Wind turbine generator yaw wind alignment error calculation method based on goodness-of-fit

Abstract

The embodiment of the invention provides a wind turbine generator yaw wind alignment error calculation method and system based on goodness of fit, a terminal and a medium, and belongs to the technical field of wind power generation. The method comprises the following steps: firstly, preprocessing original data to eliminate the interference of working conditions such as variable pitch, shutdown, limited power and the like on the generated power; interval data set division is carried out based on the wind speed interval and the yaw included angle; then a hypothesis testing method is used for checking the power distribution condition of the subsets of each wind speed interval, a corresponding fitting method is selected according to the actual distribution condition of each subset, and therefore the yaw wind direction where the maximum power is located in the interval is determined; and finally, comprehensively considering the yaw error angle calculated in each wind speed interval, if the yaw error angles obtained in each wind speed interval have relatively high consistency and the advantages and disadvantages of a fitting result meet a preset requirement, considering that a significant yaw error angle exists in the wind field, and calculating to obtain the yaw error angle. According to the invention, the accuracy of yaw error calculation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power generation, and in particular to a method, system, terminal and medium for calculating yaw-to-wind error of a wind turbine generator set based on goodness of fit. Background Art

[0002] As the world pays more and more attention to environmental protection and sustainable development, the new energy industry, especially the wind power industry, has ushered in unprecedented development opportunities. As a clean and renewable energy form, the effective use of wind power is of great significance to reducing carbon emissions and achieving energy structure transformation. However, the development of the wind power industry is not smooth sailing. The yaw system is one of the core components of the wind turbine, and its performance directly affects the power generation efficiency of the wind turbine.

[0003] The main function of the yaw system is to maximize the capture of wind energy and increase power generation by adjusting the direction of the wind turbine rotor so that it is always aligned with the incoming wind. However, in actual engineering applications, the yaw system faces many challenges. First of all, the zero-degree deviation problem of the wind vane of the unit cannot be ignored. When the zero degree of the wind vane is no longer aligned with the axis of the nacelle, the yaw error angle measured by the wind vane will deviate from the true value, thereby affecting the accuracy and reliability of the yaw system.

[0004] Secondly, during the operation of the wind turbine, the high-speed rotation of the impeller will cause the surrounding air to produce a rotation effect, forming the so-called impeller wake. This phenomenon will not only interfere with the measurement of the wind vane, causing a deviation between the measured yaw error and the actual yaw error, but also increase the operating burden of the wind turbine and reduce the power generation efficiency.

[0005] The existence of yaw error is undoubtedly a huge waste of the wind turbine's power generation potential. It not only causes the wind turbine to fail to fully utilize wind energy, but also increases the wear and tear and energy consumption of the unit due to frequent yaw adjustments, further affecting power generation.

[0006] Therefore, how to accurately identify the yaw wind error and thereby improve the accuracy and stability of the yaw system has become a technical problem that needs to be urgently solved in the current wind power industry. Summary of the invention

[0007] In view of the deficiencies in the prior art, the present invention proposes a method, system, terminal and medium for calculating the yaw-to-wind error of a wind turbine based on goodness of fit, so as to solve the technical problems existing in the prior art.

[0008] The technical solution adopted by the present invention is:

[0009] A first aspect of this embodiment provides a method for calculating a yaw error of a wind turbine generator system based on goodness of fit, comprising:

[0010] Obtain SCADA data from wind turbines;

[0011] Preprocessing the SCADA data to obtain N wind speed intervals;

[0012] Perform KS normal distribution detection and Jarque-Bera skewed distribution hypothesis detection on the power data in each wind speed interval, and obtain wind speed intervals that obey KS normal distribution, wind speed intervals that obey Jarque-Bera skewed distribution, and / or wind speed intervals that do not conform to standard distribution;

[0013] Each wind speed interval is divided into yaw angle intervals, and each wind speed interval is divided into M sub-intervals;

[0014] Calculate the average power of M sub-intervals in each wind speed interval, and obtain M average power data for each wind speed interval;

[0015] For the wind speed interval that obeys the KS normal distribution, the number of valid data points in the wind speed interval that obeys the KS normal distribution is used as the weight, and the average power and wind direction of each sub-interval of the wind speed interval that obeys the KS normal distribution are fitted with a binomial, and a quadratic function curve describing the change of power with wind direction is obtained;

[0016] If the vertex of the quadratic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the KS normal distribution, and the abscissa of the vertex of the quadratic function curve is the yaw error angle in the wind speed interval that obeys the KS normal distribution;

