Obtain the root load and blade parameters; Input the blade load and the blade parameters into a load prediction model to obtain a predicted load; Obtain a pitch angle according to the predicted load; Adjust the wind turbine blade according to the pitch angle.

[0007] In a technical solution of the above method for adjusting a wind turbine blade based on root load, obtaining the load prediction model includes: Obtain training data and test data; wherein, both the training data and the test data include root load and blade parameters; When training the i-th decision tree, select a data group from the training data and select a preset number of feature variables from the data group; Perform a partitioning process on the splitting points of the i-th decision tree according to the preset number of characteristic variables to obtain nodes, and determine whether the nodes meet the stop partitioning condition; If it is determined that the stop partitioning condition is met, the i-th decision tree is obtained; When it is determined that i = I, stop training; where I is the number of decision trees; Combine the obtained multiple decision trees to obtain the load prediction model.

[0008] In a technical solution of the above method for adjusting a wind turbine blade based on root load, the method further includes: Input a preset time period into the load prediction model to obtain a predicted load; Based on the predicted load and the true load corresponding to the preset time period in the test data, obtain the prediction accuracy; Determine whether the prediction accuracy reaches a preset accuracy; Determine that the prediction accuracy does not reach the preset accuracy, and perform a reconstruction process on the training data to obtain reconstructed training data; Based on the reconstructed training data, retrain the multiple decision trees to obtain multiple updated decision trees; Combine the multiple updated decision trees to obtain an updated load prediction model.

[0009] In a technical solution of the above method for adjusting a wind turbine blade based on root load, the performing a reconstruction process on the training data to obtain reconstructed training data includes: Obtain the test data corresponding to the training data; Perform a fitting process on the frequency domain graph and the time graph of the test data to obtain fitting data; Delete the abnormal data in the fitting data to obtain the reconstructed training data.

[0010] In a technical solution of the above method for adjusting a wind turbine blade based on root load, the obtaining the pitch angle based on the predicted load includes: Based on the predicted load and the preset root length, obtain the out-of-plane bending moment; Based on the out-of-plane bending moment and the azimuth angle of the blade, obtain the pitch bending moment and the yaw bending moment; Based on the pitch bending moment and the yaw bending moment, obtain the first pitch angle control quantity; Perform an inverse transformation process on the first pitch angle control quantity to obtain the pitch angle.

[0011] In one technical solution of the above-mentioned method for adjusting a wind turbine blade based on root load, after obtaining the pitch moment and yaw moment according to the out-of-plane bending moment and the azimuth angle of the blade, the method further includes: Filter the pitch moment and the yaw moment to obtain a filtered pitch moment and a filtered yaw moment; Obtain a second pitch angle control amount according to the filtered pitch moment and the filtered yaw moment; Perform inverse transformation on the second pitch angle control amount to obtain a filtered pitch angle.

[0012] In one technical solution of the above-mentioned method for adjusting a wind turbine blade based on root load, the method further includes: Monitor the root load of the wind turbine blade; Determine whether the root load is greater than a preset load threshold; If it is determined that the root load is greater than the preset load threshold, stop the operation of the wind turbine unit.

[0013] In a second aspect, the present application provides a device for adjusting a wind turbine blade, including: An acquisition module, configured to acquire root load and blade parameters; A prediction module, configured to input the blade load and the blade parameters into a load prediction model to obtain a predicted load; An analysis module, configured to obtain a pitch angle according to the predicted load; An adjustment module, configured to adjust the wind turbine blade according to the pitch angle.

[0014] In a third aspect, the present application provides a device for adjusting a wind turbine blade, including a processor and a storage device. The storage device is adapted to store multiple program codes, and the program codes are adapted to be loaded and run by the processor to execute the method according to any one of the first aspect.

[0015] In a fourth aspect, the present application provides a computer-readable storage medium, in which multiple program codes are stored, and the program codes are adapted to be loaded and run by a processor to execute the method according to any one of the first aspect.

