Turbulent flow capacity reduction state detection method, device and equipment of wind turbine generator and medium

Abstract

The invention discloses a wind turbine generator turbulence capacity reduction state detection method and device, equipment and a medium, and the method comprises the steps: obtaining first operation data of a first wind turbine generator in a first time interval, carrying out the feature extraction of the first operation data, and obtaining the first power feature data and first turbulence feature data of the first wind turbine generator; based on the first power characteristic data and the first turbulence characteristic data, whether the first wind turbine generator has a capacity reduction state and turbulence intensity abnormity or not is determined, and the time coincidence rate of the capacity reduction state and the turbulence intensity abnormity is further determined in response to the capacity reduction state and the turbulence intensity abnormity of the first wind turbine generator; and under the condition that the time coincidence rate is larger than the coincidence rate threshold value, it is determined that the first wind turbine generator has a turbulent flow capacity reduction state. According to the embodiment of the invention, the operation data of the wind turbine generator are analyzed, so that whether the wind turbine generator has a turbulent flow capacity reduction state or not can be accurately detected.

Description

Technical Field

[0001] The present application belongs to the technical field of wind power generation, and in particular relates to a method, device, equipment and medium for detecting turbulent capacity reduction status of a wind turbine set. Background Art

[0002] Turbulence is a state of flow in which a fluid is irregular, random and fluctuates greatly. Turbulent wind conditions can affect the load, service life and operating efficiency of wind turbines. From the perspective of the impact on the power generation of wind turbines, turbulence can cause fluctuations in wind speed and changes in wind direction, making the actual output power of wind turbines lower than the theoretical power. Especially near the rated wind speed, due to the effect of turbulence, the instantaneous wind speed is sometimes higher than the rated wind speed and sometimes lower than the rated wind speed. The wind turbine may over-retract its blades when the wind speed is higher than the rated wind speed, resulting in failure to generate power at full load; and when the wind speed is lower than the rated wind speed, the wind turbine may still be in the variable pitch state of unloading wind energy at the last moment, resulting in further reduction in wind energy conversion efficiency. From a safety perspective, turbulence can increase the limit load and fatigue load of the main components of the wind turbine, especially the tower base load and blade root load. The aerodynamic loads borne by these components become alternating loads, which can easily cause fatigue damage and fracture of the material. In addition, turbulence can also affect the yaw system of the wind turbine, making yaw control more difficult and causing excessive yaw frequency. These will lead to problems such as inaccurate wind direction, excessive vibration, and shutdown failure of the wind turbine, reducing the safety and reliability of the wind turbine.

[0003] Based on the above problems, it is necessary to monitor the turbulent environment in which the wind turbine is located. By monitoring the turbulent capacity reduction of the unit, turbulence phenomena can be identified and handled in a timely manner, and the operation and maintenance personnel can be guided to inspect the wind turbine tower and blades to avoid long-term overload operation of the unit blades and tower under complex wind conditions caused by turbulence, which affects the health and life of the unit. Turbulent capacity reduction refers to the reduced capacity operation of the wind turbine caused by turbulence.

[0004] In view of this, there is an urgent need for a solution that can detect the turbulent capacity reduction state of a wind turbine. Summary of the invention

[0005] The embodiments of the present application provide a method, device, equipment and medium for detecting the turbulent capacity reduction state of a wind turbine generator set, which can accurately detect the turbulent capacity reduction state of a wind turbine generator set.

[0006] In a first aspect, an embodiment of the present application provides a method for detecting a turbulent capacity reduction state of a wind turbine generator set, comprising:

[0007] Acquire first operating data of a first wind turbine generator set within a first time interval;

[0008] Performing feature extraction processing on the first operation data to obtain first power feature data and first turbulence feature data of the first wind turbine generator set;

[0009] Determine whether the first wind turbine generator set is in a reduced capacity state within a first time interval based on the first power characteristic data;

[0010] Determining whether the first wind turbine generator set has abnormal turbulence intensity within a first time interval based on the first turbulence characteristic data;

[0011] In response to the first wind turbine generator set being in a derated state and having abnormal turbulence intensity within a first time interval, determining a time coincidence rate of the derated state and the abnormal turbulence intensity;

[0012] In response to the time overlap rate being greater than the overlap rate threshold, it is determined that the first wind turbine generator set is in a turbulent capacity reduction state.

[0013] As a possible implementation, the operation data of the first wind turbine generator set includes wind speed and converter active power, and feature extraction processing is performed on the first operation data to obtain first power feature data and first turbulence feature data of the first wind turbine generator set, including:

[0014] Dividing a first time interval corresponding to the first operation data into a plurality of time periods;

[0015] For each time period, the operating data in the time period is calculated to obtain the power mean, wind speed mean and wind speed standard deviation in the time period;

[0016] For each time period, the mean wind speed in the time period is taken as the wind speed corresponding to the time period, the mean power in the time period is taken as the power corresponding to the time period, and the quotient of the wind speed standard deviation and the wind speed mean in the time period is taken as the turbulence intensity corresponding to the time period;

[0017] taking a plurality of wind speeds and a plurality of powers corresponding to a plurality of time periods as first power characteristic data;

[0018] A plurality of wind speeds and a plurality of turbulence intensities corresponding to a plurality of time periods are used as first turbulence characteristic data.

[0019] As a possible implementation manner, determining whether the first wind turbine generator set is in a reduced capacity state within a first time interval based on the first power characteristic data includes:

[0020] According to multiple wind speed conditions, multiple powers in the first power characteristic data are divided into multiple first power data sets, and the wind speeds corresponding to the powers in the same first power data set belong to the same wind speed condition;

[0021] For each first power data set, determining a first power characteristic value corresponding to the first power data set according to the power in the first power data set;

[0022] For each first power data set, comparing a first power characteristic value corresponding to the first power data set with a power threshold of a wind speed condition corresponding to the first power data set;

[0023] Determine a first number of target power data sets among the plurality of first power data sets, the target power data set being a first power data set whose first power characteristic value is less than a power threshold corresponding to a wind speed condition;

[0024] In response to the first number being greater than a first number threshold, determining that the first wind turbine generator system is in a reduced capacity state within a first time interval;

[0025] In response to the first number being less than or equal to a first number threshold, it is determined that the first wind turbine generator system is not in a reduced capacity state within the first time interval.

[0026] As a possible implementation manner, determining whether the first wind turbine generator set has abnormal turbulence intensity within the first time interval based on the first turbulence characteristic data includes:

[0027] According to the plurality of wind speed conditions, the plurality of turbulence intensities in the first turbulence characteristic data are divided into a plurality of first turbulence data sets, and the wind speeds corresponding to the turbulence intensities in the same first turbulence data set belong to the same wind speed condition;

[0028] For each first turbulence data set, determining a first turbulence intensity characteristic value corresponding to the first turbulence data set according to the turbulence intensity in the first turbulence data set;

[0029] For each first turbulence data set, comparing a first turbulence intensity characteristic value corresponding to the first turbulence data set with a turbulence intensity threshold value of a wind speed condition corresponding to the first turbulence data set;

[0030] Determining a second number of target turbulence data sets among the plurality of first turbulence data sets, the target turbulence data set being a first turbulence data set having a first turbulence intensity characteristic value greater than a turbulence intensity threshold corresponding to a wind speed condition;

[0031] In response to the second number being greater than a second number threshold, determining that the first wind turbine generator system has abnormal turbulence intensity within the first time interval;

[0032] In response to the second number being less than or equal to the second number threshold, it is determined that no turbulence intensity abnormality exists in the first wind turbine group within the first time interval.

[0033] As a possible implementation, before obtaining the first operating data of the wind turbine generator set in the first time interval, the method further includes: obtaining sample data, the sample data including the second operating data of each second wind turbine generator set in the plurality of second wind turbine generator sets in the second time interval and the third operating data in the third time interval, the third time interval being earlier than the second time interval;

[0034] For each second wind turbine generator set, performing feature extraction processing on the second operation data and the third operation data of the second wind turbine generator set respectively to obtain the second power characteristic data and the second turbulence characteristic data, and the third power characteristic data and the third turbulence characteristic data of the second wind turbine generator set;

[0035] For each second wind turbine generator set, determining a plurality of power deviations of the second wind turbine generator set under a plurality of wind speed conditions according to the second power characteristic data and the third power characteristic data of the second wind turbine generator set;

[0036] For each wind speed condition, determining a power threshold corresponding to the wind speed condition according to a plurality of powers and a plurality of power deviations of a plurality of second wind turbine generator sets under the wind speed condition;

[0037] For each wind speed operating condition, a turbulence intensity threshold corresponding to the wind speed operating condition is determined according to the second turbulence characteristic data and the third turbulence characteristic data of the plurality of second wind turbine generator sets.

[0038] As a possible implementation manner, the second power characteristic data includes multiple powers and multiple wind speeds corresponding to multiple time periods within the second time interval, and the third power characteristic data includes multiple powers and multiple wind speeds corresponding to multiple time periods within the third time interval. For each second wind turbine generator set, according to the second power characteristic data and the third power characteristic data of the second wind turbine generator set, the power deviation of the second wind turbine generator set under multiple wind speed conditions is determined, including:

[0039] According to multiple wind speed operating conditions, multiple powers in the third power characteristic data of the second wind turbine generator set are divided into multiple third power data sets, and the wind speeds corresponding to the powers in the same third power data set belong to the same wind speed operating condition;

[0040] For each third power data set, determining, according to the power in the third power data set, a third power characteristic value of the second wind turbine generator set under the wind speed condition corresponding to the third power data set;

[0041] For each wind speed condition, determine that the wind speed corresponding to the second power characteristic data of the second wind turbine group belongs to the first power of the wind speed condition, and calculate the difference between the first power and the third power characteristic value of the second wind turbine group under the wind speed condition to obtain the power deviation of the second wind turbine group under the wind speed condition.

