Method and device for dynamic prediction of wind turbine load based on wind direction change

Abstract

The present invention discloses a method and device for dynamically predicting the load of a wind turbine generator set based on wind direction changes, which belongs to the technical field of wind power generation. The method collects historical load, historical wind direction, and historical wind speed data of the wind turbine generator set of the target wind farm to construct a historical data set, and performs correlation analysis on the historical wind direction, historical wind speed, and historical load to obtain the correlation analysis results of the historical wind direction, wind speed, and load; the correlation analysis results are input into a preset initial model to train and optimize the initial model, and a load prediction model for predicting the future load of the wind turbine generator set is generated; the real-time wind direction, real-time wind speed, and unit operating state parameters are input into the load prediction model, and the predicted real-time load change of the wind turbine generator set is generated through the load prediction model to adjust the operating parameters of the wind turbine generator set. The present invention improves the prediction accuracy of the load impact caused by changes in wind speed and wind direction, and realizes rapid response and control of the wind turbine load.

Description

Technical Field

[0001] The present invention belongs to the technical field of wind power generation, and in particular relates to a method and a device for dynamically predicting the load of a wind power generator set based on wind direction changes. Background Art

[0002] As the global demand for renewable energy continues to increase, wind power generation has been widely used as a clean energy source. During the operation of wind turbines, their output power is affected by many factors, among which the most critical factors are changes in wind speed and wind direction. In order to optimize power generation efficiency and ensure long-term stable operation of equipment, the operation of wind turbines requires real-time monitoring of various parameters, such as wind speed, wind direction, unit load, etc.

[0003] In the prior art, wind power generation control systems collect real-time data through wind speed and wind direction sensors, and adjust the power output of the generator set accordingly based on these data. However, most existing control systems use preset fixed parameters for adjustment, lacking in-depth correlation analysis of multiple parameters such as wind speed, wind direction and load. This approach ignores the complexity and instantaneous variability of the wind environment. Especially when the wind speed and wind direction change dramatically, the system's response is often delayed and the operating status of the unit cannot be adjusted in time, resulting in unstable power output and even equipment overload. Summary of the invention

[0004] To this end, the present invention provides a method and device for dynamically predicting the load of a wind turbine generator set based on wind direction changes, so as to solve the problem in the prior art that the system response lags when the wind speed and wind direction change sharply, thereby affecting the stability of the power output of the wind turbine generator set due to the lack of in-depth correlation analysis of multiple parameters such as wind speed, wind direction and load.

[0005] In order to achieve the above object, the present invention provides the following technical solution: a method for dynamically predicting the load of a wind turbine generator set based on wind direction changes, comprising:

[0006] According to the terrain features and wind farm characteristics of the target wind farm, the real-time wind direction and real-time wind speed in the area where the target wind farm is located are collected to obtain the change frequency and change amplitude of the real-time wind direction and real-time wind speed; the unit operating status parameters of the wind turbine generator set of the target wind farm are collected, and the unit operating status parameters include unit speed, output power and tilt angle;

[0007] Collect historical load, historical wind direction, and historical wind speed data of the wind turbine generator set of the target wind farm, construct a historical data set using the historical load, historical wind direction, and historical wind speed data, and perform correlation analysis on the historical wind direction, historical wind speed, and historical load to obtain a correlation analysis result of the historical wind direction, historical wind speed, and historical load;

[0008] Inputting the correlation analysis result into a preset initial model to train and optimize the initial model, and generating a load prediction model for predicting the future load of the wind turbine generator set;

[0009] The real-time wind direction, the real-time wind speed, and the unit operating status parameters are input into the load prediction model, and the predicted real-time load change of the wind turbine is generated by the load prediction model. The operating parameters of the wind turbine are adjusted according to the predicted real-time load change of the wind turbine.

[0010] As a preferred solution of the method for dynamic prediction of wind turbine load based on wind direction change, it also includes:

[0011] Configure real-time wind direction according to the operating status of the wind turbine , Real-time wind speed , Unit operating status parameters Synchronous acquisition, and set the data acquisition interval through the acquisition clock and data sampling frequency ;

[0012] According to the wind direction and wind speed fluctuation characteristics in the area where the target wind farm is located, the data sampling frequency Make adjustments.

[0013] As a preferred method for dynamic prediction of wind turbine load based on wind direction changes, a historical data set is constructed using historical load, historical wind direction, and historical wind speed data. The expression is:

[0014] ;

[0015] In the formula, is the historical load data, is the historical wind speed data, For historical wind direction data;

[0016] In the process of correlating historical wind direction, historical wind speed and historical load, based on the historical data set , use the multi-parameter linear regression model to describe the relationship between wind direction, wind speed and load:

[0017] ;

[0018] In the formula, , is the regression parameter, Represents the nonlinear contribution of wind speed and direction to loads; , , is the empirical index parameter; Indicates the unit's own operating status parameters Impact on loads; is the error term.

