Yaw control method and device for wind turbine generator set

Abstract

The present disclosure provides a yaw control method and device for a wind turbine generator set. The yaw control method comprises: performing cluster analysis on historical environmental data and historical yaw angles of n wind turbine generator sets, wherein n is a positive integer; determining m second wind turbine generator sets related to a first wind turbine generator set from the n wind turbine generator sets through the cluster analysis, wherein the historical yaw angles of the m second wind turbine generator sets have an optimal correlation with the historical yaw angles of the first wind turbine generator set, wherein m is a positive integer; determining a mapping relationship between the historical yaw angles of the first wind turbine generator set and the historical yaw angles of the m second wind turbine generator sets; determining a current yaw angle estimation value of the first wind turbine generator set based on the identifiers of the m second wind turbine generator sets and the mapping relationship, wherein the current yaw angle estimation value is used for current yaw control of the first wind turbine generator set.

Description

Technical Field

[0001] The present disclosure relates to the field of wind power generation, and in particular to a yaw control method and device for a wind power generator set. Background Art

[0002] The yaw control system is an important part of ensuring the normal operation of wind turbines. The key to the yaw control system is how to obtain the accurate yaw angle. At present, wind turbines generally use wind vanes to obtain the accurate wind direction to calculate the yaw angle.

[0003] However, the current problem is that once the wind vane of a wind turbine is damaged, the wind turbine can only shut down and wait for a new wind vane to be replaced. If the wind vane is out of stock, it will need to shut down and wait for the spare parts to arrive, which will cause serious power generation losses during this period. Especially for offshore wind turbines, the replacement time of the wind vane is very long, resulting in a large loss of power generation. In addition, if the wind vane of the wind turbine is not completely damaged, the wind turbine will run at the wrong yaw angle, which will also cause power generation losses. Summary of the invention

[0004] The purpose of the embodiments of the present disclosure is to provide a yaw control method and device for a wind turbine generator set, so as to at least overcome many deficiencies in the prior art, enable the wind turbine generator set to perform yaw control based on an accurate yaw angle, and reduce the power generation loss of the wind turbine generator set.

[0005] According to an embodiment of the present disclosure, a yaw control method for a wind turbine is provided, the yaw control method comprising: performing cluster analysis on historical environmental data and historical yaw angles of n wind turbines, wherein n is a positive integer; determining m second wind turbines related to a first wind turbine among the n wind turbines through the cluster analysis, wherein the historical yaw angles of the m second wind turbines have an optimal correlation with the historical yaw angle of the first wind turbine, wherein m is a positive integer; determining a mapping relationship between the historical yaw angle of the first wind turbine and the historical yaw angles of the m second wind turbines; and determining a current yaw angle estimation value of the first wind turbine based on identifiers of the m second wind turbines and the mapping relationship, wherein the current yaw angle estimation value is used for current yaw control of the first wind turbine.

[0006] According to an embodiment of the present disclosure, a computer-readable storage medium storing a computer program is provided. When the computer program is executed by a processor, the yaw control method as described above is implemented.

[0007] According to an embodiment of the present disclosure, a computing device is provided, the computing device comprising: a processor; a memory storing a computer program, and when the computer program is executed by the processor, the yaw control method as described above is implemented.

[0008] According to an embodiment of the present disclosure, a yaw control device of a wind turbine is provided, the yaw control device comprising: a cluster analysis unit, configured to perform cluster analysis on historical environmental data and historical yaw angles of n wind turbines, wherein n is a positive integer, and through the cluster analysis, m second wind turbines related to a first wind turbine are determined from the n wind turbines, wherein the historical yaw angles of the m second wind turbines have an optimal correlation with the historical yaw angle of the first wind turbine, and m is a positive integer; a mapping relationship determination unit, configured to determine a mapping relationship between the historical yaw angle of the first wind turbine and the historical yaw angles of the m second wind turbines; and a yaw angle estimation unit, configured to determine a current yaw angle estimation value of the first wind turbine based on identifiers of the m second wind turbines and the mapping relationship, and the current yaw angle estimation value is used for current yaw control of the first wind turbine.

[0009] The yaw control method and device for a wind turbine generator set according to an embodiment of the present disclosure can achieve at least one of the following technical effects: real-time calculation of an estimated value of the yaw angle of the wind turbine generator set, and comparison with the yaw angle measurement value measured by a wind direction measuring device (e.g., a wind vane); when the deviation is too large, a corresponding reminder or warning is given to remind on-site operating personnel to check whether there are any abnormalities or damage in the components of the wind turbine generator set (e.g., a wind direction measuring device, a yaw control system) that make it impossible to use them normally; when the wind direction measuring device of the wind turbine generator set is damaged and needs to be replaced, the estimated value of the yaw angle of the wind turbine generator set is calculated in real time, and accurate yaw control of the wind turbine generator set is achieved based on the estimated value of the yaw angle, so that the wind turbine generator set can operate normally, avoid power generation loss, and ensure profits. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] The above and other objects and features of the present disclosure will become more apparent from the following description in conjunction with the accompanying drawings.

[0011] Figure 1 is a flow chart of a yaw control method according to an embodiment of the present disclosure.

[0012] Figure 2 is a flow chart of a yaw control method according to an embodiment of the present disclosure.

[0013] Figure 3 is a flow chart of a yaw control method according to an embodiment of the present disclosure.

[0014] Figure 4 is a flow chart of a yaw control method according to an embodiment of the present disclosure.

[0015] Figure 5 is a block diagram of a yaw control device and a controller of a wind turbine generator set according to an embodiment of the present disclosure.

[0016] Figure 6 is a block diagram of a yaw control device and a controller of a wind turbine generator set according to another embodiment of the present disclosure.

[0017] Figure 7 is a schematic diagram of a computing device according to an embodiment of the present disclosure. DETAILED DESCRIPTION

[0018] The yaw control of a wind turbine usually relies on its own wind direction measuring device (e.g., a wind vane), and the yaw angle is determined based on the wind direction measured by the wind direction measuring device. However, during operation, the wind turbine may have an inaccurate yaw angle due to various reasons, such as a stuck wind vane, abnormal yaw system, etc. The wind turbine cannot accurately face the wind, resulting in power generation loss. When the wind direction measuring device of a wind turbine is seriously damaged, the wind turbine has to stop working until maintenance personnel replace it with a new wind direction measuring device, and power generation will be lost during the waiting period. Especially when the wind direction measuring device is out of stock, a lot of time will be wasted waiting for the wind direction measuring device to arrive, resulting in serious power generation loss.