[0042] As a possible implementation manner, for each wind speed condition, determining a power threshold corresponding to the wind speed condition according to multiple powers and multiple power deviations of multiple second wind turbines under the wind speed condition includes:

[0043] Determining, from the second power characteristic data of the plurality of second wind turbine generator sets, a plurality of second powers corresponding to wind speeds belonging to the wind speed operating condition;

[0044] Calculating the average of multiple second powers to obtain a power average;

[0045] Processing multiple power deviations of multiple second wind turbines under the wind speed condition based on a quartile algorithm to obtain an intermediate power deviation;

[0046] Determine the variance of the intermediate power deviation and obtain the power deviation standard deviation;

[0047] The power value range is obtained by multiplying the standard deviation of the deviation by the set standard deviation multiple and then adding the result to the power mean value and the set first margin;

[0048] The lower limit of the power value range is used as the power threshold corresponding to the wind speed condition.

[0049] As a possible implementation manner, before determining whether the first wind turbine generator set has abnormal turbulence intensity within the first time interval based on the first turbulence characteristic data, the method further includes:

[0050] Extracting pitch characteristic data of the first wind turbine generator set from the first operating data;

[0051] Determining whether the first wind turbine generator set is in a power-limited state based on the pitch characteristic data;

[0052] Determining whether there is abnormal turbulence intensity at the position of the first wind turbine generator set within the first time interval based on the first turbulence characteristic data includes:

[0053] In response to the first wind turbine being in a capacity reduction state and a power limitation state within the first time interval, it is determined whether a turbulence intensity abnormality exists at the position of the first wind turbine within the first time interval based on the first turbulence characteristic data.

[0054] As a possible implementation manner, after determining that the first wind turbine generator set is in a turbulent capacity reduction state within the first time, the method further includes:

[0055] Generate early warning information related to turbulence degradation conditions;

[0056] Display warning information;

[0057] The warning information includes at least one of the following:

[0058] Warning text information and visual graphics;

[0059] The warning text information includes at least one of the following:

[0060] Warning problem, warning time, warning wind farm, warning unit, warning reason, warning description;

[0061] The visualization graph includes at least one of the following:

[0062] Graph showing the relationship between wind speed and power, and graph showing the relationship between wind speed and turbulence intensity.

[0063] In a second aspect, an embodiment of the present application provides a device for detecting turbulence capacity reduction state of a wind turbine generator set, comprising:

[0064] An acquisition module, used for acquiring first operating data of a first wind turbine generator set within a first time interval;

[0065] A data processing module, used for performing feature extraction processing on the first operation data to obtain first power feature data and first turbulence feature data of the first wind turbine generator set;

[0066] A capacity reduction feature identification module, used to determine whether the first wind turbine generator set is in a capacity reduction state within a first time interval based on the first power feature data;

[0067] A turbulence characteristic identification module, used to determine whether the first wind turbine generator set has abnormal turbulence intensity within a first time interval based on the first turbulence characteristic data;

[0068] A time overlap rate determination module, configured to determine a time overlap rate of the capacity reduction state and the turbulence intensity anomaly in response to the first wind turbine generator set being in a capacity reduction state and a turbulence intensity anomaly within a first time interval;

[0069] The turbulence reduction capacity identification module is used to determine that the first wind turbine generator set is in a turbulence reduction capacity state within a first time interval in response to the time overlap rate being greater than the overlap rate threshold.

[0070] In a third aspect, an embodiment of the present application provides an electronic device, the electronic device comprising: a processor and a memory storing computer program instructions;

[0071] When the processor executes the computer program instructions, the method for detecting the turbulence reduction state of the wind turbine generator set according to the first aspect is implemented.

[0072] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium having computer program instructions stored thereon. When the computer program instructions are executed by a processor, the method for detecting turbulent capacity reduction state of a wind turbine set according to the first aspect is implemented.

[0073] In a fifth aspect, an embodiment of the present application provides a computer program product. When instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the method for detecting turbulent capacity reduction state of a wind turbine set as in the first aspect.

[0074] The wind turbine turbulence reduction state detection method, device, equipment and medium of the embodiment of the present application obtains the first operating data of the first wind turbine in the first time interval, performs feature extraction on the first operating data, obtains the first power characteristic data and the first turbulence characteristic data of the first wind turbine, determines whether the first wind turbine is in a reduction state and has abnormal turbulence intensity based on the first power characteristic data and the first turbulence characteristic data, respectively, and further determines the time overlap rate of the reduction state and the turbulence intensity abnormality in response to the first wind turbine being in a reduction state and having abnormal turbulence intensity, and determines that the first wind turbine is in a turbulence reduction state when the time overlap rate is greater than the overlap rate threshold. According to this embodiment, by analyzing the operating data of the wind turbine, it is possible to accurately detect whether the wind turbine is in a turbulence reduction state. BRIEF DESCRIPTION OF THE DRAWINGS

[0075] In order to more clearly illustrate the technical solution of the embodiments of the present application, the following is a brief introduction to the drawings required for use in the embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0076] Figure 1 It is a schematic flow chart of a method for detecting turbulent capacity reduction state of a wind turbine set provided in an embodiment of the present application;

[0077] Figure 2 It is a schematic diagram of the operation data feature extraction process provided by an embodiment of the present application;

[0078] Figure 3 It is a schematic diagram of the reduced capacity state identification process provided by an embodiment of the present application;

[0079] Figure 4 is a schematic diagram of the turbulence intensity anomaly identification process provided in an embodiment of the present application;

[0080] Figure 5 It is a schematic diagram of the flow chart of the method for determining the power threshold and the turbulence intensity threshold provided in the embodiment of the present application;

[0081] Figure 6 is a power visualization schematic diagram of multiple second wind turbines provided in an embodiment of the present application;

[0082] Figure 7 is a schematic diagram of visualization of turbulence intensity characteristic values ​​of multiple second wind turbines provided in an embodiment of the present application;

[0083] Figure 8 It is a schematic flow chart of a method for detecting turbulent capacity reduction state of a wind turbine set provided in an embodiment of the present application;

[0084] Fig. 9 This is a warning information display effect diagram provided by an embodiment of the present application;

[0085] Fig.10 It is a structural schematic diagram of a device for detecting turbulence capacity reduction state of a wind turbine set provided in an embodiment of the present application;

[0086] Fig.11 It is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0087] The features and exemplary embodiments of various aspects of the present application will be described in detail below. In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the specific embodiments described herein are only intended to explain the present application, rather than to limit the present application. For those skilled in the art, the present application can be implemented without the need for some of these specific details. The following description of the embodiments is only to provide a better understanding of the present application by illustrating the examples of the present application.

[0088] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the statement "include..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0089] In order to solve the problems of the prior art, the embodiments of the present application provide a method, device, equipment and medium for detecting the turbulent capacity reduction state of a wind turbine. The following first introduces the method for detecting the turbulent capacity reduction state of a wind turbine provided by the embodiments of the present application.

[0090] See also Figure 1 , is a flow chart of a method for detecting turbulent capacity reduction state of a wind turbine set provided in an embodiment of the present application, such as Figure 1 As shown, the method may include the following steps: S11-S16.

[0091] S11. Obtain first operating data of a first wind turbine generator set within a first time interval.

[0092] The first wind turbine generator set is any wind turbine generator set that needs to be tested for turbulence reduction status.

[0093] The time length and start time of the first time interval can be set according to actual conditions.

[0094] In some embodiments of the present application, after the first time interval is determined, the operating data of the first wind turbine group in the first time interval can be obtained from a SCADA (Supervisory Control And Data Acquisition) system, and the obtained operating data can be used as the first operating data of the first wind turbine group.

[0095] In some embodiments of the present application, when performing turbulent derating state detection on a wind turbine, only the parameters affecting the turbulent derating state need to be analyzed, so the first operating data obtained only includes the target parameters, and does not need to include all the parameters during the operation of the wind turbine. Therefore, before obtaining the first operating data from the SCADA system, the target parameters required for turbulent derating state detection can be determined first, and then when obtaining the first operating data from the SCADA system, the ID of the first wind turbine and the start time of the first time interval are input to the SCADA system, and the target parameters are set. In this way, the operating data of the first wind turbine in the first time interval can be obtained from the SCADA system, and the obtained operating data only includes the target parameters, and the obtained operating data is used as the first operating data.

[0096] Among them, the target parameters are parameters related to the turbulence power reduction state of the wind turbine. The turbulence power reduction state refers to the power reduction state caused by abnormal turbulence intensity. The difference between the turbulence power reduction state and other operating states is mainly reflected in the two aspects of turbulence intensity and power. Based on this, the target parameters can be parameters related to the turbulence intensity and power of the wind turbine. Exemplarily, the target parameters can include converter active power, wind speed, pitch angle, etc.

[0097] S12. Perform feature extraction processing on the first operating data to obtain first power feature data and first turbulence feature data of the wind turbine generator set.