[0019] As a preferred solution for the dynamic prediction method of wind turbine load based on wind direction changes, the load prediction model for predicting the future load of wind turbines is generated. The formula is:

[0020] ;

[0021] In the formula, , are the reference wind speed and reference wind direction respectively; , , is the model calibration parameter, which represents the nonlinear effect of wind speed, wind direction and unit operating parameters on the load; , is the empirical coefficient; Indicates the nonlinear effect of relative changes in wind speed on loads; Reflects the adjustment of load due to wind direction deviation; Indicates the direct impact of unit operating parameters on load.

[0022] As a preferred solution of the method for dynamically predicting the load of a wind turbine generator set based on wind direction changes, the load prediction model is used to generate the predicted real-time load change of the wind turbine generator set. The formula is:

[0023] ;

[0024] In the formula, represents the reference load;

[0025] It also includes setting a warning threshold for the load of the wind turbine generator set, and generating a warning signal when the load change meets the warning threshold; executing load reduction of the control system of the wind turbine generator set according to the warning signal, and sending a warning notification to the operation and maintenance personnel.

[0026] As a preferred solution for the dynamic prediction method of wind turbine load based on wind direction change, an intelligent adjustment control strategy is constructed in the process of adjusting the operating parameters of the wind turbine according to the predicted real-time load change of the wind turbine. The formula of the intelligent adjustment control strategy is:

[0027] ;

[0028] ;

[0029] In the formula, is the fan speed at time t, is the fan speed at time t+1, is the blade pitch angle at time t, is the blade pitch angle at time t+1, and To adjust the step size parameter.

[0030] The present invention also provides a device for dynamically predicting loads of a wind turbine generator set based on wind direction changes, comprising:

[0031] The wind direction and wind speed acquisition module is used to collect the real-time wind direction and real-time wind speed in the area where the target wind farm is located according to the terrain characteristics and wind farm characteristics of the target wind farm, and obtain the change frequency and change amplitude of the real-time wind direction and real-time wind speed;

[0032] A unit operation status acquisition module, used to acquire unit operation status parameters of the wind turbine generator sets of the target wind farm, wherein the unit operation status parameters include unit speed, output power and tilt angle;

[0033] A historical data association analysis module is used to collect historical load, historical wind direction, and historical wind speed data of the wind turbine generator set of the target wind farm, construct a historical data set using the historical load, historical wind direction, and historical wind speed data, and perform association analysis on the historical wind direction, historical wind speed, and historical load to obtain an association analysis result of the historical wind direction, historical wind speed, and historical load;

[0034] A load prediction model building module, used for inputting the correlation analysis result into a preset initial model to train and optimize the initial model, and generating a load prediction model for predicting the future load of the wind turbine generator set;

[0035] A load change analysis module, used for inputting the real-time wind direction, the real-time wind speed, and the unit operation status parameters into the load prediction model, and generating a predicted real-time load change of the wind turbine generator set through the load prediction model;

[0036] The operating parameter adjustment module is used to adjust the operating parameters of the wind turbine generator set according to the predicted real-time load changes of the wind turbine generator set.

[0037] As a preferred solution of the device for dynamically predicting the load of a wind turbine generator set based on wind direction changes, it also includes:

[0038] The acquisition parameter configuration module is used to configure the real-time wind direction according to the operating status of the wind turbine , Real-time wind speed , Unit operating status parameters Synchronous acquisition, and set the data acquisition interval through the acquisition clock and data sampling frequency ; It is also used to adjust the data sampling frequency according to the wind direction and wind speed fluctuation characteristics in the area where the target wind farm is located. Make adjustments;

[0039] In the historical data association analysis module:

[0040] Construct historical data sets using historical load, historical wind direction, and historical wind speed data The expression is:

[0041] ;

[0042] In the formula, is the historical load data, is the historical wind speed data, For historical wind direction data;

[0043] In the historical data association analysis module:

[0044] Based on historical data sets , use the multi-parameter linear regression model to describe the relationship between wind direction, wind speed and load:

[0045] ;

[0046] In the formula, , is the regression parameter, Represents the nonlinear contribution of wind speed and direction to loads; , , is the empirical index parameter; Indicates the unit's own operating status parameters Impact on loads; is the error term.

[0047] As a preferred solution of a device for dynamically predicting loads of a wind turbine generator set based on wind direction changes, in the load prediction model building module:

[0048] The generated load prediction model predicts the future loads of the wind turbine The formula is:

[0049] ;

[0050] In the formula, , are the reference wind speed and reference wind direction respectively; , , is the model calibration parameter, which represents the nonlinear effect of wind speed, wind direction and unit operating parameters on the load; , is the empirical coefficient; Indicates the nonlinear effect of relative changes in wind speed on loads; Reflects the adjustment of load due to wind direction deviation; Indicates the direct impact of unit operating parameters on load;

[0051] In the load variation analysis module:

[0052] The load prediction model is used to generate the predicted real-time load change of the wind turbine generator set. The formula is:

[0053] ;

[0054] In the formula, represents the reference load.