[0019] The present invention provides a yaw control method and device for a wind turbine generator set, which can enable the wind turbine generator set to perform yaw control based on an accurate yaw angle, thereby reducing the power generation loss of the wind turbine generator set. The following will be described with reference to the accompanying drawings, but the present invention is not limited to the following embodiments.

[0020] Figure 1 is a flow chart of a yaw control method according to an embodiment of the present disclosure.

[0021] According to an embodiment of the present disclosure, one or more wind turbines (for example, n wind turbines, where n is a positive integer) are usually provided in a wind farm, and historical environmental data and historical yaw angles of all wind turbines in the wind farm can be obtained (for example, periodically obtained), for example, the historical environmental data and historical yaw angles of all wind turbines can be obtained (for example, periodically obtained) from a data acquisition and supervisory control system (SCADA system) of the wind farm.

[0022] According to an embodiment of the present disclosure, a yaw control method includes: performing cluster analysis on historical environmental data and historical yaw angles of n wind turbines (step S11), wherein n is a positive integer; determining m second wind turbines related to a first wind turbine among the n wind turbines through the cluster analysis (step S12), wherein the historical yaw angles of the m second wind turbines have an optimal correlation with the historical yaw angle of the first wind turbine, and m is a positive integer; determining a mapping relationship between the historical yaw angle of the first wind turbine and the historical yaw angles of the m second wind turbines (step S13); and determining a current yaw angle estimation value of the first wind turbine based on identifiers (e.g., unit numbers) of the m second wind turbines and the mapping relationship (step S14), wherein the current yaw angle estimation value is used for current yaw control of the first wind turbine.

[0023] The yaw control method provided by the embodiment of the present disclosure can calculate the yaw angle estimation value of the first wind turbine in real time, and can realize accurate yaw control and monitoring of the first wind turbine based on the yaw angle estimation value, thereby ensuring the normal operation of the first wind turbine (for example, after the weather vane of the first wind turbine is damaged), avoiding power generation loss, and ensuring profits.

[0024] According to an embodiment of the present disclosure, historical environmental data may include at least one of the following items: historical environmental wind direction, environmental wind speed, environmental temperature, and environmental humidity, but the present invention is not limited thereto and may also include any historical data related to the working environment of the wind turbine generator set.

[0025] In step S11, a machine learning algorithm may be used to perform cluster analysis on the historical environmental data and historical yaw angles of the n wind turbines. For example, the machine learning algorithm may include at least one of the following: a neural network algorithm, a correlation analysis algorithm, a clustering algorithm, and a regression algorithm. However, the present invention is not limited thereto, and other analysis methods may also be used to perform cluster analysis on the historical environmental data and historical yaw angles of the n wind turbines.

[0026] The above cluster analysis is an analysis method that analyzes sample observations, integrates those with certain common characteristics, and then assigns them to specific groups, and finally forms many different set clusters. In the embodiment of the present disclosure, the above cluster analysis can be based on the characteristics of the historical environmental data and historical yaw angle of each wind turbine generator set in the n wind turbine generator sets, divide the historical environmental data and historical yaw angle of the n wind turbine generator sets into groups, and then analyze them according to the characteristics of each group. Through cluster analysis, m second wind turbine generator sets related to the first wind turbine generator set can be determined among the n wind turbine generator sets (step S12).

[0027] In the embodiment of the present disclosure, the first wind turbine generator set is used as the target wind turbine generator set, which can represent each wind turbine generator set in the n wind turbine generator sets. Therefore, by performing cluster analysis on the historical environmental data and historical yaw angles of the n wind turbine generator sets, a wind turbine generator set related to each wind turbine generator set can be determined in the n wind turbine generator sets, for example, m second wind turbine generator sets related to the first wind turbine generator set, where m can be less than or equal to n.

[0028] The historical yaw angles of the m second wind generator sets have the best correlation with the historical yaw angles of the first wind generator set, which means that the historical yaw angles of the m second wind generator sets are closest to the historical yaw angles of the first wind generator set under the historical environmental data. For example, under the historical environmental data, the historical yaw angles of the m second wind generator sets have the smallest deviation from the historical yaw angles of the first wind generator set relative to the historical yaw angles of the remaining wind generator sets. For example, the m second wind generator sets may include wind generator sets that are geographically closer to the first wind generator set, so that the historical yaw angles of the m second wind generator sets have the smallest deviation from the historical yaw angles of the first wind generator set relative to the historical yaw angles of the remaining wind generator sets.

[0029] The historical environmental data may correspond to a variety of environmental conditions. The various environmental conditions may include environmental conditions of a variety of environmental wind directions, a variety of environmental wind speeds, a variety of environmental temperatures and / or a variety of environmental humidity. For example, the historical environmental data may include that the historical environmental wind directions are south wind and north wind and / or the historical environmental temperatures are 20°C and 30°C. When the historical environmental wind direction is south wind and / or the historical environmental temperature is 20°C, the historical yaw angles of a part of the m second wind turbines are closest to the historical yaw angles of the first wind turbine relative to the historical yaw angles of the remaining second wind turbines. When the historical environmental wind direction is north wind and / or the historical environmental temperature is 30°C, the historical yaw angles of another part of the m second wind turbines are closest to the historical yaw angles of the first wind turbine relative to the historical yaw angles of the remaining second wind turbines.

[0030] In step S13, a machine learning algorithm may be used to determine the mapping relationship between the historical yaw angle of the first wind turbine generator set and the historical yaw angles of the m second wind turbine generator sets. For example, the machine learning algorithm may include at least one of the following items: a neural network algorithm, a correlation analysis algorithm, a clustering algorithm, and a regression algorithm. However, the present invention is not limited thereto, and other analysis methods may also be used to determine the mapping relationship between the historical yaw angle of the first wind turbine generator set and the historical yaw angles of the m second wind turbine generator sets.

[0031] According to an embodiment of the present disclosure, a correlation analysis algorithm may be used to determine the m second wind turbines related to the first wind turbine, and then a neural network algorithm may be used to determine the mapping relationship between the historical yaw angle of the first wind turbine and the historical yaw angle of the m second wind turbines. Optionally, a clustering algorithm may be used to determine the m second wind turbines related to the first wind turbine, and then a neural network algorithm may be used to determine the mapping relationship between the historical yaw angle of the first wind turbine and the historical yaw angle of the m second wind turbines. However, the present invention is not limited to the above examples, and other machine learning algorithms may also be used to determine the m second wind turbines related to the first wind turbine and / or determine the mapping relationship between the historical yaw angle of the first wind turbine and the historical yaw angle of the m second wind turbines.

