Blade root load prediction method, device and equipment of wind turbine generator and medium

Abstract

The invention relates to the technical field of wind turbine generators, particularly provides a blade root load prediction method, device and equipment of a wind turbine generator and a medium, and aims to solve the technical problem that when the load of a blade root is too large, due to the fact that operation parameters of the wind turbine generator cannot be adjusted in time, the blade root operates in an overload mode, and then the blade is damaged. In order to achieve the purpose, the method comprises the steps that blade root load data and wind turbine generator parameters are obtained; inputting the blade root load data and the wind turbine generator parameters into a preset blade root load prediction model to obtain a predicted blade root load within a preset time; and adjusting operation parameters of the wind turbine generator according to the predicted blade root load.

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 predicting the root load of a wind turbine blade. Background Art

[0002] Currently, with the development of wind turbines towards large-scale, the aspect ratio and structural toughness of wind turbine blades have increased sharply, which will cause stall flutter of ultra-long flexible blades, and then lead to blade damage.

[0003] In the prior art, load data of the blade root is collected by sensors arranged at the blade root, and then the operating parameters of the wind turbine are adjusted according to the load data of the blade root and the operating data of the wind turbine. To a certain extent, the normal operation of the wind turbine can be ensured. However, when the load of the blade root is too large, due to the inability to adjust the operating parameters of the wind turbine in time, the blade root operates overloaded, and then the technical problem of blade damage is caused.

[0004] Correspondingly, there is a need for a new method for predicting the root load of a wind turbine in this field 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 load of the blade root is too large, due to the inability to adjust the operating parameters of the wind turbine in time, the blade root operates overloaded, and then blade damage is caused.

[0006] In a first aspect, the present application provides a method for predicting the root load of a wind turbine, including: Obtain the root load data and the wind turbine parameters; Input the root load data and the wind turbine parameters into a preset root load prediction model to obtain the predicted root load within a preset time; wherein, the predicted root load includes the root average load, the root ultimate load, the number of cycles, and the predicted equivalent fatigue load; Adjust and process the operating parameters of the wind turbine according to the predicted root load; Wherein, obtaining the preset root load prediction model includes: Obtain training data; wherein, the training data includes the root load and the wind turbine data; 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; According to the preset number of feature variables, divide the splitting point of the i-th decision tree to obtain nodes, and determine whether the nodes meet the stop division condition; If it is determined that the stopping division condition is satisfied, 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 preset root load prediction model.

[0007] In a technical solution of the above root load prediction method for a wind turbine, obtaining the root load includes: Obtain the flap strain signal and the lead-lag strain signal of the root; According to the flap strain signal and the lead-lag strain signal, obtain the flap moment and the lead-lag moment of the blade; According to the flap moment and the lead-lag moment of the blade, obtain the maximum load, the average load, and the number of load cycles; According to the maximum load and the number of load cycles, obtain the equivalent fatigue load; Combine the equivalent fatigue load, the average load, and the maximum load to obtain the root load.

[0008] In a technical solution of the above root load prediction method for a wind turbine, obtaining the wind turbine data includes: Obtain the initial parameters of the wind turbine; Perform screening processing on the initial parameters of the wind turbine to obtain the wind turbine data.

[0009] In a technical solution of the above root load prediction method for a wind turbine, the performing screening processing on the initial parameters of the wind turbine to obtain the wind turbine data includes: Perform correlation analysis on multiple parameters in the initial parameters of the wind turbine respectively with the root load to obtain a set of correlation coefficients; Compare multiple correlation coefficients in the set of correlation coefficients with a preset correlation coefficient threshold respectively; Obtain a subset of correlation coefficients corresponding to those greater than the preset correlation coefficient threshold; Match the subset of correlation coefficients with the initial parameters of the wind turbine to obtain the wind turbine data.

[0010] In a technical solution of the above root load prediction method for a wind turbine, after combining the obtained multiple decision trees to obtain the preset root load prediction model, the method further includes: Obtain the true root load; According to the true root load and the predicted root load, obtain the accuracy value of the preset root load prediction model; If it is determined that the accurate value is lower than a preset accurate threshold, the training data is screened to obtain a screened data set; According to the screened data set, a blade root load prediction update model is obtained.