[0055] As a preferred solution of the device for dynamically predicting the load of a wind turbine generator set based on wind direction changes, it also includes:

[0056] The load warning module is used to set the warning threshold of the wind turbine load. When the load change meets the warning threshold, a warning signal is generated; the control system of the wind turbine is deloaded according to the warning signal, and a warning notification is sent to the operation and maintenance personnel.

[0057] As a preferred solution of the device for dynamically predicting the load of a wind turbine generator set based on wind direction changes, in the operating parameter adjustment module:

[0058] In the process of adjusting the operating parameters of the wind turbine generator set according to the predicted real-time load changes of the wind turbine generator set, an intelligent adjustment control strategy is constructed. The formula of the intelligent adjustment control strategy is:

[0059] ;

[0060] ;

[0061] In the formula, is the fan speed at time t, is the fan speed at time t+1, is the blade pitch angle at time t, is the blade pitch angle at time t+1, and To adjust the step size parameter.

[0062] The present invention has the following advantages: according to the terrain features and wind farm characteristics of the target wind farm, the real-time wind direction and real-time wind speed in the area where the target wind farm is located are collected to obtain the change frequency and change amplitude of the real-time wind direction and real-time wind speed; the unit operating status parameters of the wind turbine generator set of the target wind farm are collected, and the unit operating status parameters include unit speed, output power and tilt angle; the historical load, historical wind direction and historical wind speed data of the wind turbine generator set of the target wind farm are collected, and the historical load, historical wind direction and historical wind speed data are used to construct a historical data set, and the historical wind speed data are stored in the historical data set. The wind direction, historical wind speed and historical load are correlated and analyzed to obtain the correlation analysis results of the historical wind direction, historical wind speed and historical load; the correlation analysis results are input into the preset initial model to train and optimize the initial model to generate a load prediction model for predicting the future load of the wind turbine; the real-time wind direction, the real-time wind speed and the unit operating state parameters are input into the load prediction model, and the predicted real-time load change of the wind turbine is generated through the load prediction model, and the operating parameters of the wind turbine are adjusted according to the predicted real-time load change of the wind turbine. The present invention improves the prediction accuracy of the load impact caused by changes in wind speed and wind direction, overcomes the deficiency of the traditional static model that it cannot reflect the fluctuation of wind conditions in time; realizes the rapid response and control of the wind turbine load, improves the load stability and the operating efficiency of the wind turbine; ensures the accurate prediction and control of load changes, and can greatly improve the real-time and adaptability of the prediction model. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0064] Figure 1 A schematic flow chart of a method for dynamically predicting a load of a wind turbine generator set based on wind direction changes provided in an embodiment of the present invention;

[0065] Figure 2 Schematic diagram of the architecture of a device for dynamically predicting loads of a wind turbine generator set based on wind direction changes provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0066] The following is a description of the implementation of the present invention by specific embodiments. People familiar with the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0067] Example 1

[0068] See also Figure 1 The embodiment of the present invention provides a method for dynamically predicting the load of a wind turbine generator set based on wind direction changes, comprising the following steps:

[0069] S1. According to the terrain features and wind farm characteristics of the target wind farm, collect the real-time wind direction and real-time wind speed in the area where the target wind farm is located, and obtain the change frequency and change amplitude of the real-time wind direction and real-time wind speed; collect the unit operation status parameters of the wind turbine generator set of the target wind farm, and the unit operation status parameters include unit speed, output power and tilt angle;

[0070] S2. Collect historical load, historical wind direction, and historical wind speed data of the wind turbine generator set of the target wind farm, construct a historical data set using the historical load, historical wind direction, and historical wind speed data, and perform correlation analysis on the historical wind direction, historical wind speed, and historical load to obtain correlation analysis results of the historical wind direction, historical wind speed, and historical load;

[0071] S3, inputting the correlation analysis result into a preset initial model to train and optimize the initial model, and generating a load prediction model for predicting the future load of the wind turbine generator set;

[0072] S4. Input the real-time wind direction, the real-time wind speed, and the unit operating status parameters into the load prediction model, generate a predicted real-time load change of the wind turbine through the load prediction model, and adjust the operating parameters of the wind turbine according to the predicted real-time load change of the wind turbine.

[0073] In this embodiment, in step S1, the real-time wind direction is collected by continuously acquiring wind direction data through a wind direction sensor to reflect the current wind direction in the area where the wind turbine generator set is located. For example, within one second, the wind direction may change from 45 degrees north by east to 30 degrees north by west; the real-time wind speed is collected by continuously acquiring the current wind speed using a wind speed sensor, for example, the wind speed rises from 10 meters per second to 15 meters per second. By simultaneously collecting real-time wind direction and wind speed data, the changes in wind conditions can be more accurately monitored, thereby providing instant feedback and adjustment basis for the operation of the wind turbine generator set. Data information related to the operating status of the wind turbine generator set is collected through sensors, including the speed, output power and tilt angle of the unit. The unit speed refers to the rotation speed of the wind rotor of the generator set, for example, the speed is 15 revolutions per minute. The output power refers to the electrical energy output generated by the unit under the current wind conditions, for example, when the wind speed reaches 12 meters per second, the unit may generate 500 kilowatts of power. The tilt angle refers to the inclination of the wind turbine generator set relative to the vertical direction, and the tilt angle must be guaranteed to be within a certain range to avoid accidents such as collapse of the unit.