[0017] For the wind speed interval that obeys the Jarque-Bera skewed distribution, the number of valid data points in the wind speed interval that obeys the Jarque-Bera skewed distribution is used as the weight, and the average power and wind direction of each sub-interval of the wind speed interval that obeys the Jarque-Bera skewed distribution are fitted with a trinomial to obtain a cubic function curve describing the change of power with wind direction;

[0018] If the vertex of the cubic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the Jarque-Bera skewed distribution, and the abscissa of the vertex of the cubic function curve is the yaw error angle in the wind speed interval that obeys the Jarque-Bera skewed distribution;

[0019] If there are wind speed intervals N with yaw error angles in the unit * Exceeds 70% of the number N of all wind speed intervals of the unit, and N * The number of wind speed intervals with yaw error angle within the range of N°±2° More than N* 90% and N° is greater than 5°, then the yaw error angle of the wind turbine is N°, where N° is N * The mean value of the yaw error angle in the wind speed interval.

[0020] Further, the SCADA data is preprocessed to obtain N wind speed intervals, including:

[0021] Eliminate the data in the initial wind turbine SCADA data, where the wind turbine working mode does not meet the normal power generation mode, the blade pitch angle is not in the range of [-1°, 1°], the wind turbine active output is less than or equal to 20kW, the wind turbine is not power-limited, and the 60s average wind speed is less than the cut-in wind speed and the 60s average wind speed is greater than the rated wind speed, to obtain a cleaned data set;

[0022] Performing wind speed interval division processing on the cleaning data set to obtain N wind speed intervals to be processed;

[0023] The wind speed outlier data in each wind speed interval to be processed are eliminated to obtain N wind speed intervals.

[0024] Furthermore, the wind speed interval division process is performed on the cleaning data set to obtain N wind speed intervals to be processed, including:

[0025] Get the preset interval length, cut-in wind speed and rated wind speed;

[0026] The cut-in wind speed is used as the starting wind speed, the rated wind speed is used as the cut-off wind speed, and the cleaning data set is divided into wind speed intervals based on the preset interval length to obtain N wind speed intervals to be processed.

[0027] Furthermore, a DBSCAN clustering algorithm, a density-based spatial clustering method with noise, is used to remove wind speed outlier data in each wind speed interval to be processed, and N wind speed intervals are obtained.

[0028] Furthermore, each wind speed interval is divided into yaw angle intervals, and each wind speed interval is respectively divided into M sub-intervals, including:

[0029] Obtaining a preset yaw angle interval length, a preset starting yaw angle, and a preset ending yaw angle for each wind speed interval;

[0030] The data set in each wind speed interval is divided into yaw angle intervals based on a preset yaw angle interval length, a preset starting yaw angle and a preset ending yaw angle, and each wind speed interval is divided into M sub-intervals.

[0031] Furthermore, the determination coefficient of the fitting results is calculated using the following formula:

[0032]

[0033] Among them, R 2 represents the coefficient of determination of the fitting results, y i represents the average power in the i-th wind direction interval, represents the fitted value of the average power in the i-th wind direction interval, It represents the average value of the average power in n wind direction intervals.

[0034] A second aspect of this embodiment provides a wind turbine yaw error calculation system based on goodness of fit, the system comprising:

[0035] SCADA data acquisition module: obtain SCADA data of wind turbines;

[0036] Data preprocessing module: preprocess the SCADA data to obtain N wind speed intervals;

[0037] Distribution detection module: Perform KS normal distribution detection and Jarque-Bera skewed distribution hypothesis detection on the power data in each wind speed range, and obtain wind speed ranges that obey KS normal distribution, wind speed ranges that obey Jarque-Bera skewed distribution, and / or wind speed ranges that do not conform to standard distribution;

[0038] Yaw angle interval division module: divide each wind speed interval into yaw angle intervals, and each wind speed interval is divided into M sub-intervals;

[0039] Average power calculation module: calculates the average power of M sub-intervals in each wind speed interval, and obtains M average power data sets in each wind speed interval;

[0040] Power with wind direction fitting module: For the wind speed interval that obeys the KS normal distribution, the number of valid data points in the wind speed interval that obeys the KS normal distribution is used as the weight, and the average power and wind direction of each sub-interval of the wind speed interval that obeys the KS normal distribution are fitted with a binomial, and a quadratic function curve describing the change of power with wind direction is obtained;

[0041] If the vertex of the quadratic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the KS normal distribution, and the abscissa of the vertex of the quadratic function curve is the yaw error angle in the wind speed interval that obeys the KS normal distribution;