[0011] In a technical solution of the above blade root load prediction method for a wind turbine, after inputting the blade root load data and the wind turbine parameters into a preset blade root load prediction model to obtain a predicted blade root load within a preset time, the method further includes: In the i-th iteration, an equivalent fatigue load calculation value is obtained according to the blade root ultimate load and the number of cycles; According to the predicted equivalent fatigue load and the equivalent fatigue load calculation value, an equivalent fatigue load error value is obtained; Determine whether the equivalent fatigue load error value is greater than a preset error value; If it is determined that the equivalent fatigue load error value is greater than the preset error value, the (i - 1)-th blade root load prediction model is retrained to obtain the i-th blade root load prediction model; where when i = 1, the (i - 1)-th blade root load prediction model is the preset blade root load prediction model; Where 0 < i ≤ I, and when the equivalent fatigue load error value is less than the preset error value, the I-th preset blade root load prediction model is obtained.

[0012] In a technical solution of the above blade root load prediction method for a wind turbine, the method further includes: Determine that the adjustment process of the operating parameters of the wind turbine is completed; Monitor the blade root load data; If it is determined that the blade root load data is greater than a preset blade root load, the wind turbine is shut down.

[0013] In a second aspect, the present application provides a blade root load prediction device for a wind turbine, including: An acquisition module, configured to acquire blade root load data and wind turbine parameters; A processing module, configured to input the blade root load data and the wind turbine parameters into a preset blade root load prediction model to obtain a predicted blade root load within a preset time; where the predicted blade root load includes a blade root average load, a blade root ultimate load, the number of cycles, and a predicted equivalent fatigue load; An analysis module, configured to adjust the operating parameters of the wind turbine according to the predicted blade root load; Where obtaining the preset blade root load prediction model includes: Obtain training data; where the training data includes blade root load and wind turbine data; 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; According to the preset number of feature variables, perform division processing on the splitting points of the i-th decision tree to obtain nodes, and determine whether the nodes meet the stop division condition; If it is determined that the stop division condition is met, obtain the i-th decision tree; When it is determined that i = I, stop training; where I is the number of decision trees; Perform combination processing on the obtained multiple decision trees to obtain the preset blade root load prediction model.

[0014] In a third aspect, the present application provides a blade root load prediction device, 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 described in any one of the first aspects.

[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 described in any one of the first aspects.

[0016] The present application provides a method, device, equipment and medium for predicting the blade root load of a wind turbine. The method specifically includes: obtaining blade root load data and wind turbine parameters; inputting the blade root load data and the wind turbine parameters into a preset blade root load prediction model to obtain the predicted blade root load within a preset time; where the predicted blade root load includes the blade root average load, the blade root ultimate load, the number of cycles, and the predicted equivalent fatigue load; adjusting the operating parameters of the wind turbine according to the predicted blade root load; where obtaining the preset blade root load prediction model includes: obtaining training data; where the training data includes blade root load and wind turbine data; 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; according to the preset number of feature variables, perform division processing on the splitting points of the i-th decision tree to obtain nodes, and determine whether the nodes meet the stop division condition; if it is determined that the stop division condition is met, obtain the i-th decision tree; when it is determined that i = I, stop training; where I is the number of decision trees; perform combination processing on the obtained multiple decision trees to obtain the preset blade root load prediction model, so that the blade operates within the normal load range, thereby ensuring the normal operation of the wind turbine. Description of the Drawings

[0017] Referring to the accompanying drawings, the disclosure of the present application will become more readily understandable. It is easily 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 It is a schematic flowchart of the first embodiment of a method for predicting blade root loads of a wind turbine provided by an embodiment of the present application; Figure 2 It is a schematic flowchart of the second embodiment of a method for predicting blade root loads of a wind turbine provided by an embodiment of the present application; Figure 3 It is a schematic flowchart of the third embodiment of a method for predicting blade root loads of a wind turbine provided by an embodiment of the present application; Figure 4 It is a schematic flowchart of the fourth embodiment of a method for predicting blade root loads of a wind turbine provided by an embodiment of the present application; Figure 5 It is a schematic flowchart of the fifth embodiment of a method for predicting blade root loads of a wind turbine provided by an embodiment of the present application; Figure 6 It is a schematic flowchart of the sixth embodiment of a method for predicting blade root loads of a wind turbine provided by an embodiment of the present application.

[0018] Figure 7 It is a schematic flowchart of the seventh embodiment of a method for predicting blade root loads of a wind turbine provided by an embodiment of the present application; Figure 8 It is a schematic flowchart of the eighth embodiment of a method for predicting blade root loads of a wind turbine provided by an embodiment of the present application; Figure 9 It is a schematic structural diagram of the first embodiment of a device for predicting blade root loads of a wind turbine provided by an embodiment of the present application; Figure 10 It is a schematic structural diagram of the first embodiment of a device for predicting blade root loads provided by an embodiment of the present application.