[0074] Specifically, according to the terrain characteristics and wind farm characteristics of the target wind farm, wind direction sensors and wind speed sensors are arranged. According to the wind direction change frequency, angle range, wind farm environment, and the terrain and height characteristics of the generator set, existing high-sensitivity, high-range sensors are selected and arranged in the best position to improve data collection accuracy. According to the operating status of the wind turbine generator set, real-time wind direction sensors are configured. , Real-time wind speed , Unit operating status parameters Synchronous acquisition, and set the data acquisition interval through the acquisition clock and data sampling frequency ; According to the wind direction and wind speed fluctuation characteristics in the area where the target wind farm is located, the data sampling frequency Make adjustments.

[0075] Specifically, the collection interval and data sampling frequency The setting process is to obtain the frequency and amplitude of wind speed and wind direction according to the changing characteristics of wind direction and wind speed in the area where the target wind farm is located, and set the initial data acquisition frequency of the wind direction sensor and wind speed sensor accordingly. By real-time monitoring the changing frequency and amplitude of wind direction and wind speed, the initial data acquisition frequency is dynamically adjusted to obtain the acquisition clock, and quickly respond to sudden changes in wind speed and wind direction.

[0076] Specifically, the above-mentioned change characteristics include seasonal wind speed fluctuations, instantaneous strong winds, and sudden changes in wind direction. When collecting data, the sensor's collection frequency is adjusted according to the fluctuation characteristics to adapt to wind speed changes in different seasons. In addition, instantaneous strong winds refer to the phenomenon of rapid increase in wind speed in a short period of time, such as typhoons, thunderstorms, or sudden wind increases. Instantaneous strong winds put a lot of pressure on the operation of wind turbines and can easily cause equipment overload. Therefore, the data collection frequency needs to be greatly increased in order to quickly capture sudden changes in wind speed.

[0077] In this embodiment, in step S2, historical wind direction, historical wind speed, and previous historical load data are collected, and a historical data set is constructed using the historical load, historical wind direction, and historical wind speed data. The expression is , where is the historical load data, is the historical wind speed data, Historical wind direction data.

[0078] Specifically, load correlation analysis based on historical wind direction and historical wind speed refers to analyzing the relationship between wind direction, wind speed and load. For example, during the analysis process, it may be found that when the wind direction changes from north-east to due north, the load decreases by 10%, or when the wind speed increases from 8 meters per second to 12 meters per second, the load increases by 20%. Through correlation analysis, the specific impact of changes in wind direction and wind speed on the unit load is clarified, thereby providing key data for further optimization of the model.

[0079] Among them, in the process of correlating historical wind direction, historical wind speed and historical load, based on the historical data set , use the multi-parameter linear regression model to describe the relationship between wind direction, wind speed and load:

[0080] ;

[0081] In the formula, , is the regression parameter, Represents the nonlinear contribution of wind speed and direction to loads; , , is an empirical index parameter, the fitting of which makes the model adapt to the load characteristics under specific environmental conditions; Indicates the unit's own operating status parameters The impact on the load is related to the unit's power generation, speed and other parameters; is the error term, which captures the randomness and error factors not considered by the load model.

[0082] In this embodiment, in step S3, a load prediction model is constructed using the historical data set. The first correlation analysis result is input into the initial model for training and optimization, and the generated load prediction model for predicting the future load of the wind turbine generator set is The formula is:

[0083] ;

[0084] In the formula, , are the reference wind speed and reference wind direction, respectively, which serve as the basis for load standardization; , , is the model calibration parameter, which represents the nonlinear effect of wind speed, wind direction and unit operating parameters on the load; , is an empirical coefficient, which enhances the accuracy of the prediction model by fitting historical data. This formula is based on the dynamic changes of wind speed and wind direction, and refines the relationship between load and wind speed and wind direction; Indicates the nonlinear effect of the relative change of wind speed on the load. The closer the wind speed is to the reference value, the smaller the load change is. Reflects the adjustment of the load due to wind direction deviation. If the wind direction deviation is large, the load will be significantly affected. Indicates the direct impact of unit operating parameters on load.

[0085] Thus, by correcting and adjusting the model parameters through a large amount of historical data, training and optimizing the model, a load prediction model that can accurately predict the future load of the wind turbine generator set is finally generated, accurately guiding the formulation of the unit operation strategy. The prediction accuracy of the load impact caused by changes in wind speed and wind direction is improved, overcoming the deficiency of traditional static models that cannot reflect wind fluctuations in a timely manner.

