Yaw control methods and equipment for wind turbine generators

Abstract

This disclosure provides a yaw control method and device for a wind turbine generator set. The yaw control method includes: predicting the wind direction of the free flow in front of the rotor of the wind turbine generator set within a preset time period in the future; and determining the yaw control strategy of the wind turbine generator set based on the predicted wind direction of the free flow in front of the rotor within the preset time period in the future.

Description

Technical Field

[0001] This disclosure generally relates to the field of wind power technology, and more specifically, to a yaw control method and device for a wind turbine generator set. Background Technology

[0002] From a control perspective, modern large-scale wind turbine generators are nonlinear systems with large inertia and large time delay. The control of wind turbine generators lags behind changes in wind conditions. Taking the yaw control system as an example, the wind turbine generator detects changes in wind direction through a wind vane. The original input signal is filtered and then input into the yaw control system. The yaw control system uses a certain yaw control algorithm to issue a yaw command when the wind direction angle deviates from the direction directly facing the rotor for a certain period of time. The yaw motor drives the entire nacelle and rotor system to yaw in a pre-calculated direction, so that the rotor plane of the unit faces the wind directly, thereby obtaining maximum energy.

[0003] Specifically, the hardware components of the yaw control system mainly include: a wind vane, a yaw motor, a yaw reducer, a yaw gear, a yaw bearing, and a yaw hydraulic braking system. Its main function is: when the wind direction changes and persists for a period of time, the yaw control system sends a start command to the yaw motor, which outputs a low-speed (0.2–0.4 deg / s) high-torque output to the yaw bearing through the yaw reducer, driving the entire nacelle-impeller-generator system to ensure the turbine impeller plane faces the wind direction, thereby maximizing wind energy capture. In actual operation, due to the rapid changes in wind direction over time and the slow yaw rate, the unit may be inaccurate in yaw alignment. This is mainly manifested in two ways: First, during the yaw process (which generally lasts from tens of seconds to several minutes), the wind direction may have already changed, resulting in inaccurate yaw alignment and reduced unit output. Second, if the wind direction changes frequently in actual operation (such as during low wind speed periods), the unit may yaw frequently, increasing the unit's own wear and tear. Excessive yaw time and frequent yaw initiation and braking will increase the wear of the yaw brake pads. Summary of the Invention

[0004] Exemplary embodiments of this disclosure provide a yaw control method and apparatus for a wind turbine generator set, which at least solves the problems in the aforementioned related technologies, or may not solve any of the aforementioned problems.

[0005] According to an exemplary embodiment of the present disclosure, a yaw control method for a wind turbine generator set is provided. The yaw control method includes: predicting the wind direction of the free flow in front of the rotor of the wind turbine generator set within a future preset time period; and determining a yaw control strategy for the wind turbine generator set based on the predicted wind direction of the free flow in front of the rotor within the future preset time period.

[0006] Optionally, the yaw control method further includes: predicting the wind speed of the free flow in front of the rotor within a future preset time period; wherein, the step of predicting the wind direction of the free flow in front of the rotor within a future preset time period includes: predicting the wind direction sequence data measured by the wind direction measuring device within a future preset time period based on the historical wind direction sequence data measured by the wind direction measuring device of the wind turbine generator set; determining the wind direction sequence data of the free flow in front of the rotor within a future preset time period corresponding to the wind direction sequence data measured by the wind direction measuring device within a future preset time period based on the predicted wind speed of the free flow in front of the rotor within a future preset time period and the historical yaw wind deviation, wherein the wind direction measuring device is installed on the nacelle behind the rotor of the wind turbine generator set.

[0007] Optionally, the step of predicting the wind speed of the free flow in front of the rotor within a future preset time period includes: predicting the wind speed sequence data measured by the wind speed measuring device within a future preset time period based on the historical wind speed sequence data measured by the wind speed measuring device of the wind turbine generator set; and determining the wind speed sequence data of the free flow in front of the rotor within a future preset time period corresponding to the predicted wind speed sequence data measured by the wind speed measuring device within a future preset time period based on the historical yaw deviation, wherein the wind speed measuring device is installed on the nacelle behind the rotor of the wind turbine generator set.

[0008] Optionally, the step of determining the wind direction sequence data corresponding to the wind direction sequence data of the free flow in front of the impeller within the predicted future preset time period, based on the predicted wind speed of the free flow in front of the impeller within the predicted future preset time period and the historical yaw deviation, includes: determining the wind direction sequence data corresponding to the wind direction sequence data of the free flow in front of the impeller within the predicted future preset time period, based on the predetermined correspondence between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller under different free flow speeds and different yaw deviations, and under the conditions of the predicted wind speed of the free flow in front of the impeller and the historical yaw deviation. The wind direction sequence data of the free flow in front of the impeller; or, based on the corresponding deviation between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller under different predetermined conditions of different free flow speeds and different yaw deviations, the deviation between the wind direction sequence data measured by the wind direction measuring device and the wind direction sequence data of the free flow in front of the impeller under the conditions of the predicted wind speed and historical yaw deviations in the free flow in front of the impeller within the predicted future preset time period is determined; and based on the deviation and the wind direction sequence data measured by the wind direction measuring device within the predicted future preset time period, the wind direction sequence data of the free flow in front of the impeller within the future preset time period is determined.

[0009] Optionally, the correspondence or the corresponding deviation is predetermined in the following manner: based on the attribute information of the wind turbine generator set, the correspondence or corresponding deviation between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the rotor under different free flow wind speeds and different yaw deviations is obtained through dynamic simulation; based on the correspondence or corresponding deviation between the wind direction actually measured by the wind direction measuring device and the wind direction of the free flow in front of the rotor actually measured by the lidar, the correspondence or corresponding deviation obtained through dynamic simulation is corrected.