[0019] List of Reference Signs : 11: Acquisition module; 12: Processing module; 13: Analysis module; 21: Processor; 22: Memory. Detailed implementation manners

[0020] 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.

[0021] In the description of the present application, "module" and "processor" may include hardware, software, or a combination of both. A module may include a hardware circuit, various appropriate sensors, communication ports, 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 magnetic disks, hard disks, optical disks, flash memories, read-only memories, random access memories, and the like. 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 of 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.

[0022] In the prior art, the load on the blade root of a wind turbine is monitored in real time to obtain real-time data, and an operator sends a control instruction to the wind turbine according to the real-time data to enable the normal operation of the wind turbine. However, when the load on the blade root is too large, since the operating parameters of the wind turbine cannot be adjusted in time, the blade root operates overloaded, which in turn leads to the technical problem of blade damage.

[0023] Based on this, in order to solve the above technical problems, the present application provides a method for predicting the blade root load of a wind turbine to adjust the operating parameters of the wind turbine according to the prediction result of the blade root, thereby ensuring that the blade operates within the normal load range.

[0024] 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.

[0025] Figure 1 It is a schematic flowchart of the first embodiment of a method for predicting the blade root load of a wind turbine provided by an embodiment of the present application. As Figure 1 shown, specifically, the method includes: Step S101: Obtain blade root load data and wind turbine parameters.

[0026] In this embodiment, the electrical signal of the blade root is obtained through the sensor at the blade root, and then the electrical signal is converted into blade root load data.

[0027] In this embodiment, the wind turbine parameters include environmental parameters, blade parameters, operating parameters, and load parameters. Among them, the environmental parameters include wind speed, wind direction, temperature, and humidity; the blade parameters include the size and shape of the blades; the operating parameters include blade rotation speed, pitch angle, and wind turbine tilt angle; the load parameters include the bending moment, shear force, and torque at the blade root.

[0028] Step S102: Input the blade root load data and the wind turbine parameters into a preset blade root load prediction model to obtain the predicted blade root load within a preset time.

[0029] In this embodiment, the predicted blade root load includes the average blade root load, the ultimate blade root load, the number of cycles, and the predicted equivalent fatigue load.

[0030] In this embodiment, after inputting the current blade root load data and the current wind turbine parameters into the preset blade root load prediction model, a predicted blade root model within a preset time is obtained. Among them, the preset blade root load prediction model can be obtained by training the data.

[0031] Step S103: Adjust the operating parameters of the wind turbine according to the predicted blade root load.

[0032] In this embodiment, by analyzing the predicted blade root load, the blade rotation speed adjustment value, the pitch angle adjustment value, and the wind turbine tilt angle adjustment value are obtained, and the blade rotation speed, pitch angle, and wind turbine tilt angle are adjusted according to the blade rotation speed adjustment value, the pitch angle adjustment value, and the wind turbine tilt angle adjustment value.

[0033] In this embodiment, the blade root load data and the wind turbine parameters are obtained; the blade root load data and the wind turbine parameters are input into a preset blade root load prediction model to obtain the predicted blade root load within a preset time; the operating parameters of the wind turbine are adjusted according to the predicted blade root load. Compared with the prior art, since the operating parameters of the wind turbine cannot be adjusted in time, resulting in overloading of the blade root and further blade damage, in this application, the obtained blade root load data and the wind turbine parameters are input into a preset blade root load prediction model to obtain the predicted blade root load within a preset time, and the operating parameters of the wind turbine are adjusted according to the predicted blade root load, so as to ensure that the blade will not operate overloaded and further ensure the normal operation of the wind turbine.

[0034] Figure 2 This is a schematic flowchart of the second embodiment of a method for predicting the blade root load of a wind turbine provided by an embodiment of the present application. As Figure 2 shown, specifically, obtaining the preset blade root load prediction model in step S102 includes: Step S201: Obtain training data; the training data includes blade root load and wind turbine data.

[0035] 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.

[0036] In this embodiment, all the training data is used as the data group, and a preset number of feature variables are randomly selected from the data group.

[0037] 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.

[0038] In this embodiment, for each feature variable, randomly select a splitting point for division, generate two nodes, and determine whether these two nodes meet the stop division condition.