[0016] The present application provides a method, a device, a device and a medium for adjusting a wind turbine blade based on root load. The method specifically includes: acquiring root load and blade parameters; inputting the blade load and the blade parameters into a load prediction model to obtain a predicted load; obtaining a pitch angle according to the predicted load; and adjusting the wind turbine blade according to the pitch angle, so as to reduce the root load and further ensure that the blade will not be damaged. Description of the Drawings

[0017] Referring to the accompanying drawings, the disclosure of the present application will become more readily understandable. It is readily understood by those skilled in the art that these drawings are only for illustrative purposes and are not intended to limit the scope of protection of the present application. In addition, similar numbers in the drawings are used to represent similar components, where: Figure 1 FIG. is a schematic flowchart of the first embodiment of a method for adjusting a wind turbine blade based on root load provided by an embodiment of the present application; Figure 2 FIG. Figure 1 is a schematic flowchart of the second embodiment of a method for adjusting a wind turbine blade based on root load provided by an embodiment of the present application; Figure 3 FIG. is a schematic flowchart of the third embodiment of a method for adjusting a wind turbine blade based on root load provided by an embodiment of the present application; Figure 4 FIG. Figure 2 is a schematic flowchart of the fourth embodiment of a method for adjusting a wind turbine blade based on root load provided by an embodiment of the present application; Figure 5 FIG. is a schematic flowchart of the fifth embodiment of a method for adjusting a wind turbine blade based on root load provided by an embodiment of the present application; Figure 6 FIG. Figure 3 is a schematic flowchart of the sixth embodiment of a method for adjusting a wind turbine blade based on root load provided by an embodiment of the present application; Figure 7 FIG. is a schematic flowchart of the seventh embodiment of a method for adjusting a wind turbine blade based on root load provided by an embodiment of the present application; Figure 8 FIG. Figure 4 is a schematic structural diagram of the first embodiment of a device for adjusting a wind turbine blade provided by an embodiment of the present application; Figure 9 FIG. is a schematic structural diagram of the first embodiment of a device for adjusting a wind turbine blade provided by an embodiment of the present application.

[0018] List of Reference Signs : 11: Acquisition module; 12: Prediction module; 13: Analysis module; 14: Adjustment module; 21: Processor; 22: Memory. Detailed Embodiments

[0019] The following describes some embodiments of the present application with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present application and are not intended to limit the scope of protection of the present application.

[0020] In the description of the present application, a "module" and a "processor" may include hardware, software, or a combination of both. A module may include a hardware circuit, various suitable sensors, communication ports, a memory, and may also include a software part, such as program code, or may be a combination of software and hardware. A processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. The processor has data and / or signal processing functions. The processor may be implemented in software, in hardware, or in a combination of both. A non-transitory computer-readable storage medium includes any suitable medium for storing program code, such as a magnetic disk, a hard disk, an optical disk, a flash memory, a read-only memory, a random access memory, and so on. The term "A and / or B" represents all possible combinations of A and B, such as only A, only B, or A and B. The term "at least one A or B" or "at least one of A and B" has a meaning similar to "A and / or B" and may include only A, only B, or A and B. The singular terms "a" and "the" may also include the plural form.

[0021] In the prior art, by using a unified pitch control method to uniformly adjust the angles of the blades of a wind turbine, the blade angles can be adjusted to the optimal values. However, when the wind speed or wind direction changes rapidly, the unbalanced cyclic load at the blade root increases sharply. At this time, the unified pitch control method cannot quickly adjust the blade angles, resulting in the inability to reduce the unbalanced cyclic load at the blade root, and further leading to the technical problem of blade damage.

[0022] Based on this, in order to solve the above technical problems, the present application provides a method for adjusting a wind turbine blade based on the blade root load to adjust the pitch angle of the wind turbine blade, reduce the blade root load of the wind turbine blade, and further ensure that the blade will not be damaged.

[0023] The technical solution of the present application and how the technical solution of the present application solves the above technical problems will be described in detail below with specific embodiments. These specific embodiments below can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments. The embodiments of the present application will be described below with reference to the accompanying drawings.

[0024] Figure 1 It is a schematic flowchart of Embodiment 1 of a method for adjusting a wind turbine blade based on the blade root load provided by an embodiment of the present application. As Figure 1 shown, specifically, the method includes: Step S101: Obtain the blade root load and blade parameters.

[0025] In this embodiment, the blade root load can be obtained by sensors installed at the blade root.

[0026] In this embodiment, the blade parameters include but are not limited to pitch angle, elevation angle, and rotational speed.