[0032] According to an embodiment of the present disclosure, the mapping relationship between the historical yaw angle of the first wind turbine generator set and the historical yaw angles of the m second wind turbine generator sets may include weights respectively associated with different data values ​​in the historical environmental data and / or weights respectively associated with the historical yaw angles of the m second wind turbine generator sets.

[0033] The following will be combined Figure 2 and Figure 3 The yaw control method according to the embodiment of the present disclosure is further described.

[0034] Reference Figure 2 , according to an embodiment of the present disclosure, Figure 1 The step S11 shown may include preprocessing the historical environmental data and historical yaw angles of the n wind turbines to generate preprocessed historical environmental data and historical yaw angles (step S21); and performing cluster analysis on the preprocessed historical environmental data and historical yaw angles (step S22).

[0035] In step S21, the historical environmental data and historical yaw angles of the n wind turbines may be preprocessed by at least one of the following operations to generate preprocessed historical environmental data and historical yaw angles: for example, the historical environmental data and historical yaw angles of the n wind turbines may be cleaned to remove the historical environmental data and historical yaw angles corresponding to the forced non-yaw situation and / or the situation where the yaw cannot be yawed due to a fault, and the preprocessed historical environmental data and historical yaw angles may be generated; for example, the historical environmental data and historical yaw angles of the n wind turbines may be time-aligned to make the times of the historical environmental data and historical yaw angles of the n wind turbines consistent with each other, and the preprocessed historical environmental data and historical yaw angles may be generated; for example, the historical environmental data and historical yaw angles of the n wind turbines may be time-continuously checked, To remove the discontinuous data segments in time, generate the preprocessed historical environment data and historical yaw angle; for example, according to the historical environment data of the n wind turbines, classify the historical yaw angles of the n wind turbines (such as classifying the historical yaw angles according to different historical environment wind directions, and classifying the historical yaw angles according to different historical environment wind speeds), and generate the preprocessed historical environment data and historical yaw angle; for example, statistically analyze the historical environment data and historical yaw angles of the n wind turbines to generate the statistical analysis results of the historical environment data and the historical yaw angles, and generate the preprocessed historical environment data and historical yaw angles. The statistical analysis method may include at least one of the following methods: finding the average value, finding the percentile value, finding the maximum value, finding the minimum value, finding the standard deviation, and other methods for statistically distributing the data. Any two or more of the above operations can be combined with each other to be performed in sequence, or can be performed in parallel to finally generate the preprocessed historical environment data and historical yaw angle.

[0036] In addition, other methods may be used to pre-process the historical environmental data and historical yaw angles of the n wind turbine generator sets. The pre-processing can help the subsequent cluster analysis to accurately determine the m second wind turbine generator sets related to the first wind turbine generator set.

[0037] Reference Figure 3 , according to an embodiment of the present disclosure, Figure 1 The step S14 shown may include: acquiring (for example, periodically acquiring) current environmental data of other wind turbines among the n wind turbines except the first wind turbine (step S31); based on the current environmental data, determining p third wind turbines related to the first wind turbine among the m second wind turbines (step S32), where p is a positive integer and may be less than or equal to m; and determining a current yaw angle estimation value of the first wind turbine based on identifiers (for example, unit numbers) of the p third wind turbines and the mapping relationship.

[0038] In step S31, current environmental data of other wind turbines among the n wind turbines except the first wind turbine may be obtained (e.g., periodically) from a data acquisition and monitoring control system (SCADA system) of the wind farm. In an embodiment of the present disclosure, the current environmental data may include at least one of the following items: current environmental wind direction, environmental wind speed, environmental temperature, and environmental humidity. Other wind turbines except the first wind turbine may include m second wind turbines, and may even include the remaining wind turbines except the first wind turbine.

[0039] In step S32, the m second wind turbine generator sets may be searched for p third wind turbine generator sets related to the first wind turbine generator set under historical environmental data that is the same as or similar to the current environmental data. For example, the current environmental data may include that the current wind direction is south wind. The m second wind turbine generator sets may be searched for p third wind turbine generator sets related to the first wind turbine generator set when the wind is south wind.

[0040] When determining the estimated value of the current yaw angle of the first wind turbine generator set based on the identifiers (e.g., unit numbers) of the p third wind turbine generator sets and the mapping relationship, the current yaw angles of the p third wind turbine generator sets may be acquired (e.g., periodically acquired) based on the identifiers of the p third wind turbine generator sets (step S33); based on the mapping relationship, the current environmental data, and the current yaw angles of the p third wind turbine generator sets, the estimated value of the current yaw angle of the first wind turbine generator set may be determined (step S34). In addition, the current yaw angles of the p third wind turbine generator sets may be acquired (e.g., periodically acquired) based on the identifiers (e.g., unit numbers) of the p third wind turbine generator sets, and then the estimated value of the current yaw angle of the first wind turbine generator set may be determined based on the mapping relationship and the current yaw angles of the p third wind turbine generator sets.

[0041] In step S33, based on the identifications of the p third wind turbines, the current yaw angles of the p third wind turbines can be obtained (e.g., periodically obtained) from a supervisory control and data acquisition system (SCADA system) of the wind farm, or the current yaw angles of the p third wind turbines can be obtained (e.g., periodically obtained) from the p third wind turbines (e.g., a yaw control system of the third wind turbines).

[0042] In step S34, a mapping relationship corresponding to the current environmental data may be determined based on the mapping relationship (i.e., the mapping relationship between the historical yaw angle of the first wind turbine generator set and the historical yaw angles of the m second wind turbine generator sets) and the current environmental data. The mapping relationship corresponding to the current environmental data may include weights respectively associated with different data values ​​in the current environmental data and / or weights respectively associated with the historical yaw angles of the p third wind turbine generator sets. Then, the current yaw angles of the p third wind turbine generator sets may be substituted for the historical yaw angles of the p third wind turbine generator sets in the mapping relationship corresponding to the current environmental data, thereby determining the current mapping relationship. According to the current mapping relationship, the estimated value of the current yaw angle of the first wind turbine generator set may be determined.

[0043] According to an embodiment of the present disclosure, the yaw control method may further include determining a current yaw angle of the first wind turbine generator set based on a current yaw angle estimation value of the first wind turbine generator set. Figure 4 Give a description.