[0098] Here, the main thing is to extract the characteristic values ​​that are more sensitive to the turbulence reduction state, so as to determine whether the first wind turbine generator set is in the turbulence reduction state within the first time interval by analyzing the characteristic values.

[0099] The first power characteristic data includes the power characteristic value of the first wind turbine generator set in the first time interval extracted based on the first operation data. The first turbulence characteristic data includes the turbulence intensity characteristic value data of the first wind turbine generator set in the first time interval extracted based on the first operation data.

[0100] S13. Determine whether the first wind turbine generator set is in a reduced capacity state within the first time interval based on the first power characteristic data.

[0101] In some embodiments of the present application, the first power characteristic data can be compared with the power characteristic data of the wind turbine group that is not in the reduced capacity state to determine whether the first wind turbine group is in a reduced capacity state within the first time interval. If the difference between the first power characteristic data and the power characteristic data of the wind turbine group that is not in the reduced capacity state satisfies the first difference condition, it can be determined that the first wind turbine group is in a reduced capacity state within the first time interval; otherwise, it can be determined that the first wind turbine group is not in a reduced capacity state within the first time interval. The first difference condition can be set according to actual conditions.

[0102] In some embodiments of the present application, if it is determined that the first wind turbine generator set is in a reduced capacity state within the first time interval, S14 may be executed again. If it is determined that the first wind turbine generator set is not in a reduced capacity state within the first time interval, S14 and subsequent steps may not be executed again, because if the first wind turbine generator set is in a turbulent reduced capacity state, then the first wind turbine generator set must be in a reduced capacity state. If the first wind turbine generator set is not in a reduced capacity state within the first time interval, it can be directly determined that the first wind turbine generator set is not in a turbulent reduced capacity state within the first time interval, so there is no need to execute S14 and subsequent steps. In this way, unnecessary calculations can be reduced.

[0103] S14. Determine whether the first wind turbine generator set has abnormal turbulence intensity within the first time interval based on the first turbulence characteristic data.

[0104] Determining whether the first wind turbine has abnormal turbulence intensity refers to determining whether the first wind turbine has abnormal turbulence intensity at the installation location of the first wind turbine. Turbulence intensity describes the degree of wind speed variation over time and space, reflects the relative intensity of pulsating wind speed, and is an important characteristic quantity that describes the characteristics of atmospheric turbulence motion.

[0105] In some embodiments of the present application, it is possible to determine whether the first wind turbine has turbulence intensity anomaly in the first time interval by comparing the first turbulence characteristic data with the turbulence characteristic data of the wind turbine without turbulence intensity anomaly. If the difference between the first turbulence characteristic data and the turbulence characteristic data of the wind turbine without turbulence intensity anomaly satisfies the second difference condition, it can be determined that the first wind turbine has turbulence intensity anomaly in the first time interval, otherwise, it can be determined that the first wind turbine does not have turbulence intensity anomaly in the first time interval. The second difference condition can be set according to actual conditions.

[0106] S15. In response to the first wind turbine generator set being in a derated state and having abnormal turbulence intensity, determining a temporal overlap ratio of the derated state and the abnormal turbulence intensity.

[0107] If the first wind turbine generator set is in both a derated state and an abnormal turbulence intensity within the first time interval, the derated state of the first wind turbine generator set may be caused by the abnormal turbulence intensity. At this time, in order to further determine whether the derated state is caused by the abnormal turbulence intensity, the time overlap rate of the derated state and the abnormal turbulence intensity is calculated.

[0108] In some embodiments of the present application, when determining the time overlap rate of the degraded state and the turbulence intensity anomaly, considering that the time when the degraded state and the turbulence intensity anomaly occur may not be continuous, the first time period set corresponding to the degraded state and the second time period set corresponding to the turbulence intensity anomaly can be determined respectively; the overlap time of the first time period set and the second time period set can be determined respectively; the first ratio of the overlap time to the first time period set and the second ratio of the overlap time to the second time period set can be determined respectively; the maximum value of the first ratio and the second ratio can be determined as the time overlap rate of the degraded state and the turbulence intensity anomaly. Among them, the overlap time is the time when the degraded state and the turbulence intensity anomaly coexist.

[0109] Because the total time length of the first time period set may be inconsistent with the total time length of the second time period set, the first ratio is usually different from the second ratio. By determining the maximum value of the first ratio and the second ratio as the time overlap rate, the overlap of the reduced capacity state and the abnormal turbulence intensity can be more accurately reflected.

[0110] S16. In response to the time overlap rate being greater than the overlap rate threshold, determine that the wind turbine generator is in a turbulent capacity reduction state.

[0111] The overlap rate threshold can be set according to actual conditions, and the value range of the overlap rate threshold is 0-1.

[0112] In some embodiments of the present application, after obtaining the time overlap rate of the reduced capacity state and the abnormal turbulence intensity, the time overlap rate is compared with the overlap rate threshold, and if the time overlap rate is greater than the overlap rate threshold, it can be determined that the reduced capacity state is caused by the abnormal turbulence intensity, thereby determining that the first wind turbine is in a turbulent reduced capacity state. In addition, if the time overlap rate is not greater than the overlap rate threshold, it can be directly determined that the reduced capacity state is not caused by the abnormal turbulence intensity, or other methods can be used to further determine whether the reduced capacity state is caused by the abnormal turbulence intensity, which is not specifically limited in this embodiment.

[0113] The method for detecting the turbulent capacity reduction state of a wind turbine provided in the present embodiment obtains the first operating data of the first wind turbine in the first time interval, performs feature extraction on the first operating data, obtains the first power characteristic data and the first turbulence characteristic data of the first wind turbine, determines whether the first wind turbine is in a capacity reduction state and has abnormal turbulence intensity based on the first power characteristic data and the first turbulence characteristic data, respectively, and further determines the time overlap rate of the capacity reduction state and the turbulence intensity abnormality in response to the first wind turbine being in a capacity reduction state and having abnormal turbulence intensity, and determines that the first wind turbine is in a turbulent capacity reduction state when the time overlap rate is greater than the overlap rate threshold. According to the present embodiment, by analyzing the operating data of the wind turbine, it is possible to accurately detect whether the wind turbine is in a turbulent capacity reduction state.

[0114] The wind turbine turbulence reduction state detection method provided in the embodiment of the present application does not require additional sensors, and can achieve early warning of the turbulence reduction state of the wind turbine only through SCADA data, thereby reducing monitoring complexity and monitoring costs. Moreover, it can be applied to wind turbines of different manufacturers and models, and only wind turbines that can obtain time, converter active power, wind speed and pitch angle can be compatible.

[0115] In some embodiments of the present application, the operating data of the first wind turbine generator set may include wind speed and converter active power. Figure 2 , performing feature extraction processing on the first operating data to obtain first power feature data and first turbulence feature data of the first wind turbine generator set may include the following steps: S121-S125.

[0116] S121. Divide the first time interval corresponding to the first operating data into multiple time periods.

[0117] In some embodiments of the present application, a sliding window algorithm may be used to divide the first time interval into multiple time periods. When dividing, the window size may be set to W, the moving step size may be set to S, and the first time interval may be divided into multiple time periods by sliding the window. The values ​​of W and S may be set according to actual conditions, wherein the value of W is less than the total length of the first time interval, and the value of S is less than W.

[0118] S122. For each time period, the operating data in the time period is calculated to obtain the power mean, wind speed mean and wind speed standard deviation in the time period.

[0119] In some embodiments of the present application, the following steps are performed for each divided time period:

[0120] Calculate the average value of active powers of all converters whose corresponding time in the first operation data is within the time period, and use the average value as the power mean value;

[0121] Calculate the average value of all wind speeds corresponding to the time in the first operation data within the time period to obtain the mean wind speed within the time period;

[0122] The standard deviation of all wind speeds whose corresponding time in the first operating data is within the time period is calculated to obtain the standard deviation of the wind speed within the time period.

[0123] S123. For each time period, the mean wind speed in the time period is taken as the wind speed corresponding to the time period, the mean power in the time period is taken as the power corresponding to the time period, and the quotient of the wind speed standard deviation and the wind speed mean in the time period is taken as the turbulence intensity corresponding to the time period.

[0124] In some embodiments of the present application, for each time period, the turbulence intensity corresponding to the time period may be calculated according to the following formula:

[0125] Turbulence intensity = wind speed standard deviation / wind speed

[0126] S124. Use multiple wind speeds and multiple powers corresponding to multiple time periods as first power characteristic data.

[0127] Here, the first power characteristic data obtained includes wind speed and power corresponding to each of the multiple time periods. Among them, the wind speed and power correspond one to one, that is, one power corresponds to one wind speed. In this way, the first power characteristic data can reflect the corresponding relationship between wind speed and power.

[0128] Compared with directly using the wind speed and converter active power in the first operating data as the first power characteristic data, the above method, on the one hand, reduces the data volume of the first power characteristic data, and on the other hand, by performing a sliding window averaging on the first operating data over time, it is possible to filter out abnormal values ​​in the first operating data and improve data quality.

[0129] S125. Use multiple wind speeds and multiple turbulence intensities corresponding to multiple time periods as turbulence characteristic data of the first operating data.

[0130] Here, the first turbulence characteristic data obtained includes wind speed and turbulence intensity corresponding to each of the multiple time ends. Among them, the wind speed and turbulence intensity correspond one to one, that is, one turbulence intensity corresponds to one wind speed. In this way, the first turbulence characteristic data can reflect the corresponding relationship between turbulence intensity and wind speed.