[0086] In this embodiment, in step S4, the real-time wind speed collected in step S1 is , Real-time wind direction and unit operating parameters Input a load prediction model and generate a predicted real-time load change of the wind turbine generator set through the load prediction model The formula is:

[0087] ;

[0088] In the formula, Represents the reference load. This formula is used to capture the dynamic impact of real-time wind speed and wind direction changes on the unit load and generate load changes. This ensures accurate prediction and control of load changes. Compared with traditional single parameter or low-frequency acquisition methods, it can greatly improve the real-time and adaptability of the prediction model.

[0089] In a possible embodiment, it also includes setting a warning threshold value for the load of the wind turbine generator set, and generating a warning signal when the load change meets the warning threshold value; executing load reduction of the control system of the wind turbine generator set according to the warning signal, and sending a warning notification to the operation and maintenance personnel.

[0090] Specifically, a warning threshold for the load of the wind turbine generator set is set, and the warning threshold is the maximum load capacity of the unit. When the load change meets the warning threshold, a warning signal is generated; based on the warning signal, the control system automatically reduces the load, and sends a warning notification to the operation and maintenance personnel. The setting of the warning threshold is based on the physical bearing capacity of the unit and historical data analysis to avoid damage to the equipment due to overload. Send a warning signal and provide further load adjustment references to facilitate intelligent adjustment and control of the unit, so as to achieve timely response to changes in the wind environment, improve power output stability and safe operation of the wind turbine generator set.

[0091] In a possible embodiment, in the process of adjusting the operating parameters of the wind turbine generator set according to the predicted real-time load change of the wind turbine generator set, an intelligent adjustment control strategy is constructed, and the formula of the intelligent adjustment control strategy is:

[0092] ;

[0093] ;

[0094] In the formula, is the fan speed at time t, is the fan speed at time t+1, is the blade pitch angle at time t, is the blade pitch angle at time t+1, and To adjust the step size parameters, the optimal adjustment of the unit operating parameters under the current wind speed and wind direction conditions can be obtained by analyzing the partial derivatives of the load with respect to wind speed and wind direction. Thus, the real-time load changes are used to intelligently adjust the unit operating parameters, such as wind turbine speed and blade pitch angle. By analyzing the sensitivity of the load to wind speed and wind direction, control optimization is performed in the form of partial derivatives, which achieves rapid response and control of the wind turbine load, improves load stability and wind turbine operating efficiency, and cooperates with nonlinear analysis models to achieve correlation analysis of wind speed, wind direction, and load, and achieves efficient prediction of real-time load changes.

[0095] In order to verify the effect of the present invention, simulation verification was carried out to collect the original power output and load conditions of a 5MW wind turbine. After data pre-processing and data analysis, a data set was formed. The dynamic impact of the load on the computer group was calculated using the load prediction model, load changes were generated, and the unit regulation was optimized. The results after optimization are shown in Table 1, that is, the statistical characteristics of the data changing in the 3600s time period. The average values ​​and standard deviations of the flapping bending moment, swing bending moment and torsional bending moment were compared. It can be seen from the statistics that the flapping bending moment and swing bending moment of the unit are reduced, the aerodynamic power of the unit is improved, and the stability of the blades is improved. Among them, according to the results in Table 1, the average value of the aerodynamic power output after optimization increased from 3325.47kW to 3340.92kW; the average values ​​of the load data were all reduced, indicating that the load of the optimized unit was reduced. In addition, the standard deviation of the data was reduced overall after optimization, especially in the standard deviation of the aerodynamic power and swing bending moment, indicating that the volatility of the system was reduced after optimization, showing a more stable performance. It can be seen that the present invention can reduce fatigue damage to the blades of the unit, thereby extending the life of the unit, and at the same time can effectively improve the power output of the unit.

[0096] Table 1 Statistics of optimization effect of unit load control

[0097]

[0098] In summary, the embodiments of the present invention collect the real-time wind direction and real-time wind speed in the area where the target wind farm is located according to the terrain features and wind farm characteristics of the target wind farm, and obtain the change frequency and change amplitude of the real-time wind direction and real-time wind speed; collect the unit operating status parameters of the wind turbine generator set of the target wind farm, and the unit operating status parameters include unit speed, output power and tilt angle; collect the historical load, historical wind direction, and historical wind speed data of the wind turbine generator set of the target wind farm, use the historical load, historical wind direction, and historical wind speed data to construct a historical data set, and perform correlation analysis on the historical wind direction, historical wind speed and historical load to obtain the correlation analysis results of the historical wind direction, historical wind speed and historical load; and input the correlation analysis results into a preset initial model The initial model is trained and optimized to generate a load prediction model for predicting the future load of the wind turbine generator set; the real-time wind direction, the real-time wind speed, and the unit operating state parameters are input into the load prediction model, and the predicted real-time load change of the wind turbine generator set is generated through the load prediction model, and the operating parameters of the wind turbine generator set are adjusted according to the predicted real-time load change of the wind turbine generator set; the warning threshold of the wind turbine generator set load is set, and when the load change meets the warning threshold, a warning signal is generated; the control system of the wind turbine generator set is deloaded according to the warning signal, and a warning notification is sent to the operation and maintenance personnel; in the process of adjusting the operating parameters of the wind turbine generator set according to the predicted real-time load change of the wind turbine generator set, an intelligent adjustment control strategy is constructed. The present invention improves the prediction accuracy of the load impact caused by changes in wind speed and wind direction, overcomes the deficiency that the traditional static model cannot reflect the fluctuation of wind conditions in time; realizes the rapid response and control of the wind turbine load, improves the load stability and the operating efficiency of the wind turbine; ensures the accurate prediction and control of load changes, and can greatly improve the real-time and adaptability of the prediction model.