[0027] Step S102: Input the blade load and blade parameters into the load prediction model to obtain the predicted load.

[0028] In this embodiment, based on the training data composed of blade load and blade parameters, training is performed through machine learning algorithms or deep learning algorithms to obtain the load prediction model.

[0029] In this embodiment, input the blade load and blade parameters into the load prediction model to obtain the predicted load within the next few minutes.

[0030] In this embodiment, the predicted load within the next few minutes is used as the load time series. On this load time series, starting from the first value of the load time series with a fixed-length window, the data of this fixed length is input into the load prediction model to obtain the load prediction value at the current moment, and then the predicted load with the earliest time in this time series is deleted.

[0031] Step S103: Obtain the pitch angle according to the predicted load.

[0032] In this embodiment, there is a preset correspondence between the predicted load and the pitch angle. According to the load range where the predicted load is located, the pitch angle corresponding to this load range is obtained.

[0033] Step S104: Adjust the wind turbine blade according to the pitch angle.

[0034] In this embodiment, the wind turbine unit sends this pitch angle to each wind turbine blade, and each wind turbine blade adjusts the wind turbine blade according to this pitch angle.

[0035] In this embodiment, the root load of the blade and the blade parameters are obtained; the blade load and the blade parameters are input into the load prediction model to obtain the predicted load; the pitch angle is obtained according to the predicted load; and the wind turbine blade is adjusted according to the pitch angle. Compared with the prior art, when the wind speed or wind direction changes rapidly and the pitch angle cannot be adjusted in time, resulting in a sharp increase in the blade load and further causing blade damage, in this application, by obtaining the root load of the blade and the blade parameters, inputting the blade load and the blade parameters into the load prediction model to obtain the predicted load, then obtaining the pitch angle according to the predicted load, and adjusting the wind turbine blade according to the pitch angle, it is possible to adjust the pitch angle of the wind turbine blade in time, thereby reducing the load on the blade and ensuring that the blade will not be damaged during operation.

[0036] Figure 2 This is a schematic flowchart of the second embodiment of a method for processing the layout of a wind farm provided by an embodiment of the present application. As Figure 2As shown, specifically, obtaining the load prediction model in step S102 includes: Step S201: Obtain training data and test data.

[0037] In this embodiment, both the training data and the test data include root loads and blade parameters.

[0038] Step S202: When training the i-th decision tree, select a data group from the training data and select a preset number of feature variables from the data group.

[0039] In this embodiment, all the training data is used as the data group, and a preset number of data is randomly selected from the data group as the feature variables.

[0040] Step S203: According to the preset number of feature variables, perform a division process on the splitting point of the i-th decision tree to obtain nodes, and determine whether the nodes meet the stop division condition.

[0041] In this embodiment, for each feature variable, a splitting point is randomly selected for division to generate two nodes, and it is determined whether these two nodes meet the stop division condition.

[0042] In this embodiment, the m-th splitting point is divided according to Formula 1 and Formula 2: (1) (2) Obtain subset Q m l (θ) and subset Q m r (θ). Where θ = (j, t m ) is the division combination, j is the division feature, corresponding to different feature variables in the array, and t m is the randomly divided feature threshold; x is the input data; y is the output data; Q m is the data set on node m.

[0043] In this embodiment, the stop division condition is that the entropy value of the subset is the smallest.

[0044] In this embodiment, according to Formula 3: (3) Obtain the entropy value Entropy of the subset, where pi is the proportion of the i-th type of feature quantity.

[0045] Step S204: If it is determined that the stop division condition is met, obtain the i-th decision tree.

[0046] In this embodiment, when it is determined that the stop division condition is met, a decision tree is obtained.

[0047] Step S205: Stop training when it is determined that i = I.

[0048] In this embodiment, I is the number of decision trees, which is a preset value.

[0049] In this embodiment, for example, the number of decision trees is 120.

[0050] In this embodiment, steps S201 to S204 are repeatedly executed 120 times to train 120 decision trees.

[0051] Step S206: Combine the obtained multiple decision trees to obtain a load prediction model.

[0052] In this embodiment, the multiple decision trees are combined to obtain an extremely randomized forest, and this extremely randomized forest is the load prediction model.