[0131] In some embodiments of the present application, see Figure 3 , determining whether the first wind turbine generator set is in a reduced capacity state within a first time based on the first power characteristic data may include the following steps:

[0132] S131. Divide the multiple powers in the first power characteristic data into multiple first power data sets according to multiple wind speed conditions, and the wind speeds corresponding to the powers in the same first power data set belong to the same wind speed condition.

[0133] Here, the multiple wind speed conditions are set according to the actual situation in advance, wherein different wind speed conditions correspond to different wind speed intervals. For example, the multiple wind speed conditions can be determined according to the operation data of the wind turbine.

[0134] In some embodiments of the present application, multiple powers in the first power characteristic data are divided according to multiple preset wind speed conditions, and the powers corresponding to the wind speeds belonging to the same wind speed condition are divided into the same first power data set. In this way, multiple first power data sets corresponding to multiple wind speed conditions can be obtained, and the wind speeds corresponding to the powers in the same first power data set belong to the same wind speed condition.

[0135] S132. For each first power data set, determine a first power characteristic value corresponding to the first power data set according to the power in the first power data set.

[0136] In some embodiments of the present application, for each first power data set, a statistical calculation can be performed on the power in the first power data set based on a preset statistical algorithm to obtain a first power characteristic value corresponding to the first power data set. Exemplarily, the statistical algorithm includes but is not limited to median calculation, etc.

[0137] S133. For each first power data set, compare the first power characteristic value of the first power data set with the power threshold of the wind speed condition corresponding to the first power data set.

[0138] In some embodiments of the present application, before the turbulence derating state is detected for the first wind turbine generator set, a power threshold corresponding to each wind speed condition in a plurality of wind speed conditions is predetermined. For each wind speed condition, the power threshold corresponding to the wind speed condition can be considered as the power value of the first wind turbine generator set under the wind speed condition when there is no derating state. Based on this, for each first power data set, after obtaining the first power characteristic value corresponding to the first power data set, by comparing the first power characteristic value with the power threshold corresponding to the wind speed condition corresponding to the first power data set, it can be determined whether the first wind turbine generator set has derating under the wind speed condition corresponding to the first power data set.

[0139] S134. Determine a first number of target power data sets among the plurality of first power data sets, the target power data set being a first power data set whose first power characteristic value is less than a power threshold corresponding to a wind speed condition.

[0140] In some embodiments of the present application, for each first power data set, a first power characteristic value corresponding to the first power data set is compared with a power threshold corresponding to the wind speed condition corresponding to the first power data set; if the first power characteristic value is less than the power threshold, it can be considered that the first wind turbine has undergone a capacity reduction under the wind speed condition.

[0141] Taking into account that the first wind turbine may also have a first power characteristic value lower than the power threshold due to power fluctuations during operation, and this is not caused by derating, in order to improve the accuracy of derating state detection, the number of target power data sets whose corresponding first power characteristic values ​​are lower than the corresponding power threshold in multiple first power data sets, that is, the first number, is counted, and it is finally determined whether a derating state exists based on the first number.

[0142] S135. In response to the first number being greater than a first number threshold, determine that the first wind turbine generator system is in a reduced capacity state within a first time interval.

[0143] The first quantity threshold may be set according to actual conditions. For example, the first quantity threshold may be a value greater than or equal to 1.

[0144] After obtaining the first number, the first number is compared with a first number threshold, and when it is determined that the first number is greater than the first number threshold, it is determined that the first wind turbine generator set is in a reduced capacity state within the first time interval.

[0145] S136. In response to the first number being less than or equal to a first number threshold, determine that the first wind turbine generator system is not in a reduced capacity state within the first time interval.

[0146] When the first number is not greater than the first number threshold, that is, the first number is less than or equal to the first number threshold, it is determined that the first wind turbine generator system is in a reduced capacity state within the first time interval.

[0147] By using the above method, the first power characteristic values ​​of the first wind turbine generator set under multiple wind speed conditions are judged respectively, so that it can be accurately identified whether the first wind turbine generator set is in a reduced capacity state within the first time interval.

[0148] In some embodiments of the present application, see Figure 4 , determining whether there is abnormal turbulence intensity at the position of the first wind turbine generator set within the first time interval based on the first turbulence characteristic data may include the following steps: S141-S147.

[0149] S141. According to multiple wind speed conditions, multiple turbulence intensities in the first turbulence characteristic data are divided into multiple first turbulence data sets, and the wind speeds corresponding to the turbulence intensities in the same first turbulence data set belong to the same wind speed condition.

[0150] Among them, the multiple wind speed conditions are consistent with the multiple wind speed conditions in S131.

[0151] In some embodiments of the present application, multiple turbulence intensities in the first turbulence characteristic data are divided according to multiple preset wind speed conditions, and the turbulence intensities corresponding to the wind speeds belonging to the same wind speed condition are divided into the same first turbulence data set. In this way, multiple first turbulence data sets corresponding to multiple wind speed conditions can be obtained, and the wind speeds corresponding to the turbulence intensities in the same first turbulence data set belong to the same wind speed condition.

[0152] S142. For each first turbulence data set, determine a first turbulence intensity characteristic value corresponding to the first turbulence data set according to the turbulence intensity in the first turbulence data set.

[0153] In some embodiments of the present application, for each first turbulence data set, the turbulence intensity in the first turbulence data set can be calculated based on a preset statistical algorithm to obtain a first turbulence intensity characteristic value corresponding to the first turbulence data set. Exemplarily, the statistical algorithm includes but is not limited to: median calculation, etc.

[0154] S143. For each first turbulence data set, compare the turbulence intensity characteristic value corresponding to the first turbulence data set with the first turbulence intensity threshold of the wind speed condition corresponding to the first turbulence data set.

[0155] In some embodiments of the present application, before the turbulence reduction state detection is performed on the first wind turbine generator set, the turbulence intensity threshold corresponding to each wind speed condition in a plurality of wind speed conditions is predetermined. For each wind speed condition, the turbulence intensity threshold corresponding to the wind speed condition can be considered as the turbulence intensity value of the first wind turbine generator set under the wind speed condition when there is no turbulence intensity anomaly. Based on this, for each first turbulence data set, after obtaining the first turbulence intensity characteristic value corresponding to the first turbulence data set, by comparing the first turbulence intensity characteristic value with the turbulence intensity threshold corresponding to the wind speed condition corresponding to the first turbulence data set, it can be determined whether the first wind turbine generator set has a turbulence intensity anomaly under the wind speed condition corresponding to the first turbulence data set.

[0156] S144. Determine a second number of target turbulence data sets among the plurality of first turbulence data sets, the target turbulence data set being a first turbulence data set having a first turbulence intensity characteristic value greater than a turbulence intensity threshold corresponding to a wind speed condition.

[0157] In some embodiments of the present application, for each first turbulence data set, a first turbulence intensity characteristic value corresponding to the first turbulence data set is compared with a turbulence intensity threshold corresponding to the wind speed condition corresponding to the first turbulence data set; if the first turbulence intensity characteristic value is less than the turbulence intensity threshold, it can be considered that the first wind turbine has turbulence intensity anomaly under the wind speed condition.

[0158] Taking into account that during the operation of the first wind turbine set, the first turbulence intensity characteristic value may be greater than the turbulence intensity threshold due to wind speed fluctuations and other reasons, and this is not caused by turbulence intensity anomaly, in order to improve the accuracy of turbulence intensity anomaly detection, the number of target turbulence data sets whose corresponding first turbulence intensity characteristic values ​​are less than the corresponding turbulence intensity threshold in multiple first turbulence data sets, that is, the second number, is counted, and it is finally determined whether there is a turbulence intensity anomaly based on the second number.

[0159] S145. In response to the second number being greater than a second number threshold, determining that the first wind turbine generator system has abnormal turbulence intensity within the first time interval.

[0160] The second quantity threshold may be set according to actual conditions. For example, the second quantity threshold is a value greater than or equal to 1.

[0161] In some embodiments of the present application, after obtaining the second number, the second number is compared with a second number threshold, and when it is determined that the second number is greater than the second number threshold, it is determined that the first wind turbine has abnormal turbulence intensity within the first time interval.

[0162] S146. In response to the second number being less than or equal to the second number threshold, determine that there is no turbulence intensity abnormality for the first wind turbine generator system within the first time interval.

[0163] In some embodiments of the present application, when the second number is not greater than the second number threshold, that is, the second number is less than or equal to the second number threshold, it is determined that there is no turbulence intensity abnormality in the first wind turbine generator set within the first time interval.

[0164] By using the above method, the first turbulence intensity characteristic values ​​of the first wind turbine generator set under multiple wind speed conditions are judged respectively, so that it can be accurately identified whether the first wind turbine generator set has turbulence intensity abnormality within the first time interval.

[0165] In some embodiments of the present application, see Figure 5 Before obtaining the first operating data of the wind turbine generator set in the first time interval, the following steps S51-S55 may be used to determine the power threshold and turbulence intensity threshold corresponding to each wind speed condition in a plurality of preset wind speed conditions.

[0166] S51. Obtain sample data, the sample data including second operating data of each second wind turbine set in the plurality of second wind turbine sets in a second time interval and third operating data in a third time interval, the third time interval being earlier than the second time interval.