[0099] Example 2

[0100] See also Figure 2 Embodiment 2 of the present invention further provides a device for dynamically predicting loads of a wind turbine generator set based on wind direction changes, comprising:

[0101] The wind direction and wind speed collection module 100 is used to collect the real-time wind direction and real-time wind speed in the area where the target wind farm is located according to the terrain characteristics and wind farm characteristics of the target wind farm, and obtain the change frequency and change amplitude of the real-time wind direction and real-time wind speed;

[0102] The unit operation status acquisition module 200 is used to acquire the unit operation status parameters of the wind turbine generator sets of the target wind farm, wherein the unit operation status parameters include unit speed, output power and tilt angle;

[0103] The historical data association analysis module 300 is used to collect the historical load, historical wind direction, and historical wind speed data of the wind turbine generator set of the target wind farm, construct a historical data set using the historical load, historical wind direction, and historical wind speed data, and perform association analysis on the historical wind direction, historical wind speed, and historical load to obtain the association analysis results of the historical wind direction, historical wind speed, and historical load;

[0104] A load prediction model building module 400 is used to input the correlation analysis result into a preset initial model to train and optimize the initial model, and generate a load prediction model for predicting the future load of the wind turbine generator set;

[0105] A load change analysis module 500, for inputting the real-time wind direction, the real-time wind speed, and the unit operation status parameters into the load prediction model, and generating a predicted real-time load change of the wind turbine generator set through the load prediction model;

[0106] The operating parameter adjustment module 600 is used to adjust the operating parameters of the wind turbine generator set according to the predicted real-time load change of the wind turbine generator set.

[0107] In this embodiment, it also includes:

[0108] The acquisition parameter configuration module 700 is used to configure the real-time wind direction according to the operating status of the wind turbine generator set. , Real-time wind speed , Unit operating status parameters Synchronous acquisition, and set the data acquisition interval through the acquisition clock and data sampling frequency ; It is also used to adjust the data sampling frequency according to the wind direction and wind speed fluctuation characteristics in the area where the target wind farm is located. Make adjustments;

[0109] In the historical data association analysis module 300:

[0110] Construct historical data sets using historical load, historical wind direction, and historical wind speed data The expression is:

[0111] ;

[0112] In the formula, is the historical load data, is the historical wind speed data, For historical wind direction data;

[0113] In the historical data association analysis module 300:

[0114] Based on historical data sets , use the multi-parameter linear regression model to describe the relationship between wind direction, wind speed and load:

[0115] ;

[0116] In the formula, , is the regression parameter, Represents the nonlinear contribution of wind speed and direction to loads; , , is the empirical index parameter; Indicates the unit's own operating status parameters Impact on loads; is the error term.

[0117] In this embodiment, in the load prediction model building module 400:

[0118] The generated load prediction model predicts the future loads of the wind turbine The formula is:

[0119] ;

[0120] In the formula, , are the reference wind speed and reference wind direction respectively; , , is the model calibration parameter, which represents the nonlinear effect of wind speed, wind direction and unit operating parameters on the load; , is the empirical coefficient; Indicates the nonlinear effect of relative changes in wind speed on loads; Reflects the adjustment of load due to wind direction deviation; Indicates the direct impact of unit operating parameters on load;

[0121] In the load change analysis module 500:

[0122] The load prediction model is used to generate the predicted real-time load change of the wind turbine generator set. The formula is:

[0123] ;

[0124] In the formula, represents the reference load.

[0125] In this embodiment, it also includes:

[0126] The load warning module 800 is used to set a warning threshold for the load of the wind turbine generator set, and generate a warning signal when the load change meets the warning threshold; according to the warning signal, the control system of the wind turbine generator set is loaded down, and a warning notification is sent to the operation and maintenance personnel.

[0127] In this embodiment, in the operating parameter adjustment module 600:

[0128] In the process of adjusting the operating parameters of the wind turbine generator set according to the predicted real-time load changes of the wind turbine generator set, an intelligent adjustment control strategy is constructed. The formula of the intelligent adjustment control strategy is:

[0129] ;

[0130] ;

[0131] In the formula, is the fan speed at time t, is the fan speed at time t+1, is the blade pitch angle at time t, is the blade pitch angle at time t+1, and To adjust the step size parameter.