[0042] For the wind speed interval that obeys the Jarque-Bera skewed distribution, the number of valid data points in the wind speed interval that obeys the Jarque-Bera skewed distribution is used as the weight, and the average power and wind direction of each sub-interval of the wind speed interval that obeys the Jarque-Bera skewed distribution are fitted with a trinomial to obtain a cubic function curve describing the change of power with wind direction;

[0043] If the vertex of the cubic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the Jarque-Bera skewed distribution, and the abscissa of the vertex of the cubic function curve is the yaw error angle in the wind speed interval that obeys the Jarque-Bera skewed distribution;

[0044] Yaw error angle calculation module: If there are N wind speed intervals with yaw error angles in the unit * Exceeds 70% of the number N of all wind speed intervals of the unit, and N * The number of wind speed intervals with yaw error angle within the range of N°±2° More than N * 90% and N° is greater than 5°, then the yaw error angle of the wind turbine is N°, where N° is N * The mean value of the yaw error angle in the wind speed interval.

[0045] A third aspect of this embodiment provides a terminal, including a processor, an input device, an output device and a memory, wherein the processor, input device, output device and memory are interconnected, wherein the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute any method described in the first aspect of this embodiment.

[0046] A fourth aspect of this embodiment provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor executes the method as described in any one of the first aspects of this embodiment.

[0047] It can be seen from the above technical solution that the beneficial technical effects of the present invention are as follows:

[0048] 1. The present invention strictly preprocesses the SCADA data to eliminate data that do not meet the requirements, such as data that do not meet the normal power generation conditions, abnormal blade pitch angles, too low power, abnormal wind speed, etc., to ensure the accuracy of subsequent analysis. According to the distribution characteristics of wind speed data, KS normal distribution detection and Jarque-Bera skewed distribution hypothesis detection are respectively adopted, and appropriate fitting methods (binomial or trinomial fitting) are selected for wind speed intervals with different distribution characteristics, thereby more accurately describing the relationship between power and wind direction. By calculating the determination coefficient of the fitting result and setting strict judgment conditions (the determination coefficient is greater than 0.9 and the vertex is within the preset wind direction range), the reliability of yaw error calculation is further improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following is a brief introduction to the drawings required for the specific embodiments or the prior art description. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, the elements or parts are not necessarily drawn according to the actual scale.

[0050] Figure 1 This is a flow chart of a method according to an embodiment of the present invention;

[0051] Figure 2 This is a flow chart of data preprocessing according to an embodiment of the present invention;

[0052] Figure 3 This is a cubic fitting curve diagram of an embodiment of the present invention;

[0053] Figure 4 A schematic diagram of a system according to an embodiment of the present invention;

[0054] Figure 5 Schematic diagram of a terminal according to an embodiment of the present invention. DETAILED DESCRIPTION

[0055] The following embodiments of the technical solution of the present invention are described in detail in conjunction with the accompanying drawings. The following embodiments are only used to more clearly illustrate the technical solution of the present invention, and are therefore only used as examples, and cannot be used to limit the protection scope of the present invention.

[0056] It should be noted that, unless otherwise specified, the technical terms or scientific terms used in this application should have the common meanings understood by those skilled in the art to which the present invention belongs.

[0057] Example

[0058] This embodiment provides a method for calculating the yaw error of a wind turbine based on goodness of fit. Figure 1 As shown, the method includes:

[0059] Obtain data acquisition and monitoring control system data SCADA data of wind turbines;

[0060] Preprocessing the SCADA data to obtain N wind speed intervals;

[0061] Perform KS normal distribution detection and Jarque-Bera skewed distribution hypothesis detection on the power data in each wind speed interval, and obtain wind speed intervals that obey KS normal distribution, wind speed intervals that obey Jarque-Bera skewed distribution, and / or wind speed intervals that do not conform to standard distribution;

[0062] Each wind speed interval is divided into yaw angle intervals, and each wind speed interval is divided into M sub-intervals;

[0063] Calculate the average power of M sub-intervals in each wind speed interval, and obtain M average power data for each wind speed interval;

[0064] For the wind speed interval that obeys the KS normal distribution, the number of valid data points in the wind speed interval that obeys the KS normal distribution is used as the weight, and the average power and wind direction of each sub-interval of the wind speed interval that obeys the KS normal distribution are fitted with a binomial, and a quadratic function curve describing the change of power with wind direction is obtained;