[0167] Here, the second wind turbine group can be a wind turbine group in any wind farm that is in normal working state within the second time interval and the third time interval. The time length and start time of the second time interval and the third time interval can be set according to actual conditions, but it is necessary to ensure that the second time interval and the third time interval do not overlap, and the third time interval is earlier than the second time interval. For example, the second time interval can be a certain day, and the third time interval can be the ten days before the certain day.

[0168] In some embodiments of the present application, in order to improve the universality of the power threshold and the turbulence intensity threshold finally calculated, the plurality of second wind turbines may include wind turbines in a plurality of wind farms.

[0169] In some embodiments of the present application, for each second wind turbine set, the second operating data of the second wind turbine set in the second time interval and the third operating data of the second wind turbine set in the third time interval can be respectively obtained from the SCADA system. The specific acquisition method is similar to the method of obtaining the first operating data. To avoid repetition, it will not be repeated here.

[0170] S52. For each second wind turbine set, perform feature extraction processing on the second operation data and the third operation data of the second wind turbine set to obtain the second power characteristic data and the second turbulence characteristic data, and the third power characteristic data and the third turbulence characteristic data of the second wind turbine set.

[0171] In some embodiments of the present application, for each second wind turbine group, after acquiring the second operating data and the third operating data of the second wind turbine group, feature extraction can be performed on the second operating data and the third operating data, respectively, so as to obtain second power characteristic data and second turbulence characteristic data extracted based on the second operating data, and third power characteristic data and third turbulence characteristic data extracted based on the third operating data.

[0172] When performing feature extraction processing on the second operating data and the third operating data, the feature extraction processing method adopted is the same as the feature extraction processing method for the first operating data of the first wind turbine generator set, and will not be described again here to avoid repetition.

[0173] S53. For each second wind turbine generator set, determine multiple power deviations of the second wind turbine generator set under multiple wind speed conditions according to the second power characteristic data and the third power characteristic data of the second wind turbine generator set.

[0174] Here, the main purpose is to calculate the deviation range of the wind speed-power curve based on the statistical values ​​of the operation data of a large number of second wind turbines.

[0175] In some embodiments of the present application, the second power characteristic data includes multiple powers and multiple wind speeds corresponding to multiple time periods within the second time interval, and the third power characteristic data includes multiple powers and multiple wind speeds corresponding to multiple time periods within the third time interval. For each second wind turbine generator set, determining the power deviation of the second wind turbine generator set under multiple wind speed conditions according to the second power characteristic data and the third power characteristic data of the second wind turbine generator set may include the following steps:

[0176] According to multiple wind speed operating conditions, multiple powers in the third power characteristic data of the second wind turbine generator set are divided into multiple third power data sets, and the wind speeds corresponding to the powers in the same third power data set belong to the same wind speed operating condition;

[0177] For each third power data set, determining, according to the power in the third power data set, a third power characteristic value of the second wind turbine generator set under the wind speed condition corresponding to the third power data set;

[0178] For each wind speed condition, determine that the wind speed corresponding to the second power characteristic data of the second wind turbine group belongs to the target power of the wind speed condition, and calculate the difference between the target power and the third power characteristic value of the second wind turbine group under the wind speed condition to obtain the power deviation of the second wind turbine group under the wind speed condition.

[0179] That is, for each wind speed condition, first, based on the power of the second wind turbine group under the wind speed condition in the third characteristic data, the power characteristic value of the second wind turbine group under the wind speed condition is calculated, and then, for each first power under the wind speed condition in the second characteristic data of the second wind turbine group, the difference between the first power and the power characteristic value is calculated respectively, so as to obtain the power deviation value of the second wind turbine group under the wind speed condition.

[0180] The method of calculating the third power characteristic value corresponding to the third power data set is the same as the method of calculating the first power characteristic value corresponding to the first power data set.

[0181] S54. For each wind speed condition, determine a power threshold corresponding to the wind speed condition according to a plurality of powers and a plurality of power deviations of a plurality of second wind turbine generator sets under the wind speed condition.

[0182] Here, the boundary value of the wind speed-power curve, that is, the power threshold corresponding to each wind speed condition, is calculated mainly by setting parameters based on business experience.

[0183] In some embodiments of the present application, for each wind speed condition, determining the power threshold corresponding to the wind speed condition according to multiple powers and multiple power deviations of multiple second wind turbines under the wind speed condition may include:

[0184] Determining, from the second power characteristic data of the plurality of second wind turbine generator sets, a plurality of second powers corresponding to wind speeds belonging to the wind speed operating condition;

[0185] Calculating the average of multiple second powers to obtain a power average;

[0186] Processing multiple power deviations of multiple second wind turbines under the wind speed condition based on a quartile algorithm to obtain an intermediate power deviation;

[0187] Determine the variance of the intermediate power deviation and obtain the power deviation standard deviation;

[0188] The power value range is obtained by multiplying the power deviation standard deviation by the set standard deviation multiple and adding the power mean value and the set first margin;

[0189] The lower limit of the power value range is used as the power threshold corresponding to the wind speed condition.

[0190] The process of processing a plurality of power deviations of a plurality of second wind turbine generator sets under the wind speed condition based on a quartile algorithm to obtain an intermediate power deviation may include:

[0191] Arrange the multiple power deviations of the multiple second wind turbines under the wind speed condition from small to large, find the median of the multiple power deviations after sorting, that is, the second quartile Q2, find the median of the power deviations on the left side of Q2, that is, the first quartile Q1, and find the median of the power deviations on the right side of Q2, that is, the third quartile Q3. Simply put, the quartile is to divide a set of data into four parts, where the minimum data value -Q1 represents the smallest 25% of the data, Q1-Q2 represents the 25% of the data to the left of the middle, Q2-Q3 represents the 25% of the data that is larger in the middle, and Q3-the maximum data value represents the largest 25% of the data. In some embodiments of the present application, the power deviation between Q2-Q3 can be used as the intermediate power deviation. In this way, outliers in multiple power deviations can be removed.

[0192] After obtaining the intermediate power deviation corresponding to the wind speed condition, the variance of the intermediate power deviation is calculated to obtain the power deviation standard deviation corresponding to the wind speed condition. After obtaining the power deviation standard deviation corresponding to the wind speed condition, the power threshold corresponding to the wind speed condition can be calculated according to the following calculation formula:

[0193] Power threshold = min (power mean + standard deviation multiple * power deviation standard deviation + first margin)

[0194] The standard deviation multiple and the first margin can be set according to actual conditions.

[0195] For example, taking the standard deviation multiple as 3 times as an example, see Figure 6 , is a schematic diagram of power visualization of multiple second wind turbines, where the scattered points are multiple power values ​​corresponding to the multiple second wind turbines under multiple wind speed conditions, the dotted lines represent the upper and lower boundaries of the power mean and three times the standard deviation of the power deviation under each wind speed condition, the solid line is the lower boundary obtained by adding the first margin, and for each wind speed condition, the power value corresponding to the wind speed condition in the solid line is used as the power threshold corresponding to the wind speed condition.

[0196] Through the above method, the accurate power threshold corresponding to each wind speed condition can be obtained.

[0197] S55. For each wind speed condition, determine a turbulence intensity threshold corresponding to the wind speed condition according to the second turbulence characteristic data and the third turbulence characteristic data of the plurality of second wind turbine generator sets.

[0198] In some embodiments of the present application, the second turbulence characteristic data includes multiple wind speeds and multiple turbulence intensities corresponding to multiple time periods in the second time interval, and the third turbulence characteristic data includes multiple wind speeds and multiple turbulence intensities corresponding to multiple time periods in the third time interval. Based on this, for each wind speed condition, according to the second turbulence characteristic data and the third turbulence characteristic data of the multiple second wind turbines, determining the turbulence intensity threshold corresponding to the wind speed condition may include the following steps:

[0199] Determining, from the second turbulence characteristic data and the third turbulence characteristic data of the plurality of second wind turbine generator sets, a target turbulence intensity for the corresponding wind speed belonging to the wind speed operating condition;

[0200] The target turbulence intensity is processed based on the quartile algorithm to obtain the intermediate turbulence intensity;

[0201] Determine the variance and mean of the intermediate turbulence intensity to obtain the turbulence intensity variance and the turbulence intensity mean;

[0202] The turbulence intensity variance is multiplied by the set variance multiple and then added to the turbulence intensity mean and the set second margin to obtain the turbulence intensity value range;

[0203] The upper limit of the turbulence intensity range is taken as the turbulence intensity threshold corresponding to the wind speed condition.

[0204] Among them, the method of processing the target turbulence intensity based on the quartile algorithm to obtain the intermediate turbulence intensity is the same as the method of processing multiple power deviations of multiple second wind turbines under wind speed conditions based on the quartile algorithm to obtain the intermediate power deviation, which will not be repeated here.

[0205] After obtaining the intermediate turbulence intensity corresponding to the wind speed condition, the variance and mean of the intermediate turbulence intensity are calculated to obtain the turbulence intensity variance and turbulence intensity mean corresponding to the wind speed condition. Then, the turbulence intensity threshold corresponding to the wind speed condition can be calculated according to the following formula:

[0206] Turbulence intensity threshold = max (variance multiple * turbulence intensity variance + turbulence intensity mean + second margin)

[0207] The variance multiple and the second margin can be set according to actual conditions.