[0010] Optionally, the step of determining the wind speed sequence data of the free flow in front of the impeller within the predicted future preset time period, corresponding to the wind speed sequence data measured by the wind speed measuring device within the historical yaw deviation, includes: determining the wind speed sequence data of the free flow in front of the impeller corresponding to the wind speed measured by the wind speed measuring device within the predicted future preset time period under the conditions of historical yaw deviation, based on a pre-determined correspondence between the wind speed measured by the wind speed measuring device and the wind speed of the free flow in front of the impeller under different yaw deviation conditions. The wind speed sequence data; or, based on the predetermined deviation between the wind speed measured by the wind speed measuring device and the wind speed of the free flow in front of the impeller under different yaw wind deviation conditions, the deviation between the wind speed sequence data measured by the wind speed measuring device and the wind speed sequence data of the free flow in front of the impeller in the predicted future preset time period under historical yaw wind deviation conditions is determined; and based on the deviation and the wind speed sequence data measured by the wind speed measuring device in the predicted future preset time period, the wind speed sequence data of the free flow in front of the impeller in the future preset time period is determined.

[0011] Optionally, the correspondence or the corresponding deviation is predetermined in the following manner: based on the attribute information of the wind turbine generator set, the correspondence or corresponding deviation between the wind speed measured by the wind speed measuring device and the free flow wind speed in front of the rotor under different yaw wind deviation conditions is obtained through dynamic simulation; based on the correspondence or corresponding deviation between the wind speed actually measured by the wind speed measuring device and the wind speed of the free flow in front of the rotor actually measured by the lidar, the correspondence or corresponding deviation obtained through dynamic simulation is corrected.

[0012] Optionally, the attribute information of the wind turbine generator set includes at least one of the following: the terrain information of the wind turbine generator set, the tower height, the rotor diameter, and the installation location information of the wind speed measuring device or the wind direction measuring device.

[0013] Optionally, the step of predicting the wind direction of the free flow in front of the impeller within a preset time period includes: acquiring the wind direction of the free flow at a preset distance from the impeller measured by lidar; and predicting the wind direction of the free flow in front of the impeller within a preset time period based on the acquired wind direction of the free flow at the preset distance from the impeller.

[0014] Optionally, the step of predicting the wind direction sequence data measured by the wind direction measuring device within a preset time period in the future, based on the historical wind direction sequence data measured by the wind direction measuring device of the wind turbine generator set, includes: inputting the historical wind direction sequence data measured by the wind direction measuring device of the wind turbine generator set into a pre-trained wind direction prediction model to obtain the wind direction sequence data measured by the wind direction measuring device within a preset time period in the future predicted by the wind direction prediction model.

[0015] According to another exemplary embodiment of the present disclosure, a yaw control device for a wind turbine generator set is provided. The yaw control device includes: a wind direction prediction unit for predicting the wind direction of the free flow in front of the rotor of the wind turbine generator set within a future preset time period; and a yaw control unit for determining the yaw control strategy of the wind turbine generator set based on the predicted wind direction of the free flow in front of the rotor within the future preset time period.

[0016] Optionally, the yaw control device further includes: a wind speed prediction unit, used to predict the wind speed of the free flow in front of the rotor within a future preset time period; wherein, the wind direction prediction unit predicts the wind direction sequence data measured by the wind direction measurement device within the future preset time period based on the historical wind direction sequence data measured by the wind direction measurement device of the wind turbine generator set; and determines the wind direction sequence data of the free flow in front of the rotor within the future preset time period corresponding to the wind direction sequence data measured by the wind direction measurement device within the future preset time period based on the predicted wind speed of the free flow in front of the rotor within the future preset time period and the historical yaw wind deviation, wherein the wind direction measurement device is installed on the nacelle behind the rotor of the wind turbine generator set.

[0017] Optionally, the wind speed prediction unit predicts the wind speed sequence data measured by the wind speed measuring device within a preset time period based on the historical wind speed sequence data measured by the wind speed measuring device of the wind turbine generator set; and determines the wind speed sequence data of the free flow in front of the rotor within a preset time period corresponding to the predicted wind speed sequence data measured by the wind speed measuring device within the preset time period, wherein the wind speed measuring device is installed on the nacelle behind the rotor of the wind turbine generator set.

[0018] Optionally, the wind direction prediction unit determines, based on a predetermined correspondence between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller under different free flow speeds and different yaw deviations, the wind direction prediction unit determines the wind direction sequence data of the free flow in front of the impeller corresponding to the wind direction sequence data measured by the wind direction measuring device within the predicted future preset time period, under the conditions of historical yaw deviations and the wind speed of the free flow in front of the impeller within the predicted future preset time period; or, the wind direction prediction unit determines, based on a predetermined free flow speed in front of the impeller, the wind direction sequence data corresponding to the wind direction sequence data measured by the wind direction measuring device within the predicted future preset time period, under the conditions of historical yaw deviations; or, the wind direction prediction unit determines, based on a predetermined correspondence between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller under different free flow speeds. Under different yaw-to-wind deviation conditions, the corresponding deviation between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller is determined. Under the conditions of historical yaw-to-wind deviation, the deviation between the wind direction sequence data measured by the wind direction measuring device and the wind direction sequence data of the free flow in front of the impeller in the predicted future preset time period is determined. Based on the deviation and the wind direction sequence data measured by the wind direction measuring device in the predicted future preset time period, the wind direction sequence data of the free flow in front of the impeller in the future preset time period is determined.

[0019] Optionally, the correspondence or the corresponding deviation is predetermined in the following manner: based on the attribute information of the wind turbine generator set, the correspondence or corresponding deviation between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the rotor under different free flow wind speeds and different yaw deviations is obtained through dynamic simulation; based on the correspondence or corresponding deviation between the wind direction actually measured by the wind direction measuring device and the wind direction of the free flow in front of the rotor actually measured by the lidar, the correspondence or corresponding deviation obtained through dynamic simulation is corrected.