[0044] Reference Figure 4 The yaw control method may include obtaining (for example, periodically obtaining) a current yaw angle measurement value of the first wind turbine generator set (step S41); calculating a difference between a current yaw angle measurement value and a current yaw angle estimation value of the first wind turbine generator set (step S42); comparing the difference with a predetermined threshold to obtain a comparison result (for example, steps S43, S45); and determining a current yaw angle of the first wind turbine generator set from the current yaw angle measurement value and the current yaw angle estimation value according to the comparison result (for example, steps S43, S44, S47).

[0045] In step S41, the current yaw angle measurement value of the first wind turbine generator set may be obtained (e.g., periodically obtained) from a SCADA system of the wind farm, or obtained (e.g., periodically obtained) from the first wind turbine generator set (e.g., a yaw control system of the first wind turbine generator set). The current yaw angle measurement value may be determined based on the wind direction measured by a wind direction measuring device (e.g., a wind vane) of the first wind turbine generator set.

[0046] In step S42, the difference between the current yaw angle measurement value and the current yaw angle estimation value of the first wind turbine generator set may be calculated. The difference between the current yaw angle measurement value and the current yaw angle estimation value may be the absolute value after subtracting the current yaw angle measurement value of the first wind turbine generator set from the current yaw angle estimation value.

[0047] According to an embodiment of the present disclosure, the predetermined threshold may include a first predetermined threshold. In step S43, the difference between the current yaw angle measurement value and the current yaw angle estimation value may be compared with the first predetermined threshold to determine whether the difference between the current yaw angle measurement value and the current yaw angle estimation value is less than or equal to the first predetermined threshold. In response to the difference between the current yaw angle measurement value and the current yaw angle estimation value being less than or equal to the first predetermined threshold, the current yaw angle measurement value is determined as the current yaw angle of the first wind turbine generator set (step S44). In response to the difference between the current yaw angle measurement value and the current yaw angle estimation value being greater than or equal to the second predetermined threshold, the current yaw angle estimation value is determined as the current yaw angle of the first wind turbine generator set (step S47). Optionally, in response to the difference between the current yaw angle measurement value and the current yaw angle estimation value being greater than the first predetermined threshold and less than the second predetermined threshold, the current yaw angle measurement value is determined as the current yaw angle of the first wind turbine generator set (step S44).

[0048] In an embodiment of the present disclosure, by setting a first predetermined threshold and comparing the difference between the current yaw angle measurement value and the current yaw angle estimation value with the first predetermined threshold, it is possible to timely identify whether the wind direction measuring device is abnormal. For example, the first predetermined threshold may be set based on a small deviation of the yaw angle measurement value that occurs when the wind direction measuring device is abnormal (e.g., the wind direction measuring device (e.g., a wind vane) is stuck or has a minor fault, or a component related to the wind direction measuring device is faulty).

[0049] In the embodiment of the present disclosure, by setting a second predetermined threshold and comparing the difference between the current yaw angle measurement value and the current yaw angle estimation value with the second predetermined threshold, it is possible to timely identify whether the wind direction measuring device is seriously damaged and needs to be replaced. For example, the second predetermined threshold can be set according to the large deviation of the yaw angle measurement value that occurs when the wind direction measuring device is damaged (for example, the wind direction measuring device (for example, the wind vane) has a serious fault and cannot be used any more, or the components related to the wind direction measuring device are seriously damaged).

[0050] According to an embodiment of the present disclosure, the yaw control method may further send a notification according to the comparison result. By sending a notification, the staff may be reminded or warned to promptly check whether each component (e.g., wind direction measuring device) in the first wind turbine generator set is working properly, so as to promptly repair or replace the components. For example, in response to the difference between the current yaw angle measurement value and the current yaw angle estimation value being greater than a first predetermined threshold and less than a second predetermined threshold, a reminder may be sent to notify that the wind direction measuring device of the first wind turbine generator set is abnormal (step S46). The abnormality of the wind direction measuring device may include a wind direction measuring device (e.g., a wind vane) being stuck or having a minor fault, or a fault of a component related to the wind direction measuring device causing a minor error in the operation of the wind direction measuring device. By sending a reminder, the staff may be prompted to inspect and repair the wind direction measuring device of the first wind turbine generator set. Optionally, in response to the difference between the current yaw angle measurement value and the current yaw angle estimation value being greater than or equal to a second predetermined threshold, a warning may be sent to warn that the wind direction measuring device of the first wind turbine generator set is damaged (step S48). The wind direction measuring device is damaged, which may include that the wind direction measuring device (e.g., a wind vane) has a serious fault and cannot be used any more, or that a component related to the wind direction measuring device is seriously damaged, resulting in a serious error in the operation of the wind direction measuring device. By sending a warning, the staff may be prompted to check and replace the wind direction measuring device of the first wind turbine generator set.

[0051] The operation of sending the notification (e.g., steps S46 and S48) may be performed before or after determining the current yaw angle, or may be performed when determining the current yaw angle. In this way, while determining the current yaw angle in real time, the first wind turbine generator set may also be monitored for abnormality.

[0052] Figure 5 is a block diagram of a yaw control device 1 and a controller 2 of a first wind turbine generator set according to an embodiment of the present disclosure.

[0053] According to an embodiment of the present disclosure, the yaw control device 1 may be provided in a central control system (e.g., a central monitoring terminal) of a wind farm. The central control system is used to monitor and control the operation of each wind turbine in the wind farm. The various units in the yaw control device 1 may be implemented using hardware or software modules in the central control system. The controller 2 is located in the first wind turbine and is used to control the yaw operation of the first wind turbine based on the current yaw angle of the first wind turbine. For example, the controller 2 may be a main controller or a yaw controller of the first wind turbine. The controller 2 may obtain (e.g., periodically obtain) the current yaw angle from the yaw control device 1.

[0054] The yaw control device 1 may include a cluster analysis unit 11, which is configured to perform cluster analysis on historical environmental data and historical yaw angles of n wind turbines, wherein n is a positive integer, and through the cluster analysis, m second wind turbines related to the first wind turbine are determined among the n wind turbines, wherein the historical yaw angles of the m second wind turbines have an optimal correlation with the historical yaw angles of the first wind turbine, and m is a positive integer; a mapping relationship determination unit 12, which is configured to determine a mapping relationship between the historical yaw angles of the first wind turbine and the historical yaw angles of the m second wind turbines; and a yaw angle estimation unit 13, which is configured to determine a current yaw angle estimation value of the first wind turbine based on the identifiers of the m second wind turbines and the mapping relationship, and the current yaw angle estimation value is used for current yaw control of the first wind turbine.