[0065] If the vertex of the quadratic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the KS normal distribution, and the abscissa of the vertex of the quadratic function curve is the yaw error angle in the wind speed interval that obeys the KS normal distribution;

[0066] For the wind speed interval that obeys the Jarque-Bera skewed distribution, the number of valid data points in the wind speed interval that obeys the Jarque-Bera skewed distribution is used as the weight, and the average power and wind direction of each sub-interval of the wind speed interval that obeys the Jarque-Bera skewed distribution are fitted with a trinomial to obtain a cubic function curve describing the change of power with wind direction;

[0067] If the vertex of the cubic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the Jarque-Bera skewed distribution, and the abscissa of the vertex of the cubic function curve is the yaw error angle in the wind speed interval that obeys the Jarque-Bera skewed distribution;

[0068] If there are wind speed intervals N with yaw error angles in the unit * Exceeds 70% of the number N of all wind speed intervals of the unit, and N * The number of wind speed intervals with yaw error angle within the range of N°±2° More than N * 90% and N° is greater than 5°, then the yaw error angle of the wind turbine is N°, where N° is N * The mean value of the yaw error angle in the wind speed interval.

[0069] In one embodiment, after acquiring the SCADA data, the raw data needs to be preprocessed to eliminate interference of other factors on the power generation;

[0070] Table 1 Parameter names and their detailed information

[0071] Parameter name More Information Working Mode Normal power generation mode of wind turbine Blade pitch angle Full propeller power generation state Active Power The wind turbine has power output status 60s average wind speed Cut-in wind speed and rated wind speed Power-limited operation status Wind turbines are not limited in power

[0072] The SCADA data is preprocessed to obtain N wind speed intervals, such as Figure 2 As shown, including:

[0073] Eliminate the data in the initial wind turbine SCADA data, where the wind turbine working mode does not meet the normal power generation mode, the blade pitch angle is not in the range of [-1°, 1°], the wind turbine active output is less than or equal to 20kW, the wind turbine is not power-limited, and the 60s average wind speed is less than the cut-in wind speed and the 60s average wind speed is greater than the rated wind speed, to obtain a cleaned data set;

[0074] The cleaning data set is divided into wind speed intervals to obtain N wind speed intervals to be processed. In this embodiment, the preset interval length is 0.5 m / s, and the cut-in wind speed is used as the starting wind speed and the rated wind speed is used as the cut-off wind speed to divide the data into N different wind speed intervals (wherein the interval length and the starting and cutting-off wind speeds can be modified according to the actual test feedback results of different wind farms).

[0075] The wind speed outlier data in each wind speed interval to be processed is eliminated to obtain N wind speed intervals; in this embodiment, the DBSCAN clustering algorithm, a density-based spatial clustering method with noise, is used to eliminate the wind speed outlier data in each wind speed interval to be processed to obtain N wind speed intervals;

[0076] Specifically, the DBSCAN clustering algorithm is used to remove wind speed outlier data in each wind speed interval to be processed, including: first determine € (neighborhood radius) and MinPts (minimum number of points), and for each point in each wind speed interval, calculate the number of points in its e-neighborhood. If the number of points is greater than or equal to MinPts, the point is marked as a core point, and a new cluster is formed. For each core point, all points in its e-neighborhood are found and added to the same cluster. This process is then recursively repeated for the newly added core points until no new points can be added to the cluster. The remaining points that are not assigned to any cluster are marked as noise points, and the wind speed data corresponding to the noise points are removed, and the remaining data is retained.

[0077] In one embodiment, a KS normal distribution test and a Jarque-Bera skewed distribution hypothesis test are performed on the power data in each wind speed interval to obtain a wind speed interval that obeys the KS normal distribution, a wind speed interval that obeys the Jarque-Bera skewed distribution, and / or a wind speed interval that does not conform to the standard distribution;

[0078] Specifically, the power data in each wind speed range are tested for KS normal distribution and Jarque-Bera skewed distribution hypothesis. They are divided into three situations: obeying normal distribution, obeying skewed distribution, and not obeying any of the distributions. Different yaw error angle calculation methods are adopted according to different situations.

[0079] Perform KS normal distribution test on wind speed range:

[0080] (1) Calculate the test distribution function (EDF):

[0081] 1. Sort data: Sort the interval power data in ascending order;

[0082] 2. Reassign the sequence number: For the i-th data after sorting (i.e., the power with the i-th smallest order of magnitude), its sequence number is recorded as i;

[0083] 3. Calculate the empirical distribution function EDF:

[0084] F(i)=(i+1) / n

[0085] Wherein, n is the total number of data points (i.e. the total number of power points in the wind speed range).