[0020] Optionally, the wind speed prediction unit determines, based on a predetermined correspondence between the wind speed measured by the wind speed measuring device and the free-flow wind speed in front of the impeller under different yaw-wind deviation conditions, the wind speed sequence data of the free-flow wind speed in front of the impeller corresponding to the wind speed sequence data measured by the wind speed measuring device within a predicted future preset time period under historical yaw-wind deviation conditions; or, the wind speed prediction unit determines, based on a predetermined deviation between the wind speed measured by the wind speed measuring device and the free-flow wind speed in front of the impeller under historical yaw-wind deviation conditions, the deviation between the wind speed sequence data measured by the wind speed measuring device and the free-flow wind speed sequence data in front of the impeller within a predicted future preset time period; and based on the deviation and the wind speed sequence data measured by the wind speed measuring device within the predicted future preset time period, determines the wind speed sequence data of the free-flow wind speed in front of the impeller within the future preset time period.

[0021] Optionally, the correspondence or the corresponding deviation is predetermined in the following manner: based on the attribute information of the wind turbine generator set, the correspondence or corresponding deviation between the wind speed measured by the wind speed measuring device and the free flow wind speed in front of the rotor under different yaw wind deviation conditions is obtained through dynamic simulation; based on the correspondence or corresponding deviation between the wind speed actually measured by the wind speed measuring device and the wind speed of the free flow in front of the rotor actually measured by the lidar, the correspondence or corresponding deviation obtained through dynamic simulation is corrected.

[0022] Optionally, the attribute information of the wind turbine generator set includes at least one of the following: the terrain information of the wind turbine generator set, the tower height, the rotor diameter, and the installation location information of the wind speed measuring device or the wind direction measuring device.

[0023] Optionally, the wind direction prediction unit acquires the wind direction of the free flow at a preset distance in front of the impeller as measured by the lidar; and based on the acquired wind direction of the free flow at the preset distance in front of the impeller, predicts the wind direction of the free flow in front of the impeller within a preset time period in the future.

[0024] Optionally, the wind direction prediction unit inputs the historical wind direction sequence data measured by the wind direction measurement device of the wind turbine into the pre-trained wind direction prediction model to obtain the wind direction sequence data measured by the wind direction measurement device within a future preset time period predicted by the wind direction prediction model.

[0025] According to another exemplary embodiment of the present disclosure, a computer device is provided, the computer device including: a processor; and a memory storing a computer program, wherein when the computer program is executed by the processor, the yaw control method of the wind turbine generator set as described above is implemented.

[0026] According to another exemplary embodiment of the present disclosure, a computer-readable storage medium storing a computer program is provided, which, when executed by a processor, implements the yaw control method for a wind turbine generator as described above.

[0027] The yaw control method and apparatus for wind turbine generators according to exemplary embodiments of the present disclosure can predict the wind direction in front of the rotor over a period of time in the future to determine the yaw control strategy of the generator, thereby transforming the lagging yaw control of the generator into active control and improving the accuracy of yaw feedforward control.

[0028] Further aspects and / or advantages of the general concept of this disclosure will be set forth in part in the description which follows, and in part will be clear from the description or may be learned by practice of the general concept of this disclosure. Attached Figure Description

[0029] The above and other objects and features of exemplary embodiments of this disclosure will become clearer from the following description taken in conjunction with the accompanying drawings, which illustrate exemplary embodiments, wherein:

[0030] Figure 1 A flowchart illustrating a yaw control method for a wind turbine generator set according to an exemplary embodiment of the present disclosure is provided.

[0031] Figure 2 An example illustrating the effect of wind direction prediction according to an exemplary embodiment of this disclosure;

[0032] Figure 3 An example of wind speed prediction performance according to an exemplary embodiment of the present disclosure is shown;

[0033] Figure 4 A structural block diagram of a yaw control device for a wind turbine generator set according to an exemplary embodiment of the present disclosure is shown. Detailed Implementation

[0034] The embodiments of this disclosure will now be described in detail with reference to the accompanying drawings, examples of which are illustrated in the drawings, wherein the same reference numerals always refer to the same parts. The embodiments will now be described with reference to the accompanying drawings in order to explain this disclosure.

[0035] Figure 1 A flowchart illustrating a yaw control method for a wind turbine generator according to an exemplary embodiment of the present disclosure is shown.

[0036] Reference Figure 1 In step S10, the direction of the free flow in front of the wind turbine rotor is predicted within a preset time period in the future.

[0037] As an example only, the preset duration can be 10-15 minutes.

[0038] In step S20, the yaw control strategy of the wind turbine is determined based on the predicted wind direction of the free flow in front of the rotor within a preset future time period, thereby realizing feedforward control of yaw.

[0039] As an example, yaw control strategies may include, but are not limited to: whether to perform an early yaw and the optimal yaw angle to which to yaw.

[0040] As an example, the yaw control method for a wind turbine generator set according to an exemplary embodiment of the present disclosure may further include: predicting the wind speed of the free flow in front of the rotor within a preset time period in the future.

[0041] As an example, step S20 may include: determining the yaw control strategy of the wind turbine based on the predicted wind direction and wind speed of the free flow in front of the rotor within a predicted future preset time period.

[0042] As an example, step S10 may include: predicting the wind direction sequence data that the wind direction measurement device will measure within a preset time period based on the historical wind direction sequence data measured by the wind direction measurement device of the wind turbine generator set; and determining the wind direction sequence data of the free flow in front of the rotor within the preset time period corresponding to the predicted wind direction sequence data that the wind direction measurement device will measure within the preset time period based on the predicted wind speed of the free flow in front of the rotor within the preset time period and the historical yaw deviation.

[0043] Here, the wind direction measuring device is installed on the nacelle behind the rotor of the wind turbine. For example, the wind direction measuring device can be a wind vane.

[0044] As an example, historical wind direction sequence data measured by a wind direction measuring device can be: wind direction sequence data measured by the wind direction measuring device within a recent period. For example, the length of this period can be the same as or different from the preset duration. As an example, historical yaw deviation can be the most recently determined yaw deviation.

[0045] As an example, wind direction sequence data, which is time series data of wind direction, can be represented as, for example, v dir =[v dir (t0),v dir (t1),v dir (t2)……v dir (t m )], where t0, t1, ... t m This indicates various points in time (moments).

[0046] As an example, historical wind direction sequence data measured by a wind direction measuring device can be input into a pre-trained wind direction prediction model to obtain wind direction sequence data that the wind direction measuring device will measure within a preset future time period as predicted by the wind direction prediction model.