[0208] For example, taking the variance multiple as 3 times, see Figure 7, is a schematic diagram for visualizing the turbulence intensity characteristic values ​​of multiple second wind turbines, where the scattered points are the turbulence intensities corresponding to the multiple second wind turbines under multiple wind speed conditions, the dotted lines represent the upper and lower boundaries of the three times variance of the intermediate turbulence intensity under each wind speed condition, the solid line is the upper boundary after adding the second margin, and for each wind speed condition, the turbulence intensity value corresponding to the wind speed condition in the solid line is used as the turbulence intensity threshold corresponding to the wind speed condition.

[0209] In some embodiments of the present application, the first operating data may further include a pitch angle. Based on this, in response to the first wind turbine generator being in a derated state and having an abnormal turbulence intensity within the first time interval, before determining the time overlap rate of the derated state and the abnormal turbulence intensity, the following steps may be performed:

[0210] Extracting pitch characteristic data of the first wind turbine generator set from the first operating data;

[0211] It is determined whether the first wind turbine generator set is in a power-limited state based on the pitch characteristic data.

[0212] Accordingly, in response to the first wind turbine generator set being in a derated state and having abnormal turbulence intensity within the first time interval, determining the time coincidence rate of the derated state and the abnormal turbulence intensity may include:

[0213] In response to the first wind turbine generator set being in a capacity reduction state, abnormal turbulence intensity, and a power limitation state within a first time interval, a time overlap rate of the capacity reduction state and the abnormal turbulence intensity is determined.

[0214] In some embodiments of the present application, extracting the pitch characteristic data of the first wind turbine generator set from the first operating data may include the following steps:

[0215] For each time period divided from the first time interval, the difference between the maximum value of the pitch angle and the minimum value of the pitch angle in the time period is calculated to obtain the pitch angle change amount corresponding to the time period;

[0216] The multiple pitch angle changes corresponding to the multiple time periods divided into the first time interval are used as pitch angle characteristic data.

[0217] In some embodiments of the present application, determining whether the first wind turbine generator set is in a power-limited state based on the pitch characteristic data may include the following steps:

[0218] For each pitch angle variation in the pitch characteristic data, comparing the pitch angle variation with a variation threshold;

[0219] Determine a third amount of target pitch angle changes among the multiple pitch angle changes, the target pitch angle change being a pitch angle change greater than a change threshold;

[0220] In response to the third number being greater than a third number threshold, determining that the first wind turbine generator set is in a power-limited state;

[0221] In response to the third number being less than or equal to a third number threshold, it is determined that the first wind turbine generator set is not in a power limiting state.

[0222] Here, the change threshold can be set according to actual conditions, for example, the change threshold can be 1 degree.

[0223] The third number may also be set according to actual conditions. For example, the third number may be a value greater than or equal to 1.

[0224] Since the pitch angle of the wind turbine is constantly changing during the power limiting period, the embodiment of the present application calculates the pitch angle variation of the first wind turbine in multiple time periods within the first time interval based on the first operating data, and detects whether the first wind turbine is in a power limiting state based on the pitch angle variation. For each time period, if the pitch angle variation in the time period is greater than the pitch angle variation threshold, it is considered that the first wind turbine is in a power limiting state in the time period. The number of time periods in which the pitch angle variation is greater than the pitch angle variation threshold within the first time interval is counted, that is, the third number of the target pitch angle variation. If the third number is greater than the set third number threshold, it is determined that the first wind turbine is in a power limiting state within the first time interval.

[0225] Usually, a wind turbine will also be in a power-limited state when turbulence derating occurs. Therefore, if a wind turbine is in a power-limited state, the wind turbine may be in a turbulence derating. However, if the wind turbine is not in a power-limited state, it can be basically ruled out that the wind turbine has turbulence derating. Based on this, before determining whether the position of the first wind turbine has an abnormal turbulence intensity within the first time interval based on the first turbulence characteristic data, a power-limited state detection is first performed. When it is determined that a power-limited state exists, a turbulence intensity abnormality detection is performed. When it is determined that there is no power-limited state, turbulence derating can be ruled out, and there is no need to perform a turbulence intensity abnormality detection.

[0226] Because the amount of calculation for power limit state detection is smaller than that for turbulence intensity anomaly detection, the above method can reduce the amount of calculation for the turbulence-free capacity reduction state. In addition, by adding power limit state detection, the accuracy of the turbulence capacity reduction state detection result can be further improved.

[0227] In some embodiments of the present application, see Figure 8 When performing turbulence reduction state detection on the first wind turbine generator set, the following steps may be performed in sequence:

[0228] S81. Obtaining first operating data of a first wind turbine generator set in a first time interval;

[0229] S82. Extracting features from the first operating data to obtain first power feature data, first turbulence feature data, and pitch feature data of the first wind turbine generator set;

[0230] S83. Determine whether the first wind turbine generator set is in a reduced capacity state within the first time interval based on the first power characteristic data, if so, execute S84, if not, execute S89;

[0231] S84. Determine whether the first wind turbine generator set is in a power-limited state within the first time interval based on the power conversion characteristic data. If so, execute S85; otherwise, execute S89;

[0232] S85. Determine whether the first wind turbine generator set has abnormal turbulence intensity in the first time interval based on the first turbulence characteristic data, if so, execute S86, if not, execute S89;

[0233] S86. Determine the temporal coincidence rate of the reduced capacity state and the abnormal turbulence intensity;

[0234] S87. Determine whether the time overlap rate is greater than the overlap rate threshold, if so, execute S88, if not, execute S89;

[0235] S88. Determine that the first wind turbine generator set is in a turbulent capacity reduction state within the first time interval;

[0236] S89. Determine that the first wind turbine generator set does not have a turbulent capacity reduction state within the first time interval.

[0237] In some embodiments of the present application, after determining that the first wind turbine generator set is in a turbulent capacity reduction state within the first time interval, the following steps may also be performed:

[0238] Generate early warning information related to turbulence degradation conditions;

[0239] Display warning information.

[0240] The warning information may include at least one of the following:

[0241] Warning text information and visual graphics.

[0242] The warning text message may include at least one of the following:

[0243] Warning problem, warning time, warning wind farm, warning unit, warning reason, warning description;

[0244] The visualization graph includes at least one of the following:

[0245] Graph showing the relationship between wind speed and power, and graph showing the relationship between wind speed and turbulence intensity.

[0246] In some embodiments of the present application, when it is determined that the first wind turbine is in a turbulent capacity reduction state within the first time interval, the first wind turbine can be used as an early warning unit to generate early warning information, draw visual graphics, and push them to the front-end display screen for display, so as to facilitate on-site personnel to track and maintain.

[0247] For example, see Fig. 9 The warning information can include the basic information of the warning unit, the warning reason and warning description information, and the visualization of the warning unit data. Fig. 9 As shown in the figure, the left side shows the basic information of the early warning unit and the alarm description information. In the visualization graph on the right, the scattered points marked with "." represent normal data points, and the scattered points marked with "*" represent abnormal data points. The image at the top shows the wind speed power graph, and the image at the bottom shows the wind speed turbulence graph.

[0248] Through early warning, it is convenient to arrange inspections by operation and maintenance personnel, thereby avoiding damage to the unit blades and tower due to long-term overload operation in turbulent wind conditions caused by turbulence.

[0249] Based on the wind turbine turbulence reduction state detection method provided in the above embodiment, the present application also provides a specific implementation of the wind turbine turbulence reduction state detection device. Please refer to the following embodiment.

[0250] See also Fig.10 The wind turbine turbulence reduction state detection device provided in the embodiment of the present application includes the following modules:

[0251] An acquisition module 101 is used to acquire first operating data of a first wind turbine generator set in a first time interval;

[0252] The data processing module 102 is used to perform feature extraction processing on the first operation data to obtain first power feature data and first turbulence feature data of the first wind turbine generator set;

[0253] A capacity reduction feature identification module 103 is used to determine whether the first wind turbine generator set is in a capacity reduction state within a first time interval based on the first power feature data;

[0254] A turbulence feature identification module 104, configured to determine whether the first wind turbine generator set has abnormal turbulence intensity within a first time interval based on the first turbulence feature data;

[0255] A time overlap rate determination module 105 is used to determine a time overlap rate of the capacity reduction state and the turbulence intensity abnormality in response to the first wind turbine generator set being in a capacity reduction state and a turbulence intensity abnormality within a first time interval;

[0256] The turbulence reduction capacity identification module 106 is configured to determine that the first wind turbine generator set is in a turbulence reduction capacity state within a first time interval in response to the time overlap rate being greater than the overlap rate threshold.

[0257] The wind turbine turbulence reduction state detection device provided in the present embodiment obtains the first operating data of the first wind turbine in the first time interval, performs feature extraction on the first operating data, obtains the first power characteristic data and the first turbulence characteristic data of the first wind turbine, determines whether the first wind turbine is in a reduction state and has abnormal turbulence intensity based on the first power characteristic data and the first turbulence characteristic data, respectively, and further determines the time overlap rate of the reduction state and the turbulence intensity abnormality in response to the first wind turbine being in a reduction state and having abnormal turbulence intensity, and determines that the first wind turbine is in a turbulence reduction state when the time overlap rate is greater than the overlap rate threshold. According to the present embodiment, by analyzing the operating data of the wind turbine, it is possible to accurately detect whether the wind turbine is in a turbulence reduction state.