[0132] It should be noted that the information interaction, execution process and other contents between the modules of the above-mentioned device are based on the same concept as the method embodiment in Example 1 of the present application, and the technical effects they bring are the same as those of the method embodiment of the present application. For specific contents, please refer to the description in the method embodiment shown in the previous part of the present application, and will not be repeated here.

[0133] Example 3

[0134] Embodiment 3 of the present invention provides a non-transitory computer-readable storage medium, in which a program code for a method for dynamically predicting the load of a wind turbine generator set based on wind direction changes is stored. The program code includes instructions for executing the method for dynamically predicting the load of a wind turbine generator set based on wind direction changes of embodiment 1 or any possible implementation thereof.

[0135] Computer-readable storage media can be any available media that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available media can be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state drives, SSDs), etc.

[0136] Example 4

[0137] Embodiment 4 of the present invention provides an electronic device, including: a memory and a processor;

[0138] The processor and the memory communicate with each other via a bus; the memory stores program instructions that can be executed by the processor, and the processor calls the program instructions to execute the method for dynamic prediction of wind turbine load based on wind direction changes in Example 1 or any possible implementation thereof.

[0139] Specifically, the processor can be implemented by hardware or by software. When implemented by hardware, the processor can be a logic circuit, an integrated circuit, etc.; when implemented by software, the processor can be a general-purpose processor implemented by reading software codes stored in a memory. The memory can be integrated in the processor or can be located outside the processor and exist independently.

[0140] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center.

[0141] Obviously, those skilled in the art should understand that the above modules or steps of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order than here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0142] Although the present invention has been described in detail above by general description and specific embodiments, it is obvious to those skilled in the art that some modifications or improvements can be made to the present invention. Therefore, these modifications or improvements made without departing from the spirit of the present invention all belong to the scope of protection claimed by the present invention.

Claims

1. A method for dynamic prediction of wind turbine load based on wind direction change, characterized in that: include: According to the terrain features and wind farm characteristics of the target wind farm, the real-time wind direction and real-time wind speed in the area where the target wind farm is located are collected to obtain the change frequency and change amplitude of the real-time wind direction and real-time wind speed; the unit operating status parameters of the wind turbine generator set of the target wind farm are collected, and the unit operating status parameters include unit speed, output power and tilt angle; Collect historical load, historical wind direction, and historical wind speed data of the wind turbine generator set of the target wind farm, construct a historical data set using the historical load, historical wind direction, and historical wind speed data, and perform correlation analysis on the historical wind direction, historical wind speed, and historical load to obtain a correlation analysis result of the historical wind direction, historical wind speed, and historical load; Inputting the correlation analysis result into a preset initial model to train and optimize the initial model, and generating a load prediction model for predicting the future load of the wind turbine generator set; Inputting the real-time wind direction, the real-time wind speed, and the unit operating status parameters into the load prediction model, generating a predicted real-time load change of the wind turbine generator set through the load prediction model, and adjusting the operating parameters of the wind turbine generator set according to the predicted real-time load change of the wind turbine generator set; Construct historical data set D using historical load, historical wind direction, and historical wind speed data h The expression is: D h ={(v h ,i h ,L h )} Where, L h is the historical load data, v h is the historical wind speed data, θ h For historical wind direction data; In the process of correlation analysis of historical wind direction, historical wind speed and historical load, based on the historical data set D h , a multi-parameter linear regression model is used to describe the relationship between wind direction, wind speed and load: In the formula, α1 and α2 are regression parameters, Indicates the nonlinear contribution of wind speed and wind direction to load; β1, β2, β3 are empirical index parameters; Indicates the unit's own operating status parameter P op (t) The influence on the load; ∈h is the error term; The generated load prediction model L(t) formula for predicting the future load of the wind turbine generator set is: In the formula, v r ,θ r are the reference wind speed and reference wind direction respectively; γ1, γ2, and γ3 are model calibration parameters, representing the nonlinear effects of wind speed, wind direction, and unit operating parameters on the load; η1 and η2 are empirical coefficients; Represents the nonlinear effect of the relative change of wind speed on the load; 1+γ2·sin(θ(t)-θ r ) reflects the adjustment of load due to wind direction deviation; Indicates the direct impact of unit operating parameters on load.

2. The method for dynamic prediction of wind turbine load based on wind direction change according to claim 1 is characterized in that: Also includes: According to the operating status of the wind turbine generator set, configure the real-time wind direction θ(t), real-time wind speed v(t), and the unit operating status parameter P op (t) synchronous acquisition, and set the data acquisition interval Δt and data sampling frequency through the acquisition clock According to the wind direction and wind speed fluctuation characteristics in the area where the target wind farm is located, the data sampling frequency f s Make adjustments.

3. The method for dynamic prediction of wind turbine load based on wind direction change according to claim 1 is characterized in that: The formula for generating the predicted real-time load change ΔL(t) of the wind turbine generator set by the load prediction model is: ΔL(t)=L(t)-L ref Where, L ref represents the reference load; It also includes setting a warning threshold of the load of the wind turbine generator set, and generating a warning signal when the load change meets the warning threshold; The control system of the wind turbine generator set is loaded down according to the warning signal, and a warning notification is sent to the operation and maintenance personnel.