[0053] In this embodiment, training data and test data are obtained; when training the i-th decision tree, a data group is selected from the training data, and a preset number of feature variables are selected from the data group; according to the preset number of feature variables, the splitting points of the i-th decision tree are divided to obtain nodes, and it is determined whether the nodes meet the stop splitting condition; if it is determined that the stop splitting condition is met, the i-th decision tree is obtained; when it is determined that i = I, training stops; the obtained multiple decision trees are combined to obtain a load prediction model, so as to obtain the load prediction model.

[0054] Figure 3 This is a schematic flowchart of the third embodiment of a method for adjusting a wind turbine blade based on root load provided by an embodiment of the present application. On the basis of the above embodiment, as Figure 3 shown, specifically, after step S206, the method further includes: Step S301: Input a preset time period into the load prediction model to obtain a predicted load.

[0055] Step S302: Obtain a prediction accuracy according to the predicted load and the true load corresponding to the preset time period in the test data.

[0056] In this embodiment, according to formula 4: (4) The mean absolute error ε is obtained. Where n represents the number of samples; y i is the predicted load; represents the true load.

[0057] In this embodiment, according to formula 5: (5) The root mean square error ρ is obtained. Where n represents the number of samples, In this embodiment, according to Equation 6: (6) The coefficient of determination R is obtained 2 . Where represents the mean value of the true load.

[0058] Step S303: Determine whether the prediction accuracy reaches a preset accuracy.

[0059] Step S304: Determine that the prediction accuracy does not reach the preset accuracy, reconstruct the training data, and obtain the reconstructed training data.

[0060] In this embodiment, if it is determined that the prediction accuracy does not reach the preset accuracy, the frequency domain diagram and time diagram of the training data obtained by the induction sheet measurement are used to refit the data set, the unreasonable sections in the data set are screened out, and the screened data set is reconstructed.

[0061] Step S305: Re-train multiple decision trees according to the reconstructed training data to obtain multiple updated decision trees.

[0062] In this embodiment, according to the reconstructed data, multiple decision trees are trained according to Steps S202 to S205 to obtain multiple updated decision trees.

[0063] Step S306: Combine multiple updated decision trees to obtain an updated load prediction model.

[0064] In this embodiment, an updated load prediction model is obtained by combining multiple updated decision trees.

[0065] In this embodiment, a preset duration is input into the load prediction model to obtain a predicted load; according to the predicted load and the true load corresponding to the preset duration in the test data, the prediction accuracy is obtained; it is determined whether the prediction accuracy reaches the preset accuracy; it is determined that the prediction accuracy does not reach the preset accuracy, the training data is reconstructed to obtain the reconstructed training data; multiple decision trees are re-trained according to the reconstructed training data to obtain multiple updated decision trees; multiple updated decision trees are combined to obtain an updated load prediction model, so as to improve the prediction accuracy of the load prediction model.

[0066] Figure 4 This is a schematic flowchart of Embodiment 4 of a method for adjusting a wind turbine blade based on root load provided by an embodiment of the present application. As Figure 4 shown, specifically, a specific implementation manner of reconstructing the training data in Step S304 to obtain the reconstructed training data is: Step S401: Obtain test data corresponding to the training data.

[0067] Step S402: Fit the frequency-domain graph and time graph of the test data to obtain the fitted data.

[0068] In this embodiment, the test data includes data in two dimensions, frequency domain and time. By fitting the frequency-domain data and time data, the fitted data is obtained.

[0069] Step S403: Delete the abnormal data in the fitted data to obtain the reconstructed training data.

[0070] In this embodiment, the maximum and minimum values in the fitted data are deleted to obtain the reconstructed training data.

[0071] In this embodiment, the test data corresponding to the training data is obtained; the frequency-domain graph and time graph of the test data are fitted to obtain the fitted data; the abnormal data in the fitted data is deleted to obtain the reconstructed training data.

[0072] Figure 5 It is a schematic flowchart of Embodiment 5 of a method for adjusting a wind turbine blade based on root load provided by an embodiment of the present application. As Figure 5 shown, specifically, a specific implementation manner of step S103 includes: Step S501: Obtain the out-of-plane bending moment according to the predicted load and the preset root length.

[0073] In this embodiment, through the predicted load and the preset root length, a load vector and a root length vector are obtained, and the out-of-plane bending moment is equal to the outer product of the load vector and the root length vector.