[0047] As an example, when the historical wind direction sequence data measured by the wind direction measuring device contains a lot of noise, it can be filtered first. Different filtering constants can be adopted according to the control objectives and system characteristics. For yaw control systems, a 30s or 60s moving average can be used for the wind direction signal, and the filtered data can be input into the wind direction prediction model mentioned above.

[0048] As an example, a large amount of relevant historical field data from wind turbine generators can be used to train the wind direction prediction model to obtain a well-trained wind direction prediction model.

[0049] As an example, wind direction prediction models can use a variety of appropriate machine learning algorithms, such as ARMA (autoregressive moving average), neural networks, multivariate linear regression, and other machine learning algorithms.

[0050] As an example, when the wind direction prediction model uses ARMA to predict the wind direction, the mathematical model of ARMA(p,q) can be expressed as:

[0051]

[0052] where y t represents the predicted value at time t, y t-i represents the actual value at time t-i, δ0 represents a constant, ∈ t represents the error between the predicted value and the actual value at time t, p represents the autoregressive order, q represents the moving average order, γ i and θ j represent the autoregressive and moving average coefficients respectively.

[0053] As an example, a stationarity test can be performed on the training data of the wind direction prediction model. For example, the stationarity test of time series data can use the ADF (Augmented Dickey-Fuller test) to ensure the stationarity of the data. If the above test passes, the corresponding data can be used as the training data of the wind direction prediction model.

[0054] As an example, the training data can be divided into two parts. One part of the data is used as the sample data for training the model (usually about 70% of the total data), and the other part is used as the model verification data. As an example, the predicted value of the wind direction after a period of time can be obtained using the trained wind direction prediction model and compared with the actual value v dir to measure the prediction effect of the wind direction prediction model. When the prediction effect of the wind direction prediction model meets certain conditions, it can be considered trained and can be used for actual prediction.

[0055] As an example, RMSE (Root Mean Square Error) can be used to measure the error between the predicted value and the actual value. The definition of RMSE can be as follows:

[0056]

[0057] where the smaller the RMSE, the higher the prediction accuracy. A value RMSE0 can be preset. When RMSE < RMSE0, it is determined that the wind direction prediction model is trained and can be used for actual prediction; otherwise, it can be considered that the accuracy of the wind direction prediction model is insufficient and cannot be used for actual prediction, and further adjustment and training are still required.

[0058] Figure 2 Shows an example of the wind direction prediction effect according to an exemplary embodiment of the present disclosure. Figure 2The data shows the actual wind direction (i.e., the raw wind direction data, transient data with a sampling period of 60 seconds, represented by a thin black line), the filtered wind direction data (i.e., the 60-second mean wind direction, represented by a thick black line), and the predicted wind direction data (represented by a thick black dashed line). It can be seen that the predicted wind direction has a good match with the actual wind direction (RMSE of 2.256). Figure 2 In the diagram, each point represents 7 seconds of transient data, and the wind direction prediction model predicts the wind direction for a total of approximately 12 minutes.

[0059] It should be understood that the indicators used to assess the magnitude of the deviation between the predicted and actual wind direction values ​​are not limited to RMSE, but may also include MSE (mean squared error), MAE (mean absolute error), etc., and this disclosure does not impose any restrictions on them.

[0060] In one embodiment, based on a predetermined correspondence between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller under different free flow speeds and different yaw deviations in front of the impeller (e.g., by using a lookup table method), the wind direction sequence data of the free flow in front of the impeller corresponding to the wind direction sequence data measured by the wind direction measuring device in the predicted future preset time period and the historical yaw deviations can be determined. This sequence data is the predicted wind direction of the free flow in front of the impeller in the predicted future preset time period.

[0061] As an example, for each time point in the wind direction sequence data measured by the wind direction measuring device within the predicted future preset time period, the wind direction of the free flow in front of the impeller corresponding to it can be determined according to the above correspondence, thereby obtaining the wind direction sequence data of the free flow in front of the impeller within the future preset time period.

[0062] As an example, the above correspondence can be predetermined in the following way: based on the attribute information of the wind turbine generator set, the correspondence between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the turbine generator set is obtained through dynamic simulation under different free flow wind speeds in front of the turbine and different yaw deviations.

[0063] Furthermore, as an example, the correspondence obtained through dynamic simulation can be further corrected based on the correspondence between the wind direction actually measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller actually measured by the lidar.

[0064] In another embodiment, based on the corresponding deviation (i.e., the deviation correspondence) between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller under predetermined conditions of different free flow speeds and different yaw deviations in front of the impeller, the deviation between the wind direction sequence data measured by the wind direction measuring device and the wind direction sequence data of the free flow in front of the impeller in the predicted future preset time period can be determined under the conditions of the wind speed of the free flow in front of the impeller and historical yaw deviations in the predicted future preset time period. Based on the above deviation and the wind direction sequence data measured by the wind direction measuring device in the predicted future preset time period, the wind direction sequence data of the free flow in front of the impeller in the future preset time period can be determined. It should be understood that the deviation between the wind direction sequence data measured by the wind direction measuring device in the predicted future preset time period and the wind direction sequence data of the free flow in front of the impeller in the predicted future preset time period is the deviation between the wind direction sequence data measured by the wind direction measuring device in the predicted future preset time period and the wind direction of the free flow in front of the impeller in the future preset time period.

[0065] As an example, for each time point in the wind direction sequence data measured by the wind direction measuring device within a predicted future preset time period, the deviation between the wind direction and the wind direction of the free flow in front of the impeller can be determined based on the aforementioned deviation correspondence, thereby obtaining the corresponding wind direction of the free flow in front of the impeller. As another example, a unified deviation can be determined between the wind direction sequence data measured by the wind direction measuring device within a predicted future preset time period and the wind direction sequence data of the free flow in front of the impeller. Then, for each time point in the wind direction sequence data measured by the wind direction measuring device within the predicted future preset time period, the wind direction of the corresponding free flow in front of the impeller can be determined based on the aforementioned unified deviation, thereby obtaining the wind direction sequence data of the free flow in front of the impeller within the future preset time period. For example, the unified deviation can be determined based on the average wind speed of the free flow in front of the impeller within the predicted future preset time period and historical yaw deviations, according to the predetermined deviation correspondence.