[0086] (2) Calculate the cumulative distribution function (CDF) of the standard normal distribution:

[0087]

[0088] in, is the error function erf(x);

[0089] in,

[0090] (3) Calculate fabs(i) = |F(i) - CDF(i)| and calculate D = max{fabs(i)}. If D < α, the wind speed data in this wind speed interval satisfies the normal distribution, otherwise, it does not, where α is the significance level.

[0091] Test the Jarque-Bera skewed distribution hypothesis for the wind speed range:

[0092] (1) Jarque-Bera statistic

[0093] Among them, n is the wind speed data capacity of each wind speed interval, S is the sample skewness, and K is the sample kurtosis; among them, the sample skewness S is one of the key factors to determine whether the distribution is skewed;

[0094] (2) If Then the null hypothesis is rejected, that is, there is evidence that the sample data does not follow a normal distribution. At this point, we can further observe the value of skewness S to determine whether it is a skewed distribution. 2 represents the chi-square distribution, so represents the significance level α (here 0.05), the chi-square test critical value with 2 degrees of freedom, which is a constant after the significance level and freedom are determined. 2 Chi-square distribution table obtained);

[0095] (3) After rejecting the null hypothesis, if S>0, the sample data may be right-skewed distribution, the data is concentrated on the left side, and the probability of extreme values ​​appearing on the right side is relatively high; on the contrary, if S<0, the sample data may be left-skewed distribution, the data is concentrated on the right side, and the probability of extreme values ​​appearing on the left side is relatively high.

[0096] In one embodiment, each wind speed interval is divided into yaw angle intervals, and each wind speed interval is respectively divided into M sub-intervals;

[0097] Calculate the average power of M sub-intervals in each wind speed interval, and obtain M average power data for each wind speed interval;

[0098] Specifically, the data sets of each wind speed interval are divided into 32 subsets with 1 degree as the interval length, -16 degrees as the starting yaw angle, and 16 degrees as the ending yaw angle, and the average power and the number of valid data points in each subset are calculated respectively.

[0099] In one embodiment, for a wind speed interval that obeys a KS normal distribution, the number of valid data points in the wind speed interval that obeys a KS normal distribution is used as a weight, and a binomial fitting is performed on the average power and wind direction of each sub-interval of the wind speed interval that obeys a KS normal distribution to obtain a quadratic function curve describing the change of power with wind direction;

[0100] If the vertex of the quadratic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the KS normal distribution, and the abscissa of the vertex of the quadratic function curve is the yaw error angle in the wind speed interval that obeys the KS normal distribution;

[0101] Specifically, for the calculation of the maximum power of the yaw angle in the wind speed range that obeys the normal distribution: if the power scatter points in the wind speed range obey the normal distribution after inspection, it is considered that in the wind speed range, the power is normally distributed with the wind direction, which means that in the wind speed range, there is a more obvious vertex of power with wind direction. The vertex of the normal distribution is the maximum power position in the wind speed range, and the corresponding wind direction value is the yaw angle at the maximum power. Since the normal distribution is symmetrical and closer to the waveform of the quadratic function, the average power and the number of valid data points in each subset are weighted with the number of valid data points as the weight, and a weighted binomial fit is performed, and the determination coefficient (R2_score) of the fitting result is used as an indicator to judge the quality of the fitting result:

[0102]

[0103] Among them, R 2 represents the coefficient of determination of the fitting results, y i represents the average power in the i-th wind direction interval, represents the fitted value of the average power in the i-th wind direction interval, It represents the average value of the average power in n wind direction intervals, and the range of R2_score is between [0, 1];

[0104] If the R2_score calculated in this wind speed range is greater than 0.9, and the vertex of the fitted quadratic curve is within the wind direction range of [-16, 16], it is considered that there is a significant yaw error angle in this wind speed range, and the horizontal coordinate (wind direction) of the vertex of the quadratic fitting curve is the yaw error angle of the wind speed range that obeys the KS normal distribution.