[0074] Step S502: Obtain the pitch bending moment and the yaw bending moment according to the out-of-plane bending moment and the azimuth angle of the blade.

[0075] In this embodiment, according to formula 7: (7) the pitch moment M y and the yaw moment M z are obtained. Where θ is the azimuth angle of the blade, M y1 , M y2 , M y3 are the out-of-plane bending moments.

[0076] Step S503: Obtain the first pitch angle control amount according to the pitch bending moment and the yaw bending moment.

[0077] In this embodiment, the pitch bending moment and the yaw bending moment are passed through two independent PI controllers, and according to formula 8 and formula 9: (8) (9) Obtain the first pitch angle control quantity β q (t) and β d (t). Among them, K y p and K y I are respectively the proportional gain and integral gain of the pitch moment under PI control; M ref y is the given pitch moment reference value; K Z p and K z I are respectively the proportional gain and integral gain of the yaw moment under PI control; M ref z is the given yaw moment reference value.

[0078] Step S504: Perform inverse transformation processing on the first pitch angle control quantity to obtain the pitch angle.

[0079] In this embodiment, according to Formula 10: (10) Obtain the pitch angle β 1 、β 2 、β 3 . Among them, β q (t) and β d (t) are the first pitch angle control quantities; θ is the azimuth angle of the blade.

[0080] In this embodiment, according to the predicted load and the preset root length of the blade, obtain the out-of-plane moment; according to the out-of-plane moment and the azimuth angle of the blade, obtain the pitch moment and the yaw moment; according to the pitch moment and the yaw moment, obtain the first pitch angle control quantity; perform inverse transformation processing on the first pitch angle control quantity to obtain the pitch angle.

[0081] Figure 6 This is the flowchart of Embodiment 6 of a method for adjusting a wind turbine blade based on root load provided by an embodiment of the present application. As Figure 6 shown, specifically, after step S502, the method further includes: Step S601: Perform filtering processing on the pitch moment and the yaw moment to obtain the filtered pitch moment and the filtered yaw moment.

[0082] In this embodiment, according to Formula 11 and Formula 12: (11) (12) Obtain the filtered pitch moment My ’ and the filtered yaw moment M z ’ . Among them, T y is the filtering time constant of the pitch moment; T z is the filtering time constant of the yaw moment; s is the complex frequency domain variable; M y is the pitch moment; M z is the yaw moment.

[0083] Step S602: Obtain the second pitch angle control quantity according to the filtered pitch moment and the filtered yaw moment.

[0084] In this embodiment, the filtered pitch moment and the filtered yaw moment are passed through two independent PI controllers, and according to Formula 13 and Formula 14, (13) (14) obtain the second pitch angle control quantities β q * (t) and β d * (t). Among them, K y p and K y I are respectively the proportional gain and the integral gain of the pitch moment under PI control; M ref y is the given reference value of the pitch moment; K Z p and K z I are respectively the proportional gain and the integral gain of the yaw moment under PI control; M ref z is the given reference value of the yaw moment.

[0085] Step S603: Perform inverse transformation processing on the second pitch angle control quantity to obtain the filtered pitch angle.

[0086] In this embodiment, according to Formula 15: (15)

[0087] obtain the filtered pitch angles β 1 * , β 2 * , β 3 * . Among them, β q * (t) and β d *(t) is the second pitch angle control quantity; θ is the azimuth angle of the blade.

[0088] In this embodiment, according to the predicted load and the preset root length, the out-of-plane bending moment is obtained; according to the out-of-plane bending moment and the azimuth angle of the blade, the pitch bending moment and the yaw bending moment are obtained; according to the filtered pitch bending moment and the filtered yaw bending moment, the second pitch angle control quantity is obtained; the second pitch angle control quantity is subjected to an inverse transformation process to obtain the filtered pitch angle.

[0089] Figure 7 It is a schematic flowchart of the seventh embodiment of a wind turbine blade adjustment method based on root load provided by the embodiment of the present application. On the basis of the above embodiment, as Figure 7 shown, specifically, after step S104, the method further includes: Step S701: Monitor the root load of the wind turbine blade.

[0090] In this embodiment, after adjusting the pitch angle of the wind turbine blade, it is necessary to determine the effect of the adjustment. Therefore, it is necessary to monitor the root load of the wind turbine blade.