[0039] 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 Q m r (θ) subset. Where θ = (j, t m ) is the division combination, j is the division feature, corresponding to different feature variables in the array, t m is the feature threshold randomly divided; x is the input data; y is the output data; Q m is the data set on node m.

[0040] In this embodiment, the stop division condition is that the entropy value of the subset is the smallest.

[0041] 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.

[0042] Step S204: If it is determined that the stop division condition is met, obtain the i-th decision tree.

[0043] In this embodiment, when it is determined that the stop division condition is met, a decision tree is obtained.

[0044] Step S205: When it is determined that i = I, stop training.

[0045] In this embodiment, I is the number of decision trees, which is a preset value.

[0046] In this embodiment, for example, the number of decision trees is 150.

[0047] In this embodiment, steps S201 to S204 are repeatedly executed to train multiple decision trees.

[0048] Step S206: Combine the obtained multiple decision trees to obtain a preset blade root load prediction model.

[0049] In this embodiment, multiple decision trees are combined to obtain an extreme random forest, which is the preset blade root load prediction model.

[0050] In this embodiment, training data is 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, multiple nodes of the i-th decision tree are divided to obtain nodes, and it is determined whether the nodes meet the stop division condition; if it is determined that the stop division 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 preset blade root load prediction model, and thus a preset blade root load prediction model is obtained.

[0051] Figure 3 This is a schematic flowchart of the third embodiment of a method for predicting the blade root load of a wind turbine provided by an embodiment of the present application. On the basis of the above embodiments, as Figure 3 shown, specifically, obtaining the blade root load in step S201 includes: Step S301: Obtain the flapping strain signal and the pitching strain signal of the blade root.

[0052] In this embodiment, the flapping strain signal and the pitching strain signal are collected by sensors.

[0053] In this embodiment, under the wind condition where the ratio of the wind load to the gravity load is small, the gravity method is adopted. The wind turbine rotor is idled or the blade is fixed in the horizontal position under different pitch angles, and the sensor is placed under the typical gravity moment, so as to realize the calibration of the sensor position.

[0054] Step S302: Obtain the blade flapping moment and the blade pitching moment according to the flapping strain signal and the pitching strain signal.

[0055] In this embodiment, according to formula 4: (4) the blade flapping moment M be and the blade pitching moment M bf . Where D 11 represents the calibration coefficient between the flapping strain signal and the flapping moment; D 12Denote the calibration coefficient between the flapping strain signal and the flapping moment; D 21 Denote the calibration coefficient between the lag strain signal and the flapping moment; D 22 Denote the calibration coefficient between the flapping strain signal and the flapping moment; S e Denote the lag strain signal; S f Denote the flapping strain signal; O e Denote the offset in the lag direction, which represents the output offset of the strain gauge in the lag direction when there is no external moment acting. O f Denote the offset in the flapping direction, which represents the output offset of the strain gauge in the flapping direction when there is no external moment acting.

[0056] Step S303: Obtain the maximum load, average load, and load cycle count based on the blade lag moment and the blade flapping moment.

[0057] In this embodiment, using the rainflow counting method, obtain the maximum load, average load, and load cycle count based on the blade lag moment and the blade flapping moment.

[0058] Step S304: Obtain the equivalent fatigue load based on the maximum load and the load cycle count.

[0059] In this embodiment, according to Equation 5: (5) Obtain the equivalent fatigue load L eq . Wherein, L i m Denote the m-th power of the maximum load of the i-th level; n i Denote the load cycle count of the i-th level; N eq Denote the load cycle count; m is the curve slope of the material stress and life.

[0060] Step S305: Combine the equivalent fatigue load, average load, and maximum load to obtain the root load of the blade.

[0061] In this embodiment, combine the equivalent fatigue load, average load, and maximum load into one data to obtain the root load of the blade.

[0062] In this embodiment, for example, the root load of the blade is {equivalent fatigue load; average load; maximum load}.

[0063] In this embodiment, the pitching strain signal and the flapping strain signal of the blade root are obtained; according to the pitching strain signal and the flapping strain signal, the blade pitching moment and the blade flapping moment are obtained; according to the blade pitching moment and the blade flapping moment, the maximum load, the average load and the load cycle times are obtained; according to the maximum load and the load cycle times, the equivalent fatigue load is obtained; the equivalent fatigue load, the average load and the maximum load are combined to obtain the blade root load, and then the accurate value of the blade root load can be obtained.