[0105] In one embodiment, for a wind speed interval that obeys the Jarque-Bera skewed distribution, the number of valid data points in the wind speed interval that obeys the Jarque-Bera skewed distribution is used as a weight, and a trinomial fitting is performed on the average power and wind direction of each sub-interval of the wind speed interval that obeys the Jarque-Bera skewed distribution to obtain a cubic function curve describing the change of power with wind direction;

[0106] If the vertex of the cubic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the Jarque-Bera skewed distribution, and the abscissa of the vertex of the cubic function curve is the yaw error angle in the wind speed interval that obeys the Jarque-Bera skewed distribution;

[0107] Specifically, for the calculation of the maximum power at the yaw angle in the wind speed interval that obeys the skewed distribution: if the power scatter points in the wind speed interval obey the skewed distribution after inspection, it is considered that in the wind speed interval, the power is skewed with the wind direction, which means that in the wind speed interval, there is a more obvious vertex for the power with the wind direction. The vertex of the distribution function is the maximum power position in the wind speed interval, and the corresponding wind direction value is the yaw angle at the maximum power. Since the skewed distribution is not a symmetrical distribution and is closer to the waveform of a cubic function, a weighted trinomial fitting is performed on the average power and the number of valid data points in each subset, with the number of valid data points as the weight. Similarly, the determination coefficient (R2_score) of the fitting result is used as an indicator to judge the quality of the fitting result:

[0108]

[0109] If the R2_score calculated in this wind speed range is greater than 0.9, and the vertex of the cubic curve is in the range of [-16, 16], it is considered that there is a significant yaw error angle in this wind speed range, and the abscissa (wind direction) of the vertex of the cubic fitting curve is the yaw error angle in the wind speed range that obeys the Jarque-Bera skewed distribution. Figure 3 The figure shows the fitting of the average power of the 2# unit in the wind speed range of 3.5-4. Since the original power scatter points obey the skewed distribution, the model selects the cubic fitting. The horizontal coordinate corresponding to the vertex value of the cubic curve is the yaw error angle in this wind speed range.

[0110] In one embodiment, the yaw angle of a wind speed interval that does not obey any distribution is calculated: if the power in a certain wind speed interval does not significantly obey the normal distribution or the skewed distribution, it is considered that there is no significant yaw error angle in the wind speed interval.

[0111] In one embodiment, determining whether the unit has a yaw to wind error angle;

[0112] The number of wind speed intervals with yaw error angles in the computer group N * ;

[0113] Judge N * Whether it exceeds 70% of the number N of all wind speed intervals of the unit;

[0114] If N * >0.7*N, then calculate N * The mean value of the effective yaw error angles N°;

[0115] If the effective yaw error angle falls within the range of N°±2° If N°>5°, the unit is judged to have a significant yaw error angle, and the yaw error angle is N°, and the error range is N°±σ Y , σY is the standard deviation of the effective yaw error angle.

[0116] In one embodiment, the reliability of the yaw to wind error angle is calculated as:

[0117] The determination coefficient (R2_score) of the average fitting result of the effective yaw error angle is used as the reliability of the wind turbine yaw to wind error angle.

[0118] In one embodiment, the yaw error angle, error range and credibility of some units calculated based on the method described above are shown in Table 2;

[0119] Table 2 is the final results of the wind deviation analysis of some units

[0120] Unit No. Yaw error angle Error margin Credibility 1 8.75 ±3.50 0.91 2 8.17 ±4.80 0.80 3 11.50 ±6.54 0.71

[0121] like Figure 4 As shown, this embodiment provides a wind turbine yaw error calculation system based on goodness of fit, the system comprising:

[0122] SCADA data acquisition module 101: acquires SCADA data of wind turbines;

[0123] Data preprocessing module 102: preprocessing the SCADA data to obtain N wind speed intervals;

[0124] Distribution detection module 103: Perform KS normal distribution detection and Jarque-Bera skewed distribution hypothesis detection on the power data in each wind speed interval, and obtain wind speed intervals that obey KS normal distribution, wind speed intervals that obey Jarque-Bera skewed distribution, and / or wind speed intervals that do not conform to standard distribution;

[0125] The yaw angle interval division module 104 divides each wind speed interval into yaw angle intervals, and each wind speed interval is divided into M sub-intervals;

[0126] Average power calculation module 105: calculates the average power of M sub-intervals in each wind speed interval, and obtains M average power data sets in each wind speed interval;

[0127] Power with wind direction fitting module 106: for the wind speed interval that obeys the KS normal distribution, using the number of valid data points in the wind speed interval that obeys the KS normal distribution as a weight, performing binomial fitting on the average power and wind direction of each sub-interval of the wind speed interval that obeys the KS normal distribution, and obtaining a quadratic function curve describing the change of power with wind direction;

[0128] If the vertex of the quadratic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the KS normal distribution, and the abscissa of the vertex of the quadratic function curve is the yaw error angle in the wind speed interval that obeys the KS normal distribution;