4. The method for dynamic prediction of wind turbine load based on wind direction change according to claim 3 is characterized in that: In the process of adjusting the operating parameters of the wind turbine generator set according to the predicted real-time load changes of the wind turbine generator set, an intelligent adjustment control strategy is constructed. The formula of the intelligent adjustment control strategy is: Where n(t) is the wind turbine speed at time t, n(t+1) is the wind turbine speed at time t+1, A(t) is the blade pitch angle at time t, A(t+1) is the blade pitch angle at time t+1, and λ1 and λ2 are adjustment step parameters.

5. A device for dynamically predicting loads of a wind turbine generator set based on wind direction changes, characterized in that: include: The wind direction and wind speed acquisition module is used to collect the real-time wind direction and real-time wind speed in the area where the target wind farm is located according to the terrain characteristics and wind farm characteristics of the target wind farm, and obtain the change frequency and change amplitude of the real-time wind direction and real-time wind speed; A unit operation status acquisition module, used to acquire unit operation status parameters of the wind turbine generator sets of the target wind farm, wherein the unit operation status parameters include unit speed, output power and tilt angle; A historical data association analysis module is used to collect historical load, historical wind direction, and historical wind speed data of the wind turbine generator set of the target wind farm, construct a historical data set using the historical load, historical wind direction, and historical wind speed data, and perform association analysis on the historical wind direction, historical wind speed, and historical load to obtain an association analysis result of the historical wind direction, historical wind speed, and historical load; A load prediction model building module, used for inputting the correlation analysis result into a preset initial model to train and optimize the initial model, and generating a load prediction model for predicting the future load of the wind turbine generator set; A load change analysis module, used for inputting the real-time wind direction, the real-time wind speed, and the unit operation status parameters into the load prediction model, and generating a predicted real-time load change of the wind turbine generator set through the load prediction model; An operating parameter adjustment module is used to adjust the operating parameters of the wind turbine generator set according to the predicted real-time load changes of the wind turbine generator set; In the historical data association analysis module: Construct historical data set D using historical load, historical wind direction, and historical wind speed data h The expression is: D h ={(v h ,i h ,L h )} Where, L h is the historical load data, v h is the historical wind speed data, θ h For historical wind direction data; In the historical data association analysis module: Based on the historical data set D h , a multi-parameter linear regression model is used to describe the relationship between wind direction, wind speed and load: In the formula, α1 and α2 are regression parameters, Indicates the nonlinear contribution of wind speed and wind direction to load; β1, β2, β3 are empirical index parameters; Indicates the unit's own operating status parameter P op (t) The influence on the load; ∈h is the error term; In the load prediction model construction module: The generated load prediction model L(t) formula for predicting the future load of the wind turbine generator set is: In the formula, v r ,θ r are the reference wind speed and reference wind direction respectively; γ1, γ2, and γ3 are model calibration parameters, representing the nonlinear effects of wind speed, wind direction, and unit operating parameters on the load; η1 and η2 are empirical coefficients; Represents the nonlinear effect of the relative change of wind speed on the load; 1+γ2·sin(θ(t)-θ r ) reflects the adjustment of load due to wind direction deviation; Indicates the direct impact of unit operating parameters on load.

6. The device for dynamically predicting load of a wind turbine generator set based on wind direction change according to claim 5, characterized in that: Also includes: The acquisition parameter configuration module is used to configure the real-time wind direction θ(t), real-time wind speed v(t), and unit operating status parameter P according to the operating status of the wind turbine generator set. op (t) synchronous acquisition, and set the data acquisition interval Δt and data sampling frequency through the acquisition clock It is also used to adjust the data sampling frequency f according to the wind direction and wind speed fluctuation characteristics in the area where the target wind farm is located. s Make adjustments.

7. The device for dynamically predicting loads of a wind turbine generator set based on wind direction changes according to claim 6, characterized in that: In the load variation analysis module: The formula for generating the predicted real-time load change ΔL(t) of the wind turbine generator set by the load prediction model is: ΔL(t)=L(t)-L ref Where, L ref represents the reference load.

8. The device for dynamically predicting loads of a wind turbine generator set based on wind direction changes according to claim 7, characterized in that: Also includes: A load warning module is used to set a warning threshold of the wind turbine load and generate a warning signal when the load change meets the warning threshold; Execute load shedding of the control system of the wind turbine generator set according to the warning signal, and send a warning notification to the operation and maintenance personnel; In the operating parameter adjustment module: In the process of adjusting the operating parameters of the wind turbine generator set according to the predicted real-time load changes of the wind turbine generator set, an intelligent adjustment control strategy is constructed. The formula of the intelligent adjustment control strategy is: Where n(t) is the wind turbine speed at time t, n(t+1) is the wind turbine speed at time t+1, A(t) is the blade pitch angle at time t, A(t+1) is the blade pitch angle at time t+1, and λ1 and λ2 are adjustment step parameters.

Images