[0066] As an example, the aforementioned corresponding deviation can be predetermined in the following way: based on the attribute information of the wind turbine generator set, the corresponding deviation between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the turbine generator set is obtained through dynamic simulation under different free flow wind speeds in front of the turbine and different yaw deviations.

[0067] Furthermore, as an example, the corresponding deviation obtained through dynamic simulation can be further corrected based on the corresponding deviation between the wind direction actually measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller actually measured by the lidar.

[0068] As an example, the attribute information of a wind turbine may include at least one of the following: the terrain information of the wind turbine, the tower height, the rotor diameter, and the installation location information of the wind direction measuring device.

[0069] Because the wind direction measured by the wind direction measuring device is affected by the impeller turbulence, the wind direction measured by the wind direction measuring device is inaccurate. Furthermore, the turbulence effect of the impeller on the wind direction is non-linear. Under different wind speeds and different yaw turbulence conditions, there are corresponding deviations between the free-flowing wind direction in front of the impeller and the wind direction measured by the wind direction measuring device. This disclosure, by simulating actual on-site conditions and ensuring the terrain, tower height, impeller diameter, and installation position of the wind direction measuring device, uses dynamic simulation to obtain the deviation between the wind direction measured by the wind direction measuring device and the free-flowing wind direction under different wind speeds and different yaw turbulence turbulence conditions: Δv dir (v,v dir Accordingly, based on the wind direction measurement device within the obtained future preset time period, the wind direction will be measured. Combined with Δv dir (v,v dir It can predict the direction of the free flow in front of the impeller within a preset time period.

[0070] As an example, the step of predicting the wind speed of the free flow in front of the rotor within a future preset time period may include: predicting the wind speed sequence data measured by the wind speed measuring device within the future preset time period based on the historical wind speed sequence data measured by the wind speed measuring device of the wind turbine generator; and determining the wind speed sequence data of the free flow in front of the rotor within the future preset time period corresponding to the predicted wind speed sequence data measured by the wind speed measuring device within the future preset time period based on the historical yaw deviation.

[0071] The wind speed measuring device is mounted on the nacelle behind the rotor of the wind turbine generator. For example, the wind speed measuring device can be an anemometer. As an example, the wind direction measuring device and the wind speed measuring device can be integrated into a single measuring device.

[0072] As an example, historical wind speed sequence data measured by the wind speed measurement device of the wind turbine generator can be input into a pre-trained wind speed prediction model to obtain wind speed sequence data measured by the wind speed measurement device within a preset future time period predicted by the wind speed prediction model.

[0073] As an example, wind speed sequence data refers to time series data of wind speed, which can be represented as v = [v(t0), v(t1), v(t2) ... v(t...]. m )], where t0, t1, ... t m Indicates various points in time.

[0074] As an example, when the historical wind speed sequence data measured by the wind speed measuring device contains a large amount of noise, it can be filtered first. Different filtering constants can be used for filtering according to the control objectives and system characteristics, and the filtered data can be input into the wind speed prediction model mentioned above.

[0075] As an example, a large amount of relevant historical field data from wind turbine generators can be used to train the wind speed prediction model to obtain a well-trained wind speed prediction model.

[0076] As an example, wind speed prediction models can use a variety of appropriate machine learning algorithms, such as ARMA (autoregressive moving average), neural networks, multivariate linear regression, and other machine learning algorithms.

[0077] As an example, the stationarity of the training data for the wind speed prediction model can be tested. For instance, the stationarity of time series data can be tested using the ADF (Augmented Dickey-Fuller test) to ensure the stationarity of the data. If the above test passes, the corresponding data can be used as the training data for the wind speed prediction model.

[0078] Figure 3 An example of wind speed prediction effect according to an exemplary embodiment of the present disclosure is shown. Figure 3 The data shows the actual wind speed data (i.e., the raw wind speed data, transient data with a sampling period of 60s, represented by a thin black line), the filtered wind speed data (i.e., the 60s mean wind speed, represented by a thick black line), and the predicted wind speed data (represented by a thick black dashed line). It can be seen that the predicted wind speed has a good agreement with the actual wind speed (RMSE of 0.062). Figure 3 In the diagram, each point represents 7 seconds of transient data, and the wind speed prediction model predicted wind speeds for a total of approximately 12 minutes.

[0079] In one embodiment, based on a predetermined correspondence between the wind speed measured by the wind speed measuring device and the free flow wind speed in front of the impeller under different yaw wind deviation conditions, the wind speed sequence data of the free flow wind speed in front of the impeller corresponding to the wind speed sequence data measured by the wind speed measuring device within a predicted future preset time period under historical yaw wind deviation conditions can be determined.

[0080] As an example, the above correspondence can be predetermined in the following way: based on the attribute information of the wind turbine generator, the correspondence between the wind speed measured by the wind speed measuring device and the free flow wind speed in front of the rotor is obtained through dynamic simulation under different yaw deviations.

[0081] As an example, the correspondence obtained through dynamic simulation can be further corrected based on the correspondence between the wind speed actually measured by the wind speed measuring device and the wind speed of the free flow in front of the impeller actually measured by the lidar.

[0082] In another embodiment, the deviation between the wind speed measured by the wind speed measuring device and the wind speed of the free flow in front of the impeller under different yaw wind deviation conditions can be determined based on the corresponding deviation between the wind speed measured by the wind speed measuring device and the wind speed sequence data of the free flow in front of the impeller under the historical yaw wind deviation conditions. Based on the above deviation and the wind speed sequence data measured by the wind speed measuring device in the predicted future preset time period, the wind speed sequence data of the free flow in front of the impeller in the future preset time period can be determined.

[0083] As an example, the aforementioned corresponding deviation can be predetermined in the following way: based on the attribute information of the wind turbine generator, the corresponding deviation between the wind speed measured by the wind speed measuring device and the free flow wind speed in front of the rotor is obtained through dynamic simulation under different yaw deviation conditions.