[0091] Step S702: Determine whether the root load is greater than a preset load threshold.

[0092] In this embodiment, for example, the preset load threshold is 5000 pascals.

[0093] Step S703: If it is determined that the root load is greater than the preset load threshold, stop the operation of the wind turbine unit.

[0094] In this embodiment, if it is determined that the root load is greater than the preset load threshold, stop the rotation of the blade and stop the operation of the equipment inside the wind turbine unit.

[0095] In this embodiment, monitor the root load of the wind turbine blade; determine whether the root load is greater than the preset load threshold; if it is determined that the root load is greater than the preset load threshold, stop the operation of the wind turbine unit to ensure that the root load of the wind turbine blade is within the normal range, thereby ensuring that the wind turbine blade is not damaged.

[0096] It should be noted that although the above embodiments describe the various steps in a specific order, those skilled in the art can understand that in order to achieve the effects of the present application, different steps do not necessarily have to be executed in such an order, and they can be executed simultaneously (in parallel) or in other orders, and these changes are all within the protection scope of the present application.

[0097] Furthermore, the present application also provides a wind turbine blade adjustment device.

[0098] Figure 8The structural schematic diagram of a wind turbine blade adjustment device provided by an embodiment of the present application. As Figure 8 shown, the device in the embodiment of the present application mainly includes an acquisition module 11, a prediction module 12, an analysis module 13, and an adjustment module 14. In some embodiments, one or more of the acquisition module 11, the prediction module 12, the analysis module 13, and the adjustment module 14 may be combined into one module. In some embodiments, the acquisition module 11 may be configured to acquire root loads and blade parameters. The prediction module 12 may be configured to input the blade loads and blade parameters into a load prediction model to obtain predicted loads. The analysis module 13 may be configured to obtain a pitch angle based on the predicted loads. The adjustment module 14 may be configured to adjust the wind turbine blade according to the pitch angle.

[0099] The above wind turbine blade adjustment device is used to execute Figure 1 the method embodiment of wind turbine blade adjustment based on root loads shown. The technical principles, the technical problems solved, and the technical effects produced by the two are similar. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working process and related descriptions of the wind turbine blade adjustment device can refer to the content described in the method embodiment of wind turbine blade adjustment based on root loads, which will not be elaborated here.

[0100] Those skilled in the art can understand that all or part of the processes of the method in an embodiment of the present application can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium that can carry the computer program code. It should be noted that the content included in the computer-readable storage medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, the computer-readable storage medium does not include electrical carrier signals and telecommunication signals.

[0101] Furthermore, the present application also provides a wind turbine blade adjustment device.

[0102] Figure 9 The structural schematic diagram of Embodiment 1 of a wind turbine blade adjustment device provided by an embodiment of the present application. As Figure 9As shown, the wind turbine blade adjustment device includes at least one processor 21 and a memory 22. The memory 22 can be configured to store a program for executing the wind turbine blade adjustment method based on root load in the above Figures 1 to 7 shown embodiment. The processor 21 can be configured to execute the program in the memory 22. This program includes, but is not limited to, a program for executing a wind turbine blade adjustment method based on root load in the above method embodiment. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The wind turbine blade adjustment device can be a control device formed by various electronic devices.

[0103] Furthermore, the present application also provides a computer-readable storage medium. In an embodiment of a computer-readable storage medium according to the present application, the computer-readable storage medium can be configured to store a program for executing the wind turbine blade adjustment method based on root load in the above method embodiment. This program can be loaded and run by a processor to implement the above wind turbine blade adjustment method based on root load. For the sake of convenience of description, only the parts related to the embodiments of the present application are shown. For the specific technical details not disclosed, please refer to the method part of the embodiments of the present application. The computer-readable storage medium can be a storage device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiments of the present application is a non-transitory computer-readable storage medium.

[0104] Furthermore, it should be understood that since the setting of each module is only for explaining the functional units of the device of the present application, the physical devices corresponding to these modules can be the processor itself, or a part of the software in the processor, a part of the hardware, or a part of the combination of software and hardware. Therefore, the number of each module in the figure is only illustrative.