[0258] In some embodiments of the present application, the operation data of the first wind turbine generator set includes wind speed and converter active power, and the data processing module 102 is specifically used to:

[0259] Dividing a first time interval corresponding to the first operation data into a plurality of time periods;

[0260] For each time period, the operating data in the time period is calculated to obtain the power mean, wind speed mean and wind speed standard deviation in the time period;

[0261] For each time period, the mean wind speed in the time period is taken as the wind speed corresponding to the time period, the mean power in the time period is taken as the power corresponding to the time period, and the quotient of the wind speed standard deviation and the wind speed mean in the time period is taken as the turbulence intensity corresponding to the time period;

[0262] taking a plurality of wind speeds and a plurality of powers corresponding to a plurality of time periods as first power characteristic data;

[0263] A plurality of wind speeds and a plurality of turbulence intensities corresponding to a plurality of time periods are used as first turbulence characteristic data.

[0264] In some embodiments of the present application, the capacity reduction feature identification module 103 is specifically used to:

[0265] According to multiple wind speed conditions, multiple powers in the first power characteristic data are divided into multiple first power data sets, and the wind speeds corresponding to the powers in the same first power data set belong to the same wind speed condition;

[0266] For each first power data set, determining a first power characteristic value corresponding to the first power data set according to the power in the first power data set;

[0267] For each first power data set, comparing a first power characteristic value corresponding to the first power data set with a power threshold of a wind speed condition corresponding to the first power data set;

[0268] Determine a first number of target power data sets among the plurality of first power data sets, the target power data set being a first power data set whose first power characteristic value is less than a power threshold corresponding to a wind speed condition;

[0269] In response to the first number being greater than a first number threshold, determining that the first wind turbine generator system is in a reduced capacity state within a first time interval;

[0270] In response to the first number being less than or equal to a first number threshold, it is determined that the first wind turbine generator system is not in a reduced capacity state within the first time interval.

[0271] In some embodiments of the present application, the turbulence feature identification module 104 is specifically used to:

[0272] According to the plurality of wind speed conditions, the plurality of turbulence intensities in the first turbulence characteristic data are divided into a plurality of first turbulence data sets, and the wind speeds corresponding to the turbulence intensities in the same first turbulence data set belong to the same wind speed condition;

[0273] For each first turbulence data set, determining a first turbulence intensity characteristic value corresponding to the first turbulence data set according to the turbulence intensity in the first turbulence data set;

[0274] For each first turbulence data set, comparing a first turbulence intensity characteristic value corresponding to the first turbulence data set with a turbulence intensity threshold value of a wind speed condition corresponding to the first turbulence data set;

[0275] Determining a second number of target turbulence data sets among the plurality of first turbulence data sets, the target turbulence data set being a first turbulence data set having a first turbulence intensity characteristic value greater than a turbulence intensity threshold corresponding to a wind speed condition;

[0276] In response to the second number being greater than a second number threshold, determining that the first wind turbine generator system has abnormal turbulence intensity within the first time interval;

[0277] In response to the second number being less than or equal to the second number threshold, it is determined that no turbulence intensity abnormality exists in the first wind turbine group within the first time interval.

[0278] In some embodiments of the present application, the acquisition module 101 is further used to acquire sample data before acquiring the first operation data of the wind turbine generator set in the first time interval, wherein the sample data includes the second operation data of each second wind turbine generator set in the second time interval and the third operation data in the third time interval of each second wind turbine generator set among the plurality of second wind turbine generator sets, and the third time interval is earlier than the second time interval;

[0279] The data processing module 102 is further used to perform feature extraction processing on the second operation data and the third operation data of each second wind turbine set, respectively, to obtain the second power characteristic data and the second turbulence characteristic data, and the third power characteristic data and the third turbulence characteristic data of the second wind turbine set;

[0280] The device further includes: a first calculation module, for determining, for each second wind turbine generator set, a plurality of power deviations of the second wind turbine generator set under a plurality of wind speed conditions according to the second power characteristic data and the third power characteristic data of the second wind turbine generator set;

[0281] A second calculation module is used to determine, for each wind speed condition, a power threshold corresponding to the wind speed condition according to a plurality of powers and a plurality of power deviations of a plurality of second wind turbine generator sets under the wind speed condition;

[0282] The third calculation module is used to determine, for each wind speed condition, a turbulence intensity threshold corresponding to the wind speed condition according to the second turbulence characteristic data and the third turbulence characteristic data of the plurality of second wind turbine generator sets.

[0283] In some embodiments of the present application, the second power characteristic data includes multiple powers and multiple wind speeds corresponding to multiple time periods in the second time interval, the third power characteristic data includes multiple powers and multiple wind speeds corresponding to multiple time periods in the third time interval, and the first calculation module is specifically used to:

[0284] According to multiple wind speed operating conditions, multiple powers in the third power characteristic data of the second wind turbine generator set are divided into multiple third power data sets, and the wind speeds corresponding to the powers in the same third power data set belong to the same wind speed operating condition;

[0285] For each third power data set, determining, according to the power in the third power data set, a third power characteristic value of the second wind turbine generator set under the wind speed condition corresponding to the third power data set;

[0286] For each wind speed condition, determine that the wind speed corresponding to the second power characteristic data of the second wind turbine group belongs to the first power of the wind speed condition, and calculate the difference between the first power and the third power characteristic value of the second wind turbine group under the wind speed condition to obtain the power deviation of the second wind turbine group under the wind speed condition.

[0287] In some embodiments of the present application, the second computing module is specifically used to:

[0288] Determining, from the second power characteristic data of the plurality of second wind turbine generator sets, a plurality of second powers corresponding to wind speeds belonging to the wind speed operating condition;

[0289] Calculating the average of multiple second powers to obtain a power average;

[0290] Processing multiple power deviations of multiple second wind turbines under the wind speed condition based on a quartile algorithm to obtain an intermediate power deviation;

[0291] Determine the variance of the intermediate power deviation and obtain the power deviation standard deviation;

[0292] The power value range is obtained by multiplying the standard deviation of the deviation by the set standard deviation multiple and then adding the result to the power mean value and the set first margin;

[0293] The lower limit of the power value range is used as the power threshold corresponding to the wind speed condition.

[0294] In some embodiments of the present application, the data processing module 102 is further configured to extract the pitch characteristic data of the first wind turbine generator set from the first operation data before determining whether the first wind turbine generator set has abnormal turbulence intensity within the first time interval based on the first turbulence characteristic data;

[0295] The device further includes: a power limit detection module, which is used to determine whether the first wind turbine generator set is in a power limit state based on the pitch characteristic data;

[0296] The turbulence characteristic identification module 104 is used to determine whether there is abnormal turbulence intensity at the position of the first wind turbine generator set in the first time interval based on the first turbulence characteristic data in response to the first wind turbine generator set being in a capacity reduction state and a power limit state in the first time interval.

[0297] In some embodiments of the present application, the device further includes an early warning module for:

[0298] After determining that the first wind turbine generator set is in a turbulent capacity reduction state within the first time, generating early warning information related to the turbulent capacity reduction state;

[0299] Display warning information;

[0300] The warning information includes at least one of the following:

[0301] Warning text information and visual graphics;

[0302] The warning text information includes at least one of the following:

[0303] Warning problem, warning time, warning wind farm, warning unit, warning reason, warning description;

[0304] The visualization graph includes at least one of the following:

[0305] Graph showing the relationship between wind speed and power, and graph showing the relationship between wind speed and turbulence intensity.

[0306] The wind turbine turbulence reduction state detection device provided in the embodiment of the present application can achieve Figures 1 to 9 To avoid repetition, the various processes implemented by the method embodiment are not described here.

[0307] Fig.11 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present application is shown.

[0308] The electronic device may include a processor 1101 and a memory 1102 storing computer program instructions.

[0309] Specifically, the processor 1101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0310] The memory 1102 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 1102 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 1102 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 1102 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 1102 is a non-volatile solid-state memory. The memory 1102 may include a read-only memory (ROM), a random access memory (RAM), a disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical, or other physical / tangible memory storage device. Therefore, typically, the memory 1102 includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in any one of the wind turbine turbulence reduction state detection methods in the above-mentioned embodiments.

[0311] The processor 1101 reads and executes the computer program instructions stored in the memory 1102 to implement any one of the wind turbine generator set turbulence reduction state detection methods in the above embodiments.

[0312] In one example, the electronic device may further include a communication interface 1103 and a bus 1110. Fig.11 As shown, the processor 1101, the memory 1102, and the communication interface 1103 are connected via a bus 1110 and communicate with each other.

[0313] The communication interface 1103 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0314] Bus 1110 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 1110 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0315] In addition, in combination with the wind turbine turbulence reduction state detection method in the above embodiment, the present application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by the processor, any one of the wind turbine turbulence reduction state detection methods in the above embodiment is implemented.

[0316] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0317] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0318] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0319] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0320] The above is only a specific implementation of the present application. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working processes of the systems, modules and units described above can refer to the corresponding processes in the aforementioned method embodiments, and will not be repeated here. It should be understood that the protection scope of the present application is not limited to this. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in this application, and these modifications or replacements should be included in the protection scope of this application.

Claims

1. A method for detecting turbulent capacity reduction state of a wind turbine generator set, characterized in that: include: Acquire first operating data of a first wind turbine generator set within a first time interval; Performing feature extraction processing on the first operating data to obtain first power feature data and first turbulence feature data of the first wind turbine generator set; Determining whether the first wind turbine generator set is in a reduced capacity state within the first time zone based on the first power characteristic data; determining whether the first wind turbine generator set has abnormal turbulence intensity within the first time interval based on the first turbulence characteristic data; In response to the first wind turbine generator set being in a derated state and having an abnormal turbulence intensity within the first time interval, determining a time overlap rate of the derated state and the abnormal turbulence intensity; In response to the time overlap rate being greater than an overlap rate threshold, it is determined that the first wind turbine generator set is in a turbulent capacity reduction state.