[0055] Optionally, the yaw control device 1 may further include a yaw angle determination unit 15, which is configured to: obtain a current yaw angle measurement value of the first wind turbine generator set; calculate the difference between the current yaw angle measurement value and the current yaw angle estimation value of the first wind turbine generator set; compare the difference between the current yaw angle measurement value and the current yaw angle estimation value with a predetermined threshold to obtain a comparison result; and determine the current yaw angle of the first wind turbine generator set from the current yaw angle measurement value and the current yaw angle estimation value according to the comparison result.

[0056] Optionally, the yaw control device 1 may further include a notification unit 14, which is configured to: obtain a current yaw angle measurement value of the first wind turbine generator set; calculate the difference between the current yaw angle measurement value and the current yaw angle estimation value of the first wind turbine generator set; compare the difference between the current yaw angle measurement value and the current yaw angle estimation value with a predetermined threshold to obtain a comparison result; and send a notification based on the comparison result.

[0057] Please refer to the above combined Figures 1 to 4 The yaw control method described is used to understand the specific details of the corresponding processing performed by the yaw control device 1 and its various units, which will not be repeated here.

[0058] According to an embodiment of the present disclosure, the yaw angle determination unit 15 may communicate with the controller 2. For example, the yaw angle determination unit 15 may establish communication with the controller 2 by sending a handshake signal to the controller 2. In response to the difference between the current yaw angle measurement value and the current yaw angle estimation value of the first wind turbine being greater than or equal to a second predetermined threshold, the yaw angle determination unit 15 may send the current yaw angle estimation value to the controller 2, and instruct the controller 2 to determine the current yaw angle estimation value as the current yaw angle of the first wind turbine. When the yaw angle determination unit 15 determines that the difference between the current yaw angle measurement value and the current yaw angle estimation value of the first wind turbine is less than the second predetermined threshold, the controller 2 may use the current yaw angle measurement value as the current yaw angle for yaw control.

[0059] According to another embodiment of the present disclosure, only when the difference between the current yaw angle measurement value and the current yaw angle estimation value of the first wind turbine generator set is greater than or equal to the second predetermined threshold value, the yaw angle determination unit 15 establishes communication with the controller 2, for example, by sending a handshake signal to the controller 2 to establish communication with the controller 2. Then, the yaw angle determination unit 15 may send the current yaw angle estimation value to the controller 2 as the current yaw angle of the first wind turbine generator set.

[0060] According to an embodiment of the present disclosure, after the yaw angle determination unit 15 first determines that the difference between the current yaw angle measurement value and the current yaw angle estimation value of the first wind turbine generator set is greater than or equal to the second predetermined threshold, the yaw angle determination unit 15 can maintain communication with the controller 2 so as to send the current yaw angle estimation value determined in real time by the yaw angle estimation unit 13 to the controller 2, so that the controller 2 always uses the current yaw angle estimation value as the current yaw angle for real-time control without the yaw angle determination unit 15 repeatedly comparing the difference between the current yaw angle measurement value and the current yaw angle estimation value with the first predetermined threshold and the second predetermined threshold. The reason is that when the difference between the current yaw angle measurement value and the current yaw angle estimation value of the first wind turbine generator set is greater than or equal to the second predetermined threshold, it indicates that the current yaw angle measurement value has a large error, the wind direction measurement device of the first wind turbine generator set has been seriously damaged and cannot work normally, and the current yaw angle measurement value has failed. After the wind direction measuring device of the first wind turbine generator set is repaired or replaced, the maintenance personnel may instruct the yaw angle determination unit 15 to compare the difference between the current yaw angle measurement value and the current yaw angle estimation value with the first predetermined threshold and the second predetermined threshold again.

[0061] According to an embodiment of the present disclosure, the yaw angle determination unit 15 may periodically receive a current yaw angle estimation value from the yaw angle estimation unit 13. The current yaw angle estimation value may change or remain unchanged. In response to a change in the current yaw angle estimation value, the handshake signal transmitted between the yaw angle determination unit 15 and the controller 2 may change, and the yaw angle determination unit 15 sends the current yaw angle estimation value to the controller 2 in real time. When the current yaw angle estimation value is determined as the current yaw angle and the current yaw angle estimation value remains unchanged, the handshake signal transmitted between the yaw angle determination unit 15 and the controller 2 may remain unchanged. Optionally, when the current yaw angle measurement value is determined as the current yaw angle, the handshake signal transmitted between the yaw angle determination unit 15 and the controller 2 may remain unchanged.

[0062] Figure 6 is a block diagram of a yaw control device 3 and a controller 4 of a first wind turbine generator set according to another embodiment of the present disclosure.

[0063] According to an embodiment of the present disclosure, the yaw control device 3 may be provided in a central control system (e.g., a central monitoring terminal) of a wind farm. The central control system is used to monitor and control the operation of each wind turbine generator set in the wind farm. The controller 4 is located in the first wind turbine generator set and is used to control the yaw operation of the first wind turbine generator set based on the current yaw angle of the first wind turbine generator set. The yaw control device 3 may communicate with the controller 4.

[0064] The yaw control device 3 may include a cluster analysis unit 31, which is configured to perform cluster analysis on the historical environmental data and historical yaw angles of n wind turbines, wherein n is a positive integer, and through the cluster analysis, m second wind turbines related to the first wind turbine are determined among the n wind turbines, wherein the historical yaw angles of the m second wind turbines have an optimal correlation with the historical yaw angle of the first wind turbine, and m is a positive integer; a mapping relationship determination unit 32, which is configured to determine the mapping relationship between the historical yaw angle of the first wind turbine and the historical yaw angle of the m second wind turbines.

[0065] The controller 4 may include a yaw angle estimation unit 41. The cluster analysis unit 31 may send the identifiers of the m second wind turbines related to the first wind turbine to the yaw angle estimation unit 41. The mapping relationship determination unit 32 may send the mapping relationship between the historical yaw angle of the first wind turbine and the historical yaw angle of the m second wind turbines to the yaw angle estimation unit 41. In this way, the controller 4 of the first wind turbine determines the current yaw angle estimation value of the first wind turbine based on the identifiers of the m second wind turbines and the mapping relationship between the historical yaw angle of the first wind turbine and the historical yaw angle of the m second wind turbines, and may determine the current yaw angle based on the current yaw angle estimation value. For example, the yaw control device 3 may periodically send the identifiers of the m second wind turbines and / or the mapping relationship to the controller 4 of the first wind turbine, so as to periodically update the identifiers of the m second wind turbines and the mapping relationship between the historical yaw angle of the first wind turbine and the historical yaw angle of the m second wind turbines stored in the controller 4.