[0105] Those skilled in the art can understand that the various modules in the device can be adaptively split or combined. Such splitting or combination of specific modules will not cause the technical solution to deviate from the principle of the present application. Therefore, the technical solutions after splitting or combination will all fall within the protection scope of the present application.

[0106] So far, the technical solution of the present application has been described in combination with the preferred embodiments shown in the drawings. However, those skilled in the art can easily understand that the protection scope of the present application is obviously not limited to these specific embodiments. Without departing from the principle of the present application, those skilled in the art can make equivalent changes or substitutions to the relevant technical features. The technical solutions after these changes or substitutions will all fall within the protection scope of the present application.

Claims

1. A method for adjusting wind turbine blades based on blade root load, characterized in that: include: Obtain blade root loads and blade parameters; Inputting the blade load and the blade parameters into a load prediction model to obtain a predicted load; According to the predicted load, a pitch angle is obtained; The wind turbine blades are adjusted according to the pitch angle.

2. The method according to claim 1, characterized in that Acquiring the load prediction model includes: Acquire training data and test data; wherein the training data and the test data both include blade root loads and blade parameters; When training the i-th decision tree, a data group is selected from the training data, and a preset number of feature variables are selected from the data group; According to the preset number of characteristic variables, the splitting point of the i-th decision tree is divided to obtain a node, and whether the node satisfies a stop division condition is determined; If it is determined that the stop partitioning condition is met, then the i-th decision tree is obtained; When it is determined that i=I, stop training; where I is the number of decision trees; The obtained multiple decision trees are combined to obtain the load prediction model.

3. The method according to claim 2, characterized in that The method further comprises: Inputting the preset duration into the load prediction model to obtain a predicted load; Obtaining prediction accuracy according to the predicted load and the actual load corresponding to the preset time length in the test data; Determining whether the prediction accuracy reaches a preset accuracy; Determining that the prediction accuracy does not reach the preset accuracy, reconstructing the training data to obtain reconstructed training data; Retraining the multiple decision trees according to the reconstructed training data to obtain multiple updated decision trees; The multiple updated decision trees are combined to obtain an updated load prediction model.

4. The method according to claim 3, characterized in that The reconstructing the training data to obtain reconstructed training data includes: Acquire test data corresponding to the training data; Performing fitting processing on the frequency domain graph and the time graph of the test data to obtain fitting data; The abnormal data in the fitting data is deleted to obtain the reconstructed training data.

5. The method according to claim 1, characterized in that: The step of obtaining a pitch angle according to the predicted load comprises: According to the predicted load and the preset blade root length, an out-of-plane bending moment is obtained; Obtaining a pitch bending moment and a yaw bending moment according to the out-of-plane bending moment and the azimuth angle of the blade; Obtaining a first pitch angle control amount according to the pitch bending moment and the yaw bending moment; The first pitch angle control amount is inversely transformed to obtain the pitch angle.

6. The method according to claim 5, characterized in that After obtaining the pitch bending moment and the yaw bending moment according to the out-of-plane bending moment and the azimuth angle of the blade, the method further comprises: Filtering the pitch bending moment and the yaw bending moment to obtain a filtered pitch bending moment and a filtered yaw bending moment; Obtaining a second pitch angle control amount according to the filtered pitch bending moment and the filtered yaw bending moment; The second pitch angle control amount is inversely transformed to obtain a filtered pitch angle.

7. The method according to claim 1, characterized in that The method further comprises: Monitoring the blade root load of the wind turbine blade; Determining whether the blade root load is greater than a preset load threshold; If it is determined that the blade root load is greater than the preset load threshold, the wind turbine generator set is shut down.

8. A wind turbine blade adjustment device, characterized in that: include: An acquisition module, used for acquiring blade root load and blade parameters; A prediction module, used for inputting the blade load and the blade parameters into a load prediction model to obtain a predicted load; An analysis module, used for obtaining a pitch angle according to the predicted load; The adjustment module is used to adjust the wind turbine blade according to the pitch angle.

9. A wind turbine blade adjustment device, comprising a processor and a storage device, wherein the storage device is suitable for storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and executed by the processor to perform the method of any one of claims 1 to 7.

10. A computer-readable storage medium storing a plurality of program codes, characterized in that: The program code is suitable for being loaded and executed by a processor to execute the method according to any one of claims 1 to 7.

Images