[0084] Furthermore, as an example, the corresponding deviation obtained through dynamic simulation can be further corrected based on the corresponding deviation between the wind speed actually measured by the wind speed measuring device and the wind speed of the free flow in front of the impeller actually measured by the lidar.

[0085] As an example, the attribute information of a wind turbine may include at least one of the following: the terrain information of the wind turbine, the tower height, the rotor diameter, and the installation location information of the wind speed measurement device.

[0086] Furthermore, as an example, step S10 may include: acquiring the wind direction of the free flow at a preset distance in front of the impeller as measured by the lidar; and predicting the wind direction of the free flow in front of the impeller within a preset time period based on the acquired wind direction at the preset distance in front of the impeller. For example, the preset distance may be 100m.

[0087] In addition, as an example, the step of predicting the wind speed of the free flow in front of the impeller within a preset time period may include: acquiring the wind speed of the free flow at a preset distance from the impeller measured by lidar; and predicting the wind speed of the free flow in front of the impeller within a preset time period based on the acquired wind speed of the free flow at the preset distance from the impeller.

[0088] This disclosure takes into account that the generator unit is an inertial system with a significant time lag. Under actual field operating conditions, the wind direction generally changes in real time, while the generator unit's yaw rate is relatively slow (approximately 0.2–0.4 deg / s). In most cases, the generator unit's yaw lags far behind the change in wind direction, leading to the following problems:

[0089] (1) Under the condition of frequent wind direction changes, the unit is in a frequent yaw state, which increases the unit's own losses and the wear of the yaw brake pads.

[0090] (2) Inaccurate wind direction leads to additional power generation loss: Because the unit yaws at a slow rate, when the unit yaws to the set position, the actual wind direction may have changed, and there may be a certain deviation angle between the impeller plane and the wind direction. The unit is not aligned with the wind, resulting in power generation loss.

[0091] (3) Affecting the overall load of the unit: According to the simulation, when the yaw deviation of the unit is 30 degrees, the overall load is the largest. If it is operating under some special conditions, such as power grid failure or propeller jamming, it may affect the ultimate load of the unit.

[0092] (4) Modern large wind turbine generator sets are generally designed for upwind. The wind direction measurement sensor (wind vane) of a typical wind turbine generator set is installed behind the rotor. When the rotor rotates, the turbulence will affect the wind vane's measurement of the wind direction. That is, the measured wind direction will be affected by the rotor turbulence, which will cause a certain deviation between the actual measured wind direction and the free flow wind direction in front of the rotor, thus affecting the wind accuracy of the unit.

[0093] Therefore, according to the exemplary embodiments of this disclosure, by learning from the historical operating data of the unit, the wind direction change in the future period is predicted. At the same time, combined with the whole-machine dynamics simulation, the relationship between the wind direction measured by the wind vane on the nacelle and the actual incoming wind direction is simulated under different wind speed conditions and different wind deviation conditions, and the wind direction in front of the impeller is deduced.

[0094] By using the predicted wind direction over a certain period of time as the input to the yaw feedforward control, the lagging yaw control of the unit is transformed into an active control.

[0095] Through dynamic simulation, a nonlinear relationship between the wind direction detected by the unit and the free flow wind direction in front of the rotor under different wind speeds and yaw deviations is established. By back-calculation and combined with wind direction prediction, the change of wind direction in front of the rotor in the future period is predicted, so as to eliminate the influence of rotor turbulence on wind direction measurement as much as possible and improve the accuracy of yaw feedforward control.

[0096] Through whole-machine dynamics simulation, under the same terrain conditions and unit configuration conditions (impeller diameter, tower height, etc.), the deviation between the wind direction measured by the wind vane and the free flow wind direction under different wind speeds and different wind deviations is obtained. Based on the above model, the wind direction in front of the impeller can be deduced.

[0097] Figure 4 A structural block diagram of a yaw control device for a wind turbine generator set according to an exemplary embodiment of the present disclosure is shown.

[0098] like Figure 4 As shown, the yaw control device for a wind turbine generator set according to an exemplary embodiment of the present disclosure includes: a wind direction prediction unit 10 and a yaw control unit 20.

[0099] Specifically, the wind direction prediction unit 10 is used to predict the wind direction of the free flow in front of the rotor of the wind turbine generator within a preset time period in the future.

[0100] The yaw control unit 20 is used to determine the yaw control strategy of the wind turbine generator based on the predicted wind direction of the free flow in front of the rotor within a preset future time period.

[0101] As an example, the yaw control device for a wind turbine generator set according to an exemplary embodiment of the present disclosure may further include: a wind speed prediction unit (not shown), which is used to predict the wind speed of the free flow in front of the rotor within a preset time period in the future.

[0102] As an example, the wind direction prediction unit 10 can predict the wind direction sequence data measured by the wind direction measurement device within a preset time period in the future based on the historical wind direction sequence data measured by the wind direction measurement device of the wind turbine generator set; and determine the wind direction sequence data of the free flow in front of the rotor within a preset time period in the future, which corresponds to the wind direction sequence data measured by the wind direction measurement device within the predicted preset time period, based on the wind speed of the free flow in front of the rotor within the predicted preset time period and the historical yaw deviation. The wind direction measurement device is installed on the nacelle behind the rotor of the wind turbine generator set.

[0103] As an example, the wind speed prediction unit can predict the wind speed sequence data measured by the wind speed measurement device within a preset time period in the future based on the historical wind speed sequence data measured by the wind speed measurement device of the wind turbine generator set; and determine the wind speed sequence data of the free flow in front of the rotor within a preset time period in the future, corresponding to the predicted wind speed sequence data measured by the wind speed measurement device within a preset time period in the future, wherein the wind speed measurement device is installed on the nacelle behind the rotor of the wind turbine generator set.