[0066] The yaw angle estimation unit 41 is configured to determine the current yaw angle estimation value of the first wind turbine generator set based on the identifiers of the m second wind turbine generator sets and the mapping relationship, and the current yaw angle estimation value is used for the current yaw control of the first wind turbine generator set. Optionally, the controller 4 may also include a yaw angle determination unit 43, and the yaw angle determination unit 43 is configured to: obtain the current yaw angle measurement value of the first wind turbine generator set; calculate the difference between the current yaw angle measurement value and the current yaw angle estimation value of the first wind turbine generator set; compare the difference between the current yaw angle measurement value and the current yaw angle estimation value with a predetermined threshold to obtain a comparison result; and determine the current yaw angle of the first wind turbine generator set from the current yaw angle measurement value and the current yaw angle estimation value according to the comparison result.

[0067] Optionally, the controller 4 may further include a notification unit 42, which is configured to: obtain a current yaw angle measurement value of the first wind turbine generator set; calculate the difference between the current yaw angle measurement value and the current yaw angle estimation value of the first wind turbine generator set; compare the difference between the current yaw angle measurement value and the current yaw angle estimation value with a predetermined threshold to obtain a comparison result; and send a notification based on the comparison result.

[0068] Please refer to the above combined Figures 1 to 4 The yaw control method described is used to understand the specific details of the corresponding processing performed by the yaw control device 1 and its various units, which will not be repeated here.

[0069] According to an embodiment of the present disclosure, there is also provided a computer-readable storage medium having a computer program stored thereon, which can realize reference to Figures 1 to 4 The described yaw control method, for example, may execute the following steps: perform cluster analysis on historical environmental data and historical yaw angles of n wind turbines, wherein n is a positive integer; determine m second wind turbines related to the first wind turbine among the n wind turbines through the cluster analysis, wherein the historical yaw angles of the m second wind turbines have an optimal correlation with the historical yaw angles of the first wind turbine, and m is a positive integer; determine a mapping relationship between the historical yaw angles of the first wind turbine and the historical yaw angles of the m second wind turbines; and determine a current yaw angle estimate of the first wind turbine based on the identifiers of the m second wind turbines and the mapping relationship, wherein the current yaw angle estimate is used for current yaw control of the first wind turbine.

[0070] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In an embodiment of the present disclosure, a computer-readable storage medium may be any tangible medium containing or storing a computer program that may be used by or in conjunction with an instruction execution system, device or device. The computer program contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination thereof. The computer-readable storage medium may be contained in any device; it may also exist alone without being assembled into the device.

[0071] According to an embodiment of the present disclosure, a computing device is also provided. Figure 7 is a schematic diagram of a computing device 5 according to an embodiment of the present disclosure.

[0072] Reference Figure 7According to the embodiment of the present disclosure, the computing device 5 may include a memory 51 and a processor 52, and a computer program 53 is stored in the memory 51. When the computer program 53 is executed by the processor 52, the yaw control method according to the embodiment of the present disclosure is implemented. For example, the following steps may be performed: cluster analysis is performed on the historical environmental data and historical yaw angles of n wind turbines, wherein n is a positive integer; through the cluster analysis, m second wind turbines related to the first wind turbine are determined from the n wind turbines, wherein the historical yaw angles of the m second wind turbines have the best correlation with the historical yaw angle of the first wind turbine, and m is a positive integer; a mapping relationship between the historical yaw angle of the first wind turbine and the historical yaw angles of the m second wind turbines is determined; based on the identifiers of the m second wind turbines and the mapping relationship, a current yaw angle estimation value of the first wind turbine is determined, and the current yaw angle estimation value is used for the current yaw control of the first wind turbine.

[0073] Figure 7 The computing device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0074] The above has been referred to Figures 1 to 7 The yaw control method and device, computer readable storage medium, and computing device according to the embodiments of the present disclosure are described. However, it should be understood that: Figure 5 and 6 The yaw control device and its respective units shown in the figure may be configured as software, hardware, firmware or any combination of the above items to perform specific functions. Figure 7 The computing device shown in is not limited to including the components shown above, but some components may be added or deleted as needed, and the above components may also be combined.

[0075] By using the yaw control method and device according to the embodiments of the present disclosure, at least one of the following technical effects can be achieved: the estimated value of the yaw angle of the wind turbine is calculated in real time, and compared with the yaw angle measurement value measured by a wind direction measuring device (for example, a wind vane), and a corresponding reminder or warning is given when the deviation is too large, reminding the on-site operating personnel to check whether the components in the wind turbine (for example, a wind direction measuring device, a yaw control system) are abnormal or damaged so that they cannot be used normally; even if the wind direction measuring device of the wind turbine is damaged and needs to be replaced, the estimated value of the yaw angle of the wind turbine can be calculated in real time, and accurate yaw control of the wind turbine can be achieved based on the estimated value of the yaw angle, so that the wind turbine can operate normally, avoid power generation loss, and ensure profits.

[0076] According to the yaw control method and device of the embodiments of the present disclosure, the working conditions of the wind turbines in the entire wind farm can be monitored online in real time, and yaw system abnormalities can be reported in time to help discover problems in time so that they can be discovered and solved in advance; at the same time, when components related to yaw angle measurement such as wind direction measuring devices are seriously damaged, the real-time determination of the yaw angle can be taken over, so that the wind turbines can operate in a fault-tolerant manner and recover the power generation loss caused by long-term shutdown waiting for component replacement. In this way, it can ensure that the wind turbines operate correctly to the wind, ensure maximum output, and increase power generation.

[0077] The control logic or functions performed by each component or controller in the control system can be represented by a flow chart or similar diagram in one or more figures. These figures provide representative control strategies and / or logic, which can be implemented using one or more processing strategies (such as event-driven, interrupt-driven, multi-tasking, multi-threading, etc.). Therefore, the various steps or functions shown can be performed in the order shown, performed in parallel, or omitted in some cases. Although not always explicitly shown, it will be recognized by those of ordinary skill in the art that one or more steps or functions shown can be repeatedly performed according to the specific processing strategy used.

[0078] While the present disclosure has been shown and described with reference to preferred embodiments, it will be understood by those skilled in the art that various modifications and variations may be made to these embodiments without departing from the spirit and scope of the disclosure as defined by the appended claims.