[0064] Figure 4 FIG. 4 is a schematic flow chart of Embodiment 4 of a method for predicting the blade root load of a wind turbine provided by an embodiment of the present application. As Figure 4 shown, specifically, obtaining the wind turbine data in step S201 includes: Step S401: Obtain the initial parameters of the wind turbine.

[0065] Step S402: Perform screening processing on the initial parameters of the wind turbine to obtain the wind turbine data.

[0066] In this embodiment, the minimum value and the maximum value in the initial parameters of the wind turbine are deleted to obtain the wind turbine data.

[0067] In this embodiment, the initial parameters of the wind turbine are obtained; the initial parameters of the wind turbine are subjected to screening processing to obtain the wind turbine data.

[0068] Figure 5 FIG. 5 is a schematic flow chart of Embodiment 5 of a method for predicting the blade root load of a wind turbine provided by an embodiment of the present application. As Figure 5 shown, specifically, a specific implementation manner of step S402 includes: Step S501: Perform correlation analysis on multiple parameters in the initial parameters of the wind turbine with the blade root load respectively to obtain a set of correlation coefficients.

[0069] In this embodiment, according to formula 6: (6) the correlation coefficient ρ X,Y is obtained. Wherein, X is a parameter; Y is the blade root load; ρ X is the standard deviation of the parameter; ρ Y is the standard deviation of the blade root load; cov(X, Y) is the covariance between X and Y.

[0070] In this embodiment, multiple parameters are respectively calculated according to formula 6 to obtain multiple correlation coefficients, and the multiple correlation coefficients are combined into a set of correlation coefficients.

[0071] Step S502: Compare and process each of the multiple correlation coefficients in the set of correlation coefficients with a preset correlation coefficient threshold.

[0072] In this embodiment, multiple correlation coefficients in the correlation coefficient set are taken out one by one and compared with a preset correlation coefficient threshold.

[0073] In this embodiment, for example, the correlation coefficient threshold is 0.6.

[0074] Step S503: Obtain a subset of correlation coefficients corresponding to those greater than the preset correlation coefficient threshold.

[0075] In this embodiment, the correlation coefficients greater than the preset correlation coefficient threshold are extracted from the correlation coefficient set to obtain a subset of correlation coefficients.

[0076] In this embodiment, when the correlation coefficient is greater than the preset correlation coefficient threshold, the current parameter is strongly correlated with the blade root load; when the correlation coefficient is greater than 0.2 and less than 0.6, the current parameter is moderately correlated with the blade root load; when the correlation coefficient is less than 0.2, the current parameter is weakly correlated or not correlated with the blade root load.

[0077] In this embodiment, the preset correlation coefficient threshold can be selected within the range greater than 0 and less than 1 as needed.

[0078] Step S504: Match the subset of correlation coefficients with the initial parameters of the wind turbine to obtain wind turbine data.

[0079] In this embodiment, the coefficients in the subset of correlation coefficients are respectively matched with the initial parameters of the wind turbine to obtain wind turbine data.

[0080] In this embodiment, the wind turbine data includes multiple wind turbine parameters.

[0081] In this embodiment, multiple parameters in the initial parameters of the wind turbine are respectively subjected to correlation analysis with the blade root load to obtain a set of correlation coefficients; multiple correlation coefficients in the set of correlation coefficients are respectively compared with a preset correlation coefficient threshold; a subset of correlation coefficients corresponding to those greater than the preset correlation coefficient threshold is obtained; the subset of correlation coefficients is matched with the initial parameters of the wind turbine to obtain wind turbine data, and further obtain wind turbine data with a high correlation with the blade root load.

[0082] Figure 6 It is a schematic flowchart of the sixth embodiment of a method for predicting the blade root load of a wind turbine provided by an embodiment of the present application. As Figure 6 shown, specifically, after step S206, the method further includes: Step S601: Obtain the true blade root load.

[0083] In this embodiment, the true blade root load is the data in the test dataset.

[0084] Step S602: Obtain the accurate value of the preset blade root load prediction model according to the actual blade root load and the predicted blade root load.

[0085] In this embodiment, according to Formula 7: (7) Obtain the mean absolute error ε. Where n represents the number of samples; y i is the predicted blade root load; represents the actual blade root load.

[0086] In this embodiment, according to Formula 8: (8) Obtain the root mean square error ρ.