[0104] As an example, the wind direction prediction unit 10 can determine, based on a predetermined correspondence between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller under different free flow speeds and different yaw deviations, the wind direction prediction unit 10 can determine the wind direction sequence data of the free flow in front of the impeller corresponding to the wind direction sequence data measured by the wind direction measuring device within the predicted future preset time period, under the conditions of the wind speed of the free flow in front of the impeller and historical yaw deviations; or, the wind direction prediction unit 10 can determine, based on a predetermined correspondence between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller under different free flow speeds and different yaw deviations, the wind direction prediction unit 10 can determine the wind direction sequence data of the free flow in front of the impeller corresponding to the wind direction sequence data of the free flow in front of the impeller within the predicted future preset time period, under the conditions of the wind speed of the free flow in front of the impeller and historical yaw deviations; Under conditions of incoming wind speed and different yaw deviations, the corresponding deviation between the wind direction measured by the wind direction measuring device and the wind direction of the free incoming flow in front of the impeller is determined. Under the conditions of the predicted wind speed of the free incoming flow in front of the impeller and historical yaw deviations, the deviation between the wind direction sequence data measured by the wind direction measuring device and the wind direction sequence data of the free incoming flow in front of the impeller in the predicted future preset time period is determined. Based on the above deviation and the wind direction sequence data measured by the wind direction measuring device in the predicted future preset time period, the wind direction sequence data of the free incoming flow in front of the impeller in the predicted future preset time period is determined.

[0105] As an example, the above correspondence or deviation can be predetermined in the following way: based on the attribute information of the wind turbine generator, the correspondence or deviation between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the rotor under different free flow wind speeds and different yaw deviations is obtained through dynamic simulation; based on the correspondence or deviation between the wind direction actually measured by the wind direction measuring device and the wind direction of the free flow in front of the rotor actually measured by the lidar, the correspondence or deviation obtained through dynamic simulation is corrected.

[0106] As an example, the wind speed prediction unit can determine the wind speed sequence data of the free flow in front of the impeller corresponding to the wind speed sequence data measured by the wind speed measuring device within a predicted future time period under historical yaw deviation conditions, based on a predetermined correspondence between the wind speed measured by the wind speed measuring device and the wind speed of the free flow in front of the impeller under different yaw deviation conditions; or, the wind speed prediction unit can determine the deviation between the wind speed sequence data measured by the wind speed measuring device and the wind speed sequence data of the free flow in front of the impeller within a predicted future time period under historical yaw deviation conditions, based on a predetermined correspondence deviation between the wind speed measured by the wind speed measuring device and the wind speed sequence data of the free flow in front of the impeller under historical yaw deviation conditions; and based on the above deviation and the wind speed sequence data measured by the wind speed measuring device within the predicted future time period, determine the wind speed sequence data of the free flow in front of the impeller within the predicted future time period.

[0107] As an example, the above correspondence or deviation can be predetermined in the following way: based on the attribute information of the wind turbine generator, the correspondence or deviation between the wind speed measured by the wind speed measuring device and the free flow wind speed in front of the rotor under different yaw deviation conditions is obtained through dynamic simulation; based on the correspondence or deviation between the wind speed actually measured by the wind speed measuring device and the wind speed of the free flow in front of the rotor actually measured by the lidar, the correspondence or deviation obtained through dynamic simulation is corrected.

[0108] As an example, the attribute information of a wind turbine may include at least one of the following: the terrain information of the wind turbine, the tower height, the rotor diameter, and the installation location information of the wind speed measurement device or the wind direction measurement device.

[0109] As an example, the wind direction prediction unit 10 can acquire the wind direction of the free flow at a preset distance in front of the impeller as measured by the lidar; and based on the acquired wind direction of the free flow at the preset distance in front of the impeller, predict the wind direction of the free flow in front of the impeller within a preset time period in the future.

[0110] As an example, the wind direction prediction unit 10 can input the historical wind direction sequence data measured by the wind direction measurement device of the wind turbine generator into the pre-trained wind direction prediction model to obtain the wind direction sequence data measured by the wind direction measurement device within a preset time period in the future predicted by the wind direction prediction model.

[0111] It should be understood that the specific processing performed by the yaw control device of the wind turbine generator according to the exemplary embodiments of this disclosure has been referenced. Figure 1-3 A detailed description has been provided, and the relevant details will not be repeated here.

[0112] It should be understood that the various units in the yaw control device of the wind turbine generator according to the exemplary embodiments of this disclosure may be implemented as hardware components and / or software components. Those skilled in the art may implement the various units, for example, using field-programmable gate arrays (FPGAs) or application-specific integrated circuits (ASICs), based on the processes performed by the defined various units.

[0113] Exemplary embodiments of this disclosure provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the yaw control method for a wind turbine generator as described in the exemplary embodiments above. The computer-readable storage medium is any data storage device capable of storing data read from a computer system. Examples of computer-readable storage media include: read-only memory, random access memory, read-only optical disk, magnetic tape, floppy disk, optical data storage device, and carrier waves (such as data transmission via the Internet through wired or wireless transmission paths).

[0114] A computer device according to an exemplary embodiment of the present disclosure includes a processor (not shown) and a memory (not shown), wherein the memory stores a computer program that, when executed by the processor, implements the yaw control method for a wind turbine generator as described in the exemplary embodiment above.

[0115] While some exemplary embodiments of this disclosure have been shown and described, those skilled in the art will understand that modifications may be made to these embodiments without departing from the principles and spirit of this disclosure, which are defined by the claims and their equivalents.

Claims

1. A yaw control method for a wind turbine generator set, characterized in that, The yaw control method includes: Predict the direction of the free flow in front of the rotor of the wind turbine generator set within a preset time period in the future; Based on the predicted wind direction of the free flow in front of the rotor within a preset future time period, the yaw control strategy of the wind turbine generator set is determined. The steps for predicting the direction of the free flow in front of the impeller within a preset time period include: Based on the historical wind direction sequence data measured by the wind direction measuring device of the wind turbine generator set, predict the wind direction sequence data measured by the wind direction measuring device within a preset time period in the future; Based on the predicted wind speed of the free flow in front of the impeller within the predicted future preset time period and the historical yaw deviation, the wind direction sequence data of the free flow in front of the impeller within the predicted future preset time period is determined, which corresponds to the wind direction sequence data measured by the wind direction measuring device within the predicted future preset time period.