Claims

1. A yaw control method for a wind turbine generator set, It is characterized in that The yaw control method comprises: Performing cluster analysis on historical environmental data and historical yaw angles of n wind turbine generator sets, wherein n is a positive integer; Determine m second wind turbines related to the first wind turbine from the n wind turbines through the cluster analysis, wherein the historical yaw angles of the m second wind turbines have an optimal correlation with the historical yaw angle of the first wind turbine, and m is a positive integer; Determine a mapping relationship between a historical yaw angle of the first wind turbine generator set and the historical yaw angles of the m second wind turbine generator sets; Based on the identifiers of the m second wind turbine generator sets and the mapping relationship, a current yaw angle estimation value of the first wind turbine generator set is determined, and the current yaw angle estimation value is used for current yaw control of the first wind turbine generator set.

2. The yaw control method according to claim 1, It is characterized in that Cluster analysis of historical environmental data and historical yaw angles of n wind turbines includes: Preprocessing the historical environmental data and historical yaw angles of the n wind turbine generator sets to generate preprocessed historical environmental data and historical yaw angles; Perform cluster analysis on the preprocessed historical environmental data and historical yaw angles.

3. The yaw control method according to claim 2, It is characterized in that Preprocessing the historical environmental data and the historical yaw angles of the n wind turbine generator sets to generate preprocessed historical environmental data and historical yaw angles includes performing at least one of the following operations: Cleaning the historical environmental data and historical yaw angles of the n wind turbine generator sets to remove the historical environmental data and historical yaw angles corresponding to the forced non-yaw situation and / or the situation where the yaw cannot be yawed due to a fault, and generating pre-processed historical environmental data and historical yaw angles; Performing time alignment on the historical environmental data and historical yaw angles of the n wind turbine generator sets so that the times of the historical environmental data and historical yaw angles of the n wind turbine generator sets are consistent with each other, and generating preprocessed historical environmental data and historical yaw angles; Performing a time continuity check on the historical environmental data and historical yaw angles of the n wind turbine generator sets to remove time-discontinuous data segments and generate pre-processed historical environmental data and historical yaw angles; Classifying the historical yaw angles of the n wind turbines according to the historical environmental data of the n wind turbines to generate pre-processed historical environmental data and historical yaw angles; Performing statistical analysis on the historical environmental data and the historical yaw angles of the n wind turbine generator sets to generate statistical analysis results of the historical environmental data and the historical yaw angles, and generating pre-processed historical environmental data and historical yaw angles.

4. The yaw control method according to claim 1, It is characterized in that Determining the current yaw angle estimation value of the first wind turbine generator set based on the identifiers of the m second wind turbine generator sets and the mapping relationship comprises: Acquiring current environmental data of other wind turbine generator sets among the n wind turbine generator sets except the first wind turbine generator set; Based on the current environmental data, determining p third wind turbine generator sets related to the first wind turbine generator set from the m second wind turbine generator sets, where p is a positive integer; A current yaw angle estimation value of the first wind turbine generator set is determined based on the identifiers of the p third wind turbine generator sets and the mapping relationship.

5. The yaw control method according to claim 4, It is characterized in that Determining the current yaw angle estimation value of the first wind turbine generator set based on the identifiers of the p third wind turbine generator sets and the mapping relationship comprises: Based on the identifiers of the p third wind turbine generator sets, acquiring current yaw angles of the p third wind turbine generator sets; Based on the mapping relationship, the current environmental data and the current yaw angles of the p third wind turbine generator sets, an estimated value of the current yaw angle of the first wind turbine generator set is determined.

6. The yaw control method according to any one of claims 1 to 5, It is characterized in that The yaw control method further comprises: Obtaining a current yaw angle measurement value of the first wind turbine generator set; Calculating a difference between a current yaw angle measurement value and a current yaw angle estimation value of the first wind turbine generator set; comparing the difference with a predetermined threshold to obtain a comparison result; According to the comparison result, the current yaw angle of the first wind turbine generator set is determined from the current yaw angle measurement value and the current yaw angle estimation value.

7. The yaw control method according to claim 6, It is characterized in that The predetermined threshold comprises a first predetermined threshold, According to the comparison result, determining the current yaw angle of the first wind turbine generator set from the current yaw angle measurement value and the current yaw angle estimation value comprises: In response to the difference being less than or equal to a first predetermined threshold, determining a current yaw angle measurement value as a current yaw angle of the first wind turbine generator system.

8. The yaw control method according to claim 7, It is characterized in that The predetermined threshold value also includes a second predetermined threshold value, and the second predetermined threshold value is greater than the first predetermined threshold value. According to the comparison result, determining the current yaw angle of the first wind turbine generator set from the current yaw angle measurement value and the current yaw angle estimation value comprises: In response to the difference being greater than or equal to a second predetermined threshold, determining the current yaw angle estimation value as the current yaw angle of the first wind turbine generator set; and / or, In response to the difference being greater than a first predetermined threshold and less than a second predetermined threshold, the current yaw angle measurement value is determined as a current yaw angle of the first wind turbine generator system.

9. The yaw control method according to any one of claims 1 to 5, It is characterized in that The yaw control method further comprises: Obtaining a current yaw angle measurement value of the first wind turbine generator set; Calculating a difference between a current yaw angle measurement value and a current yaw angle estimation value of the first wind turbine generator set; comparing the difference with a predetermined threshold to obtain a comparison result; A notification is sent based on the comparison result.

10. The yaw control method according to claim 9, It is characterized in that The predetermined threshold includes a first predetermined threshold and a second predetermined threshold, the second predetermined threshold is greater than the first predetermined threshold, Sending a notification according to the comparison result includes: In response to the difference being greater than a first predetermined threshold and less than a second predetermined threshold, sending a reminder to notify that an abnormality exists in a wind direction measuring device of the first wind turbine generator set; and / or, In response to the difference being greater than or equal to a second predetermined threshold, a warning is sent to warn that the wind direction measuring device of the first wind turbine generator system is damaged.

11. The yaw control method according to any one of claims 1 to 5, It is characterized in that Performing cluster analysis on the historical environmental data and historical yaw angles of the n wind turbines using a machine learning algorithm, and / or A machine learning algorithm is used to determine a mapping relationship between the historical yaw angle of the first wind turbine generator set and the historical yaw angles of the m second wind turbine generator sets. The machine learning algorithm includes at least one of the following: a neural network algorithm, a correlation analysis algorithm, a clustering algorithm, and a regression algorithm.

12. The yaw control method according to any one of claims 1 to 5, It is characterized in that The historical environmental data includes at least one of the following items: historical environmental wind direction, environmental wind speed, environmental temperature, and environmental humidity.

13. A computer-readable storage medium storing a computer program, It is characterized in that When the computer program is executed by a processor, the yaw control method according to any one of claims 1 to 12 is implemented.