[0129] For the wind speed interval that obeys the Jarque-Bera skewed distribution, the number of valid data points in the wind speed interval that obeys the Jarque-Bera skewed distribution is used as the weight, and the average power and wind direction of each sub-interval of the wind speed interval that obeys the Jarque-Bera skewed distribution are fitted with a trinomial to obtain a cubic function curve describing the change of power with wind direction;

[0130] If the vertex of the cubic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the Jarque-Bera skewed distribution, and the abscissa of the vertex of the cubic function curve is the yaw error angle in the wind speed interval that obeys the Jarque-Bera skewed distribution;

[0131] Yaw error angle calculation module 107: If there are wind speed intervals N with yaw error angles in the unit * Exceeds 70% of the number N of all wind speed intervals of the unit, and N * The number of wind speed intervals with yaw error angle within the range of N°±2° More than N * 90% and N° is greater than 5°, then the yaw error angle of the wind turbine is N°, where N° is N * The mean value of the yaw error angle in the wind speed interval.

[0132] like Figure 5 As shown, this embodiment provides a terminal, including a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, and the computer program includes program instructions, and the processor is configured to call the program instructions to execute part or all of the steps described in a method for calculating the yaw wind error of a wind turbine based on goodness of fit provided in this embodiment.

[0133] This embodiment also provides a computer-readable storage medium, which stores a computer program. The computer program includes program instructions. When the program instructions are executed by a processor, the processor executes part or all of the steps described in a method for calculating the yaw wind error of a wind turbine based on goodness of fit provided in this embodiment.

[0134] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein by equivalents. These modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention, and they should all be included in the scope of the claims and specification of the present invention.

Claims

1. A method for calculating the yaw error of a wind turbine based on goodness of fit, characterized in that: include: Obtain SCADA data from wind turbines; Preprocessing the SCADA data to obtain N wind speed intervals; Perform KS normal distribution detection and Jarque-Bera skewed distribution hypothesis detection on the power data in each wind speed interval, and obtain wind speed intervals that obey KS normal distribution, wind speed intervals that obey Jarque-Bera skewed distribution, and / or wind speed intervals that do not conform to standard distribution; Each wind speed interval is divided into yaw angle intervals, and each wind speed interval is divided into M sub-intervals; Calculate the average power of M sub-intervals in each wind speed interval, and obtain M average power data for each wind speed interval; For the wind speed interval that obeys the KS normal distribution, the number of valid data points in the wind speed interval that obeys the KS normal distribution is used as the weight, and the average power and wind direction of each sub-interval of the wind speed interval that obeys the KS normal distribution are fitted with a binomial, and a quadratic function curve describing the change of power with wind direction is obtained; If the vertex of the quadratic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the KS normal distribution, and the abscissa of the vertex of the quadratic function curve is the yaw error angle in the wind speed interval that obeys the KS normal distribution; For the wind speed interval that obeys the Jarque-Bera skewed distribution, the number of valid data points in the wind speed interval that obeys the Jarque-Bera skewed distribution is used as the weight, and the average power and wind direction of each sub-interval of the wind speed interval that obeys the Jarque-Bera skewed distribution are fitted with a trinomial to obtain a cubic function curve describing the change of power with wind direction; If the vertex of the cubic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the Jarque-Bera skewed distribution, and the abscissa of the vertex of the cubic function curve is the yaw error angle in the wind speed interval that obeys the Jarque-Bera skewed distribution; If there are wind speed intervals N with yaw error angles in the unit * Exceeds 70% of the number N of all wind speed intervals of the unit, and N * The number of wind speed intervals with yaw error angle within the range of N°±2° More than N * 90% and N° is greater than 5°, then the yaw error angle of the wind turbine is N°, where N° is N * The mean value of the yaw error angle in the wind speed interval.

2. The method for calculating the yaw error of a wind turbine generator system based on goodness of fit according to claim 1, characterized in that: The SCADA data is preprocessed to obtain N wind speed intervals, including: Eliminate the data in the initial wind turbine SCADA data, where the wind turbine working mode does not meet the normal power generation mode, the blade pitch angle is not in the range of [-1°, 1°], the wind turbine active output is less than or equal to 20kW, the wind turbine is not power-limited, and the 60s average wind speed is less than the cut-in wind speed and the 60s average wind speed is greater than the rated wind speed, to obtain a cleaned data set; Performing wind speed interval division processing on the cleaning data set to obtain N wind speed intervals to be processed; The wind speed outlier data in each wind speed interval to be processed are eliminated to obtain N wind speed intervals.