2. The method according to claim 1, characterized in that The operation data of the first wind turbine generator set includes wind speed and converter active power. The feature extraction process is performed on the first operation data to obtain first power feature data and first turbulence feature data of the first wind turbine generator set, including: Dividing a first time interval corresponding to the first operation data into a plurality of time periods; For each time period, the operating data in the time period is calculated to obtain the power mean, wind speed mean and wind speed standard deviation in the time period; For each time period, the mean wind speed in the time period is taken as the wind speed corresponding to the time period, the mean power in the time period is taken as the power corresponding to the time period, and the quotient of the wind speed standard deviation and the wind speed mean in the time period is taken as the turbulence intensity corresponding to the time period; taking a plurality of wind speeds and a plurality of powers corresponding to the plurality of time periods as the first power characteristic data; The multiple wind speeds and the multiple turbulence intensities corresponding to the multiple time periods are used as the first turbulence characteristic data.

3. The method according to claim 2, characterized in that The determining, based on the first power characteristic data, whether the first wind turbine generator set is in a reduced capacity state within the first time interval includes: According to multiple wind speed conditions, multiple powers in the first power characteristic data are divided into multiple first power data sets, and the wind speeds corresponding to the powers in the same first power data set belong to the same wind speed condition; For each first power data set, determining a first power characteristic value corresponding to the first power data set according to the power in the first power data set; For each first power data set, comparing a first power characteristic value corresponding to the first power data set with a power threshold of a wind speed condition corresponding to the first power data set; Determine a first number of target power data sets among the plurality of first power data sets, the target power data set being a first power data set whose first power characteristic value is less than a power threshold corresponding to a wind speed condition; In response to the first number being greater than a first number threshold, determining that the first wind turbine generator set is in a reduced capacity state within the first time interval; In response to the first number being less than or equal to the first number threshold, it is determined that the first wind turbine generator set is not in a reduced capacity state within the first time interval.

4. The method according to claim 2, characterized in that: The determining whether the first wind turbine generator set has abnormal turbulence intensity in the first time interval based on the first turbulence characteristic data includes: According to a plurality of wind speed conditions, a plurality of turbulence intensities in the first turbulence characteristic data are divided into a plurality of first turbulence data sets, and the wind speeds corresponding to the turbulence intensities in the same first turbulence data set belong to the same wind speed condition; For each first turbulence data set, determining a first turbulence intensity characteristic value corresponding to the first turbulence data set according to the turbulence intensity in the first turbulence data set; For each first turbulence data set, comparing a first turbulence intensity characteristic value corresponding to the first turbulence data set with a turbulence intensity threshold value of a wind speed condition corresponding to the first turbulence data set; Determining a second number of target turbulence data sets among the plurality of first turbulence data sets, the target turbulence data set being a first turbulence data set having a first turbulence intensity characteristic value greater than a turbulence intensity threshold corresponding to a wind speed condition; In response to the second number being greater than a second number threshold, determining that the first wind turbine generator system has abnormal turbulence intensity within the first time interval; In response to the second number being less than or equal to the second number threshold, it is determined that the first wind turbine generator system has no turbulence intensity abnormality within the first time interval.

5. The method according to claim 3, characterized in that: Before acquiring the first operating data of the wind turbine generator set in the first time interval, the method further includes: acquiring sample data, the sample data including second operating data of each second wind turbine generator set in the plurality of second wind turbine generator sets in the second time interval and third operating data in a third time interval, the third time interval being earlier than the second time interval; For each second wind turbine generator set, performing feature extraction processing on the second operation data and the third operation data of the second wind turbine generator set respectively to obtain the second power characteristic data and the second turbulence characteristic data, and the third power characteristic data and the third turbulence characteristic data of the second wind turbine generator set; For each second wind turbine generator set, determining a plurality of power deviations of the second wind turbine generator set under the plurality of wind speed conditions according to the second power characteristic data and the third power characteristic data of the second wind turbine generator set; For each wind speed condition, determining a power threshold corresponding to the wind speed condition according to a plurality of powers and a plurality of power deviations of the plurality of second wind turbine generator sets under the wind speed condition; For each wind speed operating condition, a turbulence intensity threshold corresponding to the wind speed operating condition is determined according to the second turbulence characteristic data and the third turbulence characteristic data of the plurality of second wind turbine generator sets.

6. The method according to claim 5, characterized in that The second power characteristic data includes multiple powers and multiple wind speeds corresponding to multiple time periods within the second time interval, the third power characteristic data includes multiple powers and multiple wind speeds corresponding to multiple time periods within the third time interval, and for each second wind turbine generator set, determining the power deviation of the second wind turbine generator set under multiple wind speed conditions according to the second power characteristic data and the third power characteristic data of the second wind turbine generator set includes: According to multiple wind speed operating conditions, multiple powers in the third power characteristic data of the second wind turbine generator set are divided into multiple third power data sets, and the wind speeds corresponding to the powers in the same third power data set belong to the same wind speed operating condition; For each third power data set, determining, according to the power in the third power data set, a third power characteristic value of the second wind turbine generator set under the wind speed condition corresponding to the third power data set; For each wind speed condition, determine that the wind speed corresponding to the second power characteristic data of the second wind turbine group belongs to the first power of the wind speed condition, and calculate the difference between the first power and the third power characteristic value of the second wind turbine group under the wind speed condition to obtain the power deviation of the second wind turbine group under the wind speed condition.

7. The method according to claim 6, characterized in that The step of determining, for each wind speed condition, a power threshold corresponding to the wind speed condition according to a plurality of powers and a plurality of power deviations of the plurality of second wind turbine generator sets under the wind speed condition, comprises: Determine, from the second power characteristic data of the plurality of second wind turbine generator sets, a plurality of second powers corresponding to wind speeds belonging to the wind speed operating condition; Calculating the average of the plurality of second powers to obtain a power average; Processing a plurality of power deviations of the plurality of second wind turbine generator sets under the wind speed condition based on a quartile algorithm to obtain an intermediate power deviation; Determine the variance of the intermediate power deviation to obtain the power deviation standard deviation; The power value range is obtained by multiplying the deviation standard deviation by a set standard deviation multiple and adding the resultant to the power mean value and a set first margin; The lower limit value of the power value interval is used as the power threshold corresponding to the wind speed condition.

8. The method according to any one of claims 3 to 5, characterized in that: Before determining whether the first wind turbine generator set has abnormal turbulence intensity within the first time interval based on the first turbulence characteristic data, the method further includes: Extracting pitch characteristic data of the first wind turbine generator set from the first operating data; Determining whether the first wind turbine generator set is in a power-limited state based on the pitch characteristic data; The determining, based on the first turbulence characteristic data, whether the position of the first wind turbine generator set has abnormal turbulence intensity within the first time interval includes: In response to the first wind turbine being in a capacity reduction state and a power limitation state within the first time interval, it is determined whether the position of the first wind turbine has abnormal turbulence intensity within the first time interval based on the first turbulence characteristic data.

9. The method according to any one of claims 1 to 7, characterized in that: After determining that the first wind turbine generator set is in a turbulent capacity reduction state within the first time, the method further includes: generating warning information related to the turbulent capacity reduction state; Displaying the warning information; The warning information includes at least one of the following: Warning text information and visual graphics; The warning text information includes at least one of the following: Warning problem, warning time, warning wind farm, warning unit, warning reason, warning description; The visualization graph includes at least one of the following: Graph showing the relationship between wind speed and power, and graph showing the relationship between wind speed and turbulence intensity.

10. A wind turbine turbulence reduction state detection device, characterized in that: include: An acquisition module, used for acquiring first operating data of a first wind turbine generator set within a first time interval; a data processing module, configured to perform feature extraction processing on the first operating data to obtain first power feature data and first turbulence feature data of the first wind turbine generator set; a capacity reduction feature identification module, configured to determine whether the first wind turbine generator set is in a capacity reduction state within the first time interval based on the first power feature data; a turbulence characteristic identification module, configured to determine whether the first wind turbine generator set has abnormal turbulence intensity within the first time interval based on the first turbulence characteristic data; a time overlap rate determination module, configured to determine a time overlap rate of the reduced capacity state and the abnormal turbulence intensity in response to the first wind turbine generator set being in a reduced capacity state and abnormal turbulence intensity in the first time interval; The turbulence reduction capacity identification module is used to determine that the first wind turbine generator set is in a turbulence reduction capacity state within the first time interval in response to the time overlap rate being greater than the overlap rate threshold.

11. An electronic device, characterized in that: The device comprises: a processor and a memory storing computer program instructions; When the processor executes the computer program instructions, the method for detecting the turbulence reduction state of a wind turbine set according to any one of claims 1 to 9 is implemented.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer program instructions, and when the computer program instructions are executed by the processor, the method for detecting the turbulent capacity reduction state of a wind turbine generator set according to any one of claims 1 to 9 is implemented.

13. A computer program product, characterized in that When the instructions in the computer program product are executed by a processor of an electronic device, the electronic device executes the method for detecting the turbulent capacity reduction state of a wind turbine set as described in any one of claims 1 to 9.

Images