Wind turbine generator static yaw error diagnosis method and system

Abstract

The invention provides a wind turbine generator static yaw error diagnosis method and system, and belongs to the technical field of wind turbine generator control. The method comprises the steps that according to preset variable characteristics of historical operation data of a target wind turbine generator, the historical operation data are subjected to warehouse dividing processing, and multiple first warehouse dividing intervals and historical operation data of the first warehouse dividing intervals are obtained; each first sub-warehouse interval comprises a plurality of second sub-warehouse intervals; smoothing the historical operation data of each second sub-warehouse interval, and performing yaw power curve fitting on the smoothed historical operation data of each second sub-warehouse interval to obtain a yaw power curve corresponding to each second sub-warehouse interval; based on the yaw power curve of each second sub-bin interval, static yaw error data of each first sub-bin interval is determined; and the static yaw error data of all the first sub-bin intervals are integrated to obtain final static yaw error data, and therefore the yaw angle interval where the static yaw error is located and the specific error can be accurately recognized.

Description

Technical Field

[0001] The present invention relates to the technical field of wind turbine control, and in particular to a method for diagnosing a static yaw error of a wind turbine, a system for diagnosing a static yaw error of a wind turbine, a machine-readable storage medium and an electronic device. Background Art

[0002] The yaw control system of a wind turbine is a key system to ensure that the wind rotor is always aligned with the wind direction to maximize wind energy capture. The yaw control system measures the incoming wind direction through the wind vane on the top of the nacelle. The information on the incoming wind direction reflects the position of the wind relative to the central axis of the wind turbine nacelle. The yaw control system uses the information on the incoming wind direction to trigger the yaw action and adjust the direction of the nacelle and rotor to face the wind direction, thereby ensuring maximum power extraction.

[0003] The yaw error of a wind turbine refers to the angle between the wind direction measured by the wind vane and the axis of the nacelle. Ideally, the zero point of the wind vane sensor should coincide with the axis of the wind rotor, and the actual yaw error calculated value of the wind vane should be the angle between the wind direction and the axis of the nacelle. However, in the actual measurement process, there are two major factors that will cause the measurement accuracy of the above variables: (1) the human factors of the operation and maintenance personnel in calibrating the wind vane, as well as equipment aging, line signal transmission errors, etc.; (2) the wind vane is usually installed at the rear of the nacelle, and the blade wake will affect the measurement results of the wind vane. Therefore, the existence of these factors leads to a deviation between the actual yaw error and the measured value, which is defined as the static yaw error. The static yaw error of a wind turbine seriously affects the power generation performance of the wind turbine, and the existing wind turbine static yaw error diagnosis method has problems such as large diagnostic error, low accuracy and reliance on expensive high-precision sensors.

[0004] Therefore, how to accurately identify the yaw angle range and specific error of the static yaw error is a problem that needs to be solved urgently. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a method and system for diagnosing static yaw errors of wind turbines, so as to at least solve the above-mentioned problem of how to accurately identify the yaw angle range and specific error of the static yaw error.

[0006] In order to achieve the above object, the present invention provides a first aspect of a wind turbine generator static yaw error diagnosis method, comprising: According to the preset variable characteristics of the historical operation data of the target wind turbine group obtained in advance, the historical operation data of the target wind turbine group is processed by binning to obtain a plurality of first binning intervals and historical operation data of each first binning interval; wherein each first binning interval includes a plurality of second binning intervals; After smoothing the historical operating data of each second sub-bin interval, a yaw power curve is fitted on the smoothed historical operating data of each second sub-bin interval to obtain a yaw power curve corresponding to each second sub-bin interval; Based on the yaw power curves of each second sub-bin interval under each first sub-bin interval, respectively determine the static yaw error data of each first sub-bin interval; The static yaw error data of each first sub-bin interval is integrated to obtain the final static yaw error data corresponding to the target wind turbine.

[0007] Optionally, before binning the historical operation data of the target wind turbine generator set, the method further includes: Preprocess the historical operation data of the target wind turbine, including: Correct the historical operation data of the target wind turbine; According to the preset data screening rules and the operating data of the target wind turbine generator set, the historical operating data of the target wind turbine generator set is preliminarily screened to obtain the historical operating data after the preliminarily screening; Clean the historical operation data after preliminary screening.

[0008] Optionally, the preset variable characteristics of the historical operation data of the target wind turbine generator set include the yaw error angle of the target wind turbine generator set, the output power of the wind turbine generator set and the wind speed; The above binning process of the historical operation data of the target wind turbine generator set includes: According to the wind speed, the historical operation data of the target wind turbine is processed into wind speed bins to obtain a plurality of first bin intervals; According to different yaw error angles corresponding to historical operation data of the target wind turbine generator set, yaw error angle binning processing is performed on the historical operation data of each first binning interval to obtain multiple second binning intervals corresponding to each first binning interval.

[0009] Optionally, the above-mentioned rules for smoothing the historical operation data of each second sub-warehouse interval include: The historical operation data of each second sub-warehouse interval is smoothed based on the XGBoost model optimized by the NRBO algorithm; Among them, the optimization rules of the XGBoost model include: The NRBO algorithm is set in the output layer of the XGBoost model to optimize the output results of the XGBoost model using the NRBO algorithm.