3. The method for calculating the yaw error of a wind turbine generator system based on goodness of fit according to claim 2, characterized in that: The wind speed interval division process is performed on the cleaning data set to obtain N wind speed intervals to be processed, including: Get the preset interval length, cut-in wind speed and rated wind speed; The cut-in wind speed is used as the starting wind speed, the rated wind speed is used as the cut-off wind speed, and the cleaning data set is divided into wind speed intervals based on the preset interval length to obtain N wind speed intervals to be processed.

4. The method for calculating the yaw error of a wind turbine generator system based on goodness of fit according to claim 3, characterized in that: The DBSCAN clustering algorithm, a density-based spatial clustering method with noise, is used to remove wind speed outlier data in each wind speed interval to be processed, and N wind speed intervals are obtained.

5. The method for calculating the yaw error of a wind turbine generator system based on goodness of fit according to claim 1, characterized in that: The yaw angle interval is divided into each wind speed interval, and each wind speed interval is respectively obtained into M sub-intervals, including: Obtaining a preset yaw angle interval length, a preset starting yaw angle, and a preset ending yaw angle for each wind speed interval; The data set in each wind speed interval is divided into yaw angle intervals based on a preset yaw angle interval length, a preset starting yaw angle and a preset ending yaw angle, and each wind speed interval is divided into M sub-intervals.

6. The method for calculating the yaw error of a wind turbine generator system based on goodness of fit according to claim 1, characterized in that: The determination coefficient of the fitting results is calculated using the following formula: Among them, R 2 represents the coefficient of determination of the fitting result, y i represents the average power in the i-th wind direction interval, represents the fitted value of the average power in the i-th wind direction interval, It represents the average value of the average power in n wind direction intervals.

7. A wind turbine yaw error calculation system based on goodness of fit, characterized in that: The system comprises: SCADA data acquisition module: obtain SCADA data of wind turbines; Data preprocessing module: preprocess the SCADA data to obtain N wind speed intervals; Distribution detection module: Perform KS normal distribution detection and Jarque-Bera skewed distribution hypothesis detection on the power data in each wind speed range, and obtain wind speed ranges that obey KS normal distribution, wind speed ranges that obey Jarque-Bera skewed distribution, and / or wind speed ranges that do not conform to standard distribution; Yaw angle interval division module: divide each wind speed interval into yaw angle intervals, and each wind speed interval is divided into M sub-intervals; Average power calculation module: calculates the average power of M sub-intervals in each wind speed interval, and obtains M average power data sets in each wind speed interval; Power with wind direction fitting module: For the wind speed interval that obeys the KS normal distribution, the number of valid data points in the wind speed interval that obeys the KS normal distribution is used as the weight, and the average power and wind direction of each sub-interval of the wind speed interval that obeys the KS normal distribution are fitted with a binomial, and a quadratic function curve describing the change of power with wind direction is obtained; If the vertex of the quadratic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the KS normal distribution, and the abscissa of the vertex of the quadratic function curve is the yaw error angle in the wind speed interval that obeys the KS normal distribution; For the wind speed interval that obeys the Jarque-Bera skewed distribution, the number of valid data points in the wind speed interval that obeys the Jarque-Bera skewed distribution is used as the weight, and the average power and wind direction of each sub-interval of the wind speed interval that obeys the Jarque-Bera skewed distribution are fitted with a trinomial to obtain a cubic function curve describing the change of power with wind direction; If the vertex of the cubic function curve is within the preset wind direction range, and the determination coefficient of the fitting result is greater than 0.9, then the yaw error angle exists in the wind speed interval that obeys the Jarque-Bera skewed distribution, and the abscissa of the vertex of the cubic function curve is the yaw error angle in the wind speed interval that obeys the Jarque-Bera skewed distribution; Yaw error angle calculation module: If there are N wind speed intervals with yaw error angles in the unit * Exceeds 70% of the number N of all wind speed intervals of the unit, and N * The number of wind speed intervals with yaw error angle within the range of N°±2° More than N * 90% and N° is greater than 5°, then the yaw error angle of the wind turbine is N°, where N° is N * The mean value of the yaw error angle in the wind speed interval.

8. A terminal, characterized in that: The method comprises a processor, an input device, an output device and a memory, wherein the processor, the input device, the output device and the memory are interconnected, wherein the memory is used to store a computer program, the computer program comprises program instructions, and the processor is configured to call the program instructions to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by a processor, the processor is caused to perform the method according to any one of claims 1 to 6.

Images