[0087] In this embodiment, according to Formula 9: (9) Obtain the coefficient of determination R 2 . Where represents the mean value of the actual blade root load.

[0088] In this embodiment, since the actual blade root load is the blade root load within a preset time, there are multiple blade root load values for this actual blade root load.

[0089] In this embodiment, the mean absolute error or the root mean square error or the coefficient of determination can be used as the accurate value of the preset blade root load prediction model.

[0090] Step S603: If it is determined that the accurate value is lower than the preset accurate threshold, perform screening processing on the training data to obtain a screened data set.

[0091] In this embodiment, if it is determined that the accurate value is lower than the preset accurate threshold, re-fit the data set through the frequency domain diagram and time diagram of the data obtained by the induction sheet, screen out the unreasonable sections in the data set, and reconstruct the screened data set.

[0092] Step S604: Obtain a blade root load prediction update model according to the screened data set.

[0093] In this embodiment, use the screened data set to train according to the method of Embodiment 2 to obtain a blade root load prediction update model, and then obtain the accurate value of this blade root load prediction update model again. If it is determined that the accurate value is higher than the preset accurate threshold, obtain the prediction result.

[0094] In this embodiment, the true root load is obtained; according to the true root load and the predicted root load, the accurate value of the preset root load prediction model is obtained; if it is determined that the accurate value is lower than the preset accurate threshold, the training data is screened to obtain a screened data set; according to the screened data set, a root load prediction update model is obtained, and thus a more accurate root load prediction model can be obtained.

[0095] Figure 7 FIG. 7 is a schematic flow chart of Embodiment 7 of a method for predicting the root load of a wind turbine provided by an embodiment of the present application. As Figure 7 shown, specifically, after step S102, the method further includes: Step S701: In the i-th iteration, according to the root ultimate load and the number of cycles, an equivalent fatigue load calculation value is obtained.

[0096] In this embodiment, the root ultimate load and the number of cycles are substituted into Formula 5 to obtain an equivalent fatigue load calculation value.

[0097] Step S702: According to the predicted equivalent fatigue load and the equivalent fatigue load calculation value, an equivalent fatigue load error value is obtained.

[0098] In this embodiment, the predicted equivalent fatigue load and the equivalent fatigue load calculation value are subtracted to obtain a difference, and this difference is the equivalent fatigue load error value.

[0099] In this embodiment, according to the equivalent fatigue load error value, the accuracy of the predicted equivalent fatigue load can be judged, that is, the smaller the equivalent fatigue load error value, the higher the accuracy of the predicted equivalent fatigue load, and the larger the equivalent fatigue load error value, the lower the accuracy of the predicted equivalent fatigue load.

[0100] Step S703: Judge whether the equivalent fatigue load error value is greater than a preset error value.

[0101] Step S704: Determine that the equivalent fatigue load error value is greater than the preset error value, and retrain the (i - 1)-th root load prediction model to obtain the i-th preset root load prediction model.

[0102] In this embodiment, when i = 1, the (i - 1)-th root load prediction model is the preset root load prediction model.

[0103] In this embodiment, if it is determined that the equivalent fatigue load error value is greater than the preset error value, the (i - 1)-th root load prediction model is retrained according to steps S201 to S206.

[0104] In this embodiment, 0 < i ≤ I, where I is the number of times when the equivalent fatigue load error value is less than the preset error value, and the I-th preset root load prediction model is obtained.

[0105] In this embodiment, in the i-th iteration, according to the root limit load and the number of cycles, the calculated value of the equivalent fatigue load is obtained; according to the predicted equivalent fatigue load and the calculated value of the equivalent fatigue load, the error value of the equivalent fatigue load is obtained; it is determined whether the error value of the equivalent fatigue load is greater than the preset error value; it is determined that the error value of the equivalent fatigue load is greater than the preset error value, and the root load prediction model of the (i - 1)-th stage is retrained to obtain the root load prediction model of the i-th stage, so as to obtain a root load prediction model with high prediction accuracy.

[0106] Figure 8 This is a schematic flowchart of the eighth embodiment of a method for predicting the root load of a wind turbine provided by an embodiment of the present application. As Figure 8 shown, specifically, after step S103, the method further includes: Step S801: Determine that the adjustment process of the operating parameters of the wind turbine is completed.

[0107] In this embodiment, after determining that the adjustment process of the operating parameters of the wind turbine is completed, a completion message is obtained, and based on this completion message, it is determined that the adjustment process of the operating parameters of the wind turbine is completed.