2. The yaw control method according to claim 1, characterized in that, The wind direction measuring device is installed on the nacelle behind the rotor of the wind turbine generator set.

3. The yaw control method according to claim 2, characterized in that, The yaw control method further includes: predicting the wind speed of the free flow in front of the impeller within a preset time period in the future; The steps for predicting the wind speed of the free flow in front of the impeller within a preset time period include: Based on the historical wind speed sequence data measured by the wind speed measuring device of the wind turbine generator set, predict the wind speed sequence data measured by the wind speed measuring device within a preset time period in the future; Based on historical yaw deviations, the wind speed sequence data of the free flow in front of the impeller within the predicted future preset time period is determined, corresponding to the wind speed sequence data measured by the wind speed measurement device within the future preset time period. The wind speed measuring device is installed on the nacelle behind the rotor of the wind turbine generator set.

4. The yaw control method according to claim 2, characterized in that, The steps for determining the wind direction sequence data of the free flow in front of the impeller within the predicted future preset time period, based on the predicted wind speed in the free flow in front of the impeller within the predicted future preset time period and the historical yaw deviation, include: Based on the predetermined correspondence between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller under different free flow speeds and different yaw deviations, the wind direction sequence data of the free flow in front of the impeller corresponding to the wind direction sequence data measured by the wind direction measuring device in the predicted future preset time period is determined under the conditions of the wind speed of the free flow in front of the impeller and the historical yaw deviation. Alternatively, based on the predetermined deviation between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller under different free flow speeds and different yaw deviations, the deviation between the wind direction sequence data measured by the wind direction measuring device and the wind direction sequence data of the free flow in front of the impeller under the predicted free flow speed and historical yaw deviations within a predicted future preset time period is determined; and based on the deviation and the wind direction sequence data measured by the wind direction measuring device within the predicted future preset time period, the wind direction sequence data of the free flow in front of the impeller within the future preset time period is determined.

5. The yaw control method according to claim 4, characterized in that, The correspondence or the correspondence deviation is predetermined in the following manner: Based on the attribute information of the wind turbine generator set, the correspondence or corresponding deviation between the wind direction measured by the wind direction measuring device and the wind direction of the free flow in front of the rotor under different free flow wind speeds in front of the rotor and different yaw deviations is obtained through dynamic simulation. Based on the correspondence or deviation between the wind direction actually measured by the wind direction measuring device and the wind direction of the free flow in front of the impeller actually measured by the lidar, the correspondence or deviation obtained through dynamic simulation is corrected.

6. The yaw control method according to claim 3, characterized in that, The steps for determining the wind speed sequence data of the free flow in front of the impeller within the predicted future preset time period, based on historical yaw deviations, include: Based on the predetermined correspondence between the wind speed measured by the wind speed measuring device and the free flow wind speed in front of the impeller under different yaw wind deviation conditions, the wind speed sequence data of the free flow in front of the impeller corresponding to the wind speed sequence data measured by the wind speed measuring device in the future within a preset time period under the historical yaw wind deviation conditions is determined. Alternatively, based on the predetermined deviation between the wind speed measured by the wind speed measuring device and the wind speed of the free flow in front of the impeller under different yaw wind deviation conditions, the deviation between the wind speed sequence data measured by the wind speed measuring device and the wind speed sequence data of the free flow in front of the impeller in the predicted future time period under historical yaw wind deviation conditions is determined; and based on the deviation and the wind speed sequence data measured by the wind speed measuring device in the predicted future time period, the wind speed sequence data of the free flow in front of the impeller in the predicted future time period is determined.

7. The yaw control method according to claim 6, characterized in that, The correspondence or the correspondence deviation is predetermined in the following manner: Based on the attribute information of the wind turbine generator set, the corresponding relationship or corresponding deviation between the wind speed measured by the wind speed measuring device and the free flow wind speed in front of the rotor is obtained through dynamic simulation under different yaw wind deviation conditions. Based on the correspondence or deviation between the wind speed actually measured by the wind speed measuring device and the wind speed of the free flow in front of the impeller actually measured by the lidar, the correspondence or deviation obtained through dynamic simulation is corrected.

8. The yaw control method according to claim 5 or 7, characterized in that, The attribute information of the wind turbine generator set includes at least one of the following: The information includes the terrain, tower height, rotor diameter, and installation location of the wind turbine generator set.

9. The yaw control method according to claim 2, characterized in that, The step of predicting the wind direction sequence data measured by the wind direction measuring device within a preset time period based on the historical wind direction sequence data measured by the wind turbine generator set includes: The historical wind direction sequence data measured by the wind direction measuring device of the wind turbine generator is input into the pre-trained wind direction prediction model to obtain the wind direction sequence data measured by the wind direction measuring device within a future preset time period predicted by the wind direction prediction model.

10. A yaw control device for a wind turbine generator set, characterized in that, The yaw control device includes: The wind direction prediction unit is used to predict the wind direction of the free flow in front of the rotor of the wind turbine generator set within a preset time period in the future; The yaw control unit is used to determine the yaw control strategy of the wind turbine generator set based on the predicted wind direction of the free flow in front of the rotor within a preset future time period. The wind direction prediction unit is specifically configured as follows: Based on the historical wind direction sequence data measured by the wind direction measuring device of the wind turbine generator set, predict the wind direction sequence data measured by the wind direction measuring device within a preset time period in the future; Based on the predicted wind speed of the free flow in front of the impeller within the predicted future preset time period and the historical yaw deviation, the wind direction sequence data of the free flow in front of the impeller within the predicted future preset time period is determined, which corresponds to the wind direction sequence data measured by the wind direction measuring device within the predicted future preset time period.

11. A computer device, characterized in that, The computer device includes: processor; and Memory, which stores computer programs When the computer program is executed by the processor, it implements the yaw control method for wind turbine generator sets as described in any one of claims 1 to 9.

12. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the yaw control method for wind turbine generator sets as described in any one of claims 1 to 9.

Images