14. A computing device, It is characterized in that The computing device comprises: processor; A memory storing a computer program, wherein when the computer program is executed by a processor, the yaw control method according to any one of claims 1 to 12 is implemented.

15. A yaw control device for a wind turbine generator set, It is characterized in that The yaw control device comprises: a cluster analysis unit, configured to perform cluster analysis on historical environmental data and historical yaw angles of n wind turbines, wherein n is a positive integer, and to determine m second wind turbines related to the first wind turbine among the n wind turbines through the cluster analysis, wherein the historical yaw angles of the m second wind turbines have an optimal correlation with the historical yaw angle of the first wind turbine, and m is a positive integer; a mapping relationship determining unit, configured to determine a mapping relationship between a historical yaw angle of the first wind turbine generator set and the historical yaw angles of the m second wind turbine generator sets; The yaw angle estimation unit is configured to determine a current yaw angle estimation value of the first wind turbine generator set based on the identifiers of the m second wind turbine generator sets and the mapping relationship, wherein the current yaw angle estimation value is used for current yaw control of the first wind turbine generator set.

16. The yaw control device according to claim 15, It is characterized in that The cluster analysis unit is configured to: Preprocessing the historical environmental data and historical yaw angles of the n wind turbine generator sets to generate preprocessed historical environmental data and historical yaw angles; Perform cluster analysis on the preprocessed historical environmental data and historical yaw angles.

17. The yaw control device according to claim 16, It is characterized in that The cluster analysis unit is configured to perform at least one of the following operations: Cleaning the historical environmental data and historical yaw angles of the n wind turbine generator sets to remove the historical environmental data and historical yaw angles corresponding to the forced non-yaw situation and / or the situation where the yaw cannot be yawed due to a fault, and generating pre-processed historical environmental data and historical yaw angles; Performing time alignment on the historical environmental data and historical yaw angles of the n wind turbine generator sets so that the times of the historical environmental data and historical yaw angles of the n wind turbine generator sets are consistent with each other, and generating preprocessed historical environmental data and historical yaw angles; Performing a time continuity check on the historical environmental data and historical yaw angles of the n wind turbine generator sets to remove time-discontinuous data segments and generate pre-processed historical environmental data and historical yaw angles; Classifying the historical yaw angles of the n wind turbines according to the historical environmental data of the n wind turbines to generate pre-processed historical environmental data and historical yaw angles; Performing statistical analysis on the historical environmental data and the historical yaw angles of the n wind turbine generator sets to generate statistical analysis results of the historical environmental data and the historical yaw angles, and generating pre-processed historical environmental data and historical yaw angles.

18. The yaw control device according to claim 15, It is characterized in that The yaw angle estimation unit is configured as: Acquiring current environmental data of other wind turbine generator sets among the n wind turbine generator sets except the first wind turbine generator set; Based on the current environmental data, determining p third wind turbine generator sets related to the first wind turbine generator set from the m second wind turbine generator sets, where p is a positive integer; A current yaw angle estimation value of the first wind turbine generator set is determined based on the identifiers of the p third wind turbine generator sets and the mapping relationship.

19. The yaw control device according to claim 18, It is characterized in that The yaw angle estimation unit is configured as: Based on the identifiers of the p third wind turbine generator sets, acquiring current yaw angles of the p third wind turbine generator sets; Based on the mapping relationship, the current environmental data and the current yaw angles of the p third wind turbine generator sets, an estimated value of the current yaw angle of the first wind turbine generator set is determined.

20. The yaw control device according to any one of claims 15 to 19, It is characterized in that The yaw control device further comprises a yaw angle determination unit, wherein the yaw angle determination unit is configured to: Obtaining a current yaw angle measurement value of the first wind turbine generator set; Calculating a difference between a current yaw angle measurement value and a current yaw angle estimation value of the first wind turbine generator set; comparing the difference with a predetermined threshold to obtain a comparison result; According to the comparison result, the current yaw angle of the first wind turbine generator set is determined from the current yaw angle measurement value and the current yaw angle estimation value.

21. The yaw control device according to claim 20, It is characterized in that The predetermined threshold comprises a first predetermined threshold, The yaw angle determination unit is configured to: in response to the difference being less than or equal to a first predetermined threshold, determine a current yaw angle measurement value as a current yaw angle of the first wind turbine generator system.

22. The yaw control device according to claim 21, It is characterized in that The predetermined threshold value also includes a second predetermined threshold value, and the second predetermined threshold value is greater than the first predetermined threshold value. The yaw angle determination unit is configured to: In response to the difference being greater than or equal to a second predetermined threshold, determining the current yaw angle estimation value as the current yaw angle of the first wind turbine generator set; and / or, In response to the difference being greater than a first predetermined threshold and less than a second predetermined threshold, the current yaw angle measurement value is determined as a current yaw angle of the first wind turbine generator system.

23. The yaw control device according to any one of claims 15 to 19, It is characterized in that The yaw control device further includes a notification unit, which is configured to: Obtaining a current yaw angle measurement value of the first wind turbine generator set; Calculating a difference between a current yaw angle measurement value and a current yaw angle estimation value of the first wind turbine generator set; comparing the difference with a predetermined threshold to obtain a comparison result; A notification is sent based on the comparison result.

24. The yaw control device according to claim 23, It is characterized in that The predetermined threshold includes a first predetermined threshold and a second predetermined threshold, the second predetermined threshold is greater than the first predetermined threshold, The notification unit is further configured to: In response to the difference being greater than a first predetermined threshold and less than a second predetermined threshold, sending a reminder to notify that an abnormality exists in a wind direction measuring device of the first wind turbine generator set; and / or, In response to the difference being greater than or equal to a second predetermined threshold, a warning is sent to warn that the wind direction measuring device of the first wind turbine generator system is damaged.

25. The yaw control device according to any one of claims 15 to 19, It is characterized in that The cluster analysis unit is configured to: Performing cluster analysis on the historical environmental data and historical yaw angles of the n wind turbines using a machine learning algorithm, and / or A machine learning algorithm is used to determine a mapping relationship between the historical yaw angle of the first wind turbine generator set and the historical yaw angles of the m second wind turbine generator sets. The machine learning algorithm includes at least one of the following: a neural network algorithm, a correlation analysis algorithm, a clustering algorithm, and a regression algorithm.

26. The yaw control device according to any one of claims 15 to 19, It is characterized in that The historical environmental data includes at least one of the following items: historical environmental wind direction, environmental wind speed, environmental temperature, and environmental humidity.

Images