[0108] Step S802: Monitor the root load data.

[0109] In this embodiment, after the adjustment process of the operating parameters of the wind turbine is completed, in order to determine the change in the root load after adjustment, it is necessary to monitor the root load data.

[0110] Step S803: Determine that the root load data is greater than the preset root load, and stop the operation of the wind turbine.

[0111] In this embodiment, after the adjustment process of the operating parameters of the wind turbine is completed, if the monitored root load data is greater than the preset root load, in order to avoid damage to the blade caused by excessive root load, it is necessary to stop the operation of the wind turbine.

[0112] In this embodiment, it is determined that the adjustment process of the operating parameters of the wind turbine is completed; the root load data is monitored; it is determined that the root load data is greater than the preset root load, and the operation of the wind turbine is stopped to ensure the stable operation of the wind turbine.

[0113] 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, it is not necessary for different steps to be executed in such an order. They can be executed simultaneously (in parallel) or in other orders, and these variations are all within the protection scope of the present application.

[0114] Furthermore, the present application also provides a device for predicting the root load of a wind turbine.

[0115] Figure 9 It is a schematic structural diagram of the first embodiment of a device for predicting the root load of a wind turbine provided by an embodiment of the present application. As Figure 9 shown, the device in the embodiment of the present application mainly includes an acquisition module 11, a processing module 12, and an analysis module 13. In some embodiments, one or more of the acquisition module 11, the processing module 12, and the analysis module 13 can be combined into one module. In some embodiments, the acquisition module 11 can be configured to acquire root load data and wind turbine parameters. The processing module 12 can be configured to input the root load data and wind turbine parameters into a preset root load prediction model to obtain the predicted root load within a preset time; wherein, the predicted root load includes the root average load, the root ultimate load, the number of cycles, and the predicted equivalent fatigue load. The analysis module 13 can be configured to adjust and process the operating parameters of the wind turbine according to the predicted root load. Among them, obtaining the preset root load prediction model includes: obtaining training data; wherein, the training data includes root load and wind turbine data; when training the i-th decision tree, selecting a data group from the training data and selecting a preset number of feature variables from the data group; dividing the splitting point of the i-th decision tree according to the preset number of feature variables to obtain nodes, and determining whether the nodes meet the stop division condition; if it is determined that the stop division condition is met, obtaining the i-th decision tree; when it is determined that i = I, stop training; wherein, I is the number of decision trees; combining the obtained multiple decision trees to obtain a preset root load prediction model.

[0116] The above device for predicting the root load of a wind turbine is used to execute Figure 1 the embodiment of the method for predicting the root load of a wind turbine shown. The technical principles, the technical problems solved, and the technical effects produced by the two are similar. Those skilled in the art of the present technology can clearly understand that for the convenience and conciseness of description, the specific working process and related descriptions of the device for predicting the root load of a wind turbine can refer to the content described in the embodiment of the method for predicting the root load of a wind turbine, which will not be elaborated here.

[0117] Those skilled in the art can understand that all or part of the processes in the methods of the above embodiments 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.

[0118] Furthermore, the present application also provides a blade root load prediction device.

[0119] Figure 10 It is a schematic structural diagram of Embodiment 1 of a blade root load prediction device provided by an embodiment of the present application. As Figure 10 shown, the blade root load prediction device includes at least one processor 21 and a memory 22. The memory 22 can be configured to store a program for executing the blade root load prediction method of the wind turbine unit in the above Figures 1 to 8 shown embodiment. The processor 21 can be configured to execute the program in the memory 22. The program includes, but is not limited to, a program for executing a blade root load prediction method of a wind turbine unit 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 blade root load prediction device can be a control device formed by various electronic devices.

[0120] 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 blade root load prediction method of the wind turbine unit in the above method embodiment. The program can be loaded and run by a processor to implement the blade root load prediction method of the wind turbine unit. 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.

[0121] Furthermore, it should be understood that since the settings of the respective modules are only for illustrating 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.

[0122] Those skilled in the art can understand that the respective modules in the device can be adaptively split or combined. Such splitting or combining 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 combining will all fall within the protection scope of the present application.

[0123] So far, the technical solution of the present application has been described in conjunction with the preferred embodiments shown in the drawings. However, it is easy for those skilled in the art to 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, and the technical solutions after these changes or substitutions will all fall within the protection scope of the present application.

Claims

1. A method for predicting blade root load of a wind turbine, characterized in that: include: Obtain blade root load data and wind turbine parameters; Input the blade root load data and the wind turbine set parameters into a preset blade root load prediction model to obtain a predicted blade root load within a preset time; wherein the predicted blade root load includes the blade root average load, the blade root limit load, the number of cycles, and the predicted equivalent fatigue load; According to the predicted blade root load, adjusting the operating parameters of the wind turbine generator set; Wherein, obtaining the preset blade root load prediction model includes: Acquire training data; wherein the training data includes blade root load and wind turbine data; 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 preset blade root load prediction model.

2. The method according to claim 1, characterized in that Obtaining the blade root load includes: Obtaining the swing array strain signal and the flapping strain signal of the blade root; Obtaining a blade swing moment and a blade flapping moment according to the swing array strain signal and the flapping strain signal; According to the blade swing moment and the blade flapping moment, a maximum load value, an average load and a number of load cycles are obtained; Obtaining an equivalent fatigue load according to the maximum load value and the number of load cycles; The blade root load is obtained by combining the equivalent fatigue load, the average load and the maximum load value.

3. The method according to claim 1, characterized in that Acquiring the wind turbine data, including: Obtain initial parameters of wind turbines; The initial parameters of the wind turbine generator set are screened to obtain the data of the wind turbine generator set.

4. The method according to claim 3, characterized in that The screening and processing of the initial parameters of the wind turbine generator set to obtain the wind turbine generator set data includes: Performing correlation analysis on a plurality of parameters in the initial parameters of the wind turbine generator set and the blade root load respectively to obtain a set of correlation coefficients; Compare the multiple correlation coefficients in the correlation coefficient set with the preset correlation coefficient thresholds respectively; Acquire a correlation coefficient subset corresponding to a value greater than the preset correlation coefficient threshold; The correlation coefficient subset is matched with the initial parameters of the wind turbine generator set to obtain wind turbine generator set data.

5. The method according to claim 1, characterized in that After combining the obtained multiple decision trees to obtain the preset blade root load prediction model, the method further includes: Get the real blade root load; Obtaining an accurate value of the preset blade root load prediction model according to the actual blade root load and the predicted blade root load; If it is determined that the accuracy value is lower than a preset accuracy threshold, the training data is screened to obtain a screened data set; A blade root load prediction update model is obtained according to the screened data set.

6. The method according to claim 1, characterized in that After inputting the blade root load data and the wind turbine set parameters into a preset blade root load prediction model to obtain a predicted blade root load within a preset time, the method further includes: In the i-th iteration, an equivalent fatigue load calculation value is obtained according to the root limit load and the number of cycles. An equivalent fatigue load error value is obtained according to the predicted equivalent fatigue load and the equivalent fatigue load calculation value. It is determined whether the equivalent fatigue load error value is greater than a preset error value. If it is determined that the equivalent fatigue load error value is greater than the preset error value, the (i - 1)-th root load prediction model is retrained to obtain the i-th root load prediction model; wherein, when i = 1, the (i - 1)-th root load prediction model is the preset root load prediction model. Wherein, 0 < i ≤ I, and when the equivalent fatigue load error value is less than the preset error value, the I-th preset root load prediction model is obtained.

7. The method according to claim 1, characterized in that The method further includes: It is determined that the adjustment process of the operating parameters of the wind turbine is completed. The root load data is monitored. If it is determined that the root load data is greater than the preset root load, the wind turbine is shut down.

8. A blade root load prediction device for a wind turbine, characterized in that: It includes: An acquisition module for acquiring root load data and wind turbine parameters. A processing module for inputting the root load data and the wind turbine parameters into a preset root load prediction model to obtain a predicted root load within a preset time; wherein, the predicted root load includes the root average load, the root limit load, the number of cycles, and the predicted equivalent fatigue load. An analysis module for adjusting the operating parameters of the wind turbine according to the predicted root load. Wherein, obtaining the preset root load prediction model includes: Obtaining training data; wherein, the training data includes root load and wind turbine data. 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 point of the i-th decision tree is divided to obtain nodes, and it is determined whether the nodes meet the stop division condition. If it is determined that the stop division condition is met, the i-th decision tree is obtained. When it is determined that i = I, the training is stopped; wherein, I is the number of decision trees. The obtained multiple decision trees are combined to obtain the preset root load prediction model.

9. A blade root load prediction 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 run by the processor to execute the method according to 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 run by the processor to execute the method according to any one of claims 1 to 7.

Images