[0010] Optionally, the rule for fitting the yaw power curve to the smoothed historical operating data of each second bin interval includes: The Gaussian function fitting model is used to fit the yaw power curve to the historical operation data of each second compartment interval; Among them, the Gaussian function fitting model is: , f (x) represents the yaw power curve, a represents the height of the yaw power curve, b represents the mean of the yaw power curve, c represents the standard deviation of the yaw power curve, and x represents the historical operation data.

[0011] Optionally, the above-mentioned integrated static yaw error data of each first sub-bin interval is used to obtain the final static yaw error data corresponding to the target wind turbine group, including: For each first sub-bin interval, the wind speed with the highest frequency in the first sub-bin interval is used as the representative wind speed of the current first sub-bin interval; Based on the representative wind speed of each first sub-bin interval, calculate the interval weight of each first sub-bin interval; Based on the interval weight of each first sub-bin interval and the corresponding occurrence frequency of the representative wind speed, the comprehensive wind speed weight of each first sub-bin interval is calculated; Based on the comprehensive wind speed weight of each first sub-bin interval, the static yaw error data of each first sub-bin interval is weighted to obtain the final static yaw error data corresponding to the target wind turbine group.

[0012] Optionally, the calculation formula of the above interval weight is: ; The calculation formula for the comprehensive wind speed weight is: ; The calculation formula for the final static yaw error data corresponding to the target wind turbine is: ; in, is the interval weight of the first sub-warehouse interval of the i-th interval, is the frequency of occurrence of the representative wind speed in the first bin interval of the i-th bin, is the static yaw error data of the first bin interval of the i-th bin, is the comprehensive wind speed weight of the first compartment of the i-th interval, is the representative wind speed of the i-th first bin interval, α is the final static yaw error data corresponding to the target wind turbine, and N is the number of the first bin intervals.

[0013] A second aspect of the present invention provides a wind turbine static yaw error diagnosis system, comprising: A bin processing module, for binning the historical operation data of the target wind turbine generator set according to preset variable characteristics of the historical operation data of the target wind turbine generator set obtained in advance, to obtain a plurality of first bin intervals and historical operation data of each first bin interval; wherein each first bin interval includes a plurality of second bin intervals; A yaw power curve fitting module is used to perform yaw power curve fitting on the historical operating data of each second bin interval after smoothing, so as to obtain a yaw power curve corresponding to each second bin interval; A static yaw error data determination module, configured to determine the static yaw error data of each first sub-bin interval based on the yaw power curves of each second sub-bin interval under each first sub-bin interval; The data integration module is used to integrate the static yaw error data of each first sub-bin interval to obtain the final static yaw error data corresponding to the target wind turbine group.

[0014] In a third aspect of the present invention, a machine-readable storage medium is provided, on which instructions are stored. When the instructions are executed by a processor, the processor is configured to execute the above-mentioned static yaw error diagnosis method of a wind turbine.

[0015] In a fourth aspect of the present invention, an electronic device is provided, the electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the static yaw error diagnosis method for a wind turbine when executing the computer program.

[0016] Through the above technical scheme, a method and system for diagnosing static yaw error of a wind turbine is provided. According to the preset variable characteristics of the historical operation data of the target wind turbine acquired in advance, the historical operation data of the target wind turbine is processed by binning to obtain multiple first bin intervals, historical operation data of each first bin interval, multiple second bin intervals contained in each first bin interval, and historical operation data of each second bin interval. After smoothing the historical operation data of each second bin interval, the smoothed historical operation data of each second bin interval is fitted with a yaw power curve to obtain the yaw power curve corresponding to each second bin interval, so as to reflect the overall change of the yaw power data corresponding to the second bin interval through the yaw power curve. According to the yaw power curve corresponding to each second bin interval corresponding to each first bin interval, the static yaw error data of each first bin interval is determined. Thus, the static yaw error data of each first bin interval is combined to obtain the final static yaw error data corresponding to the target wind turbine, so as to achieve the purpose of accurately identifying the yaw angle interval and specific error where the static yaw error is located.

[0017] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings: Figure 1 It is a flow chart of a method for diagnosing static yaw error of a wind turbine provided by one embodiment of the present invention; Figure 2 is a schematic diagram of yaw error provided by an embodiment of the present invention; Figure 3 is a schematic diagram of a static yaw error provided by an embodiment of the present invention; Figure 4 is a flow chart of a static yaw error diagnostic algorithm provided by one embodiment of the present invention; Figure 5 It is a block diagram of a static yaw error diagnostic system for a wind turbine set provided by one embodiment of the present invention; Figure 6 It is a schematic diagram of the structure of an electronic device provided by a preferred embodiment of the present invention.

[0019] Description of Reference Numerals 10 - electronic device, 100 - processor, 101 - memory, 102 - computer program. DETAILED DESCRIPTION

[0020] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0021] Figure 1 is a flow chart of a method for diagnosing static yaw error of a wind turbine provided by an embodiment of the present invention. Figure 2 is a schematic diagram of yaw error provided by an embodiment of the present invention, Figure 3 FIG. 1 is a schematic diagram of a static yaw error provided by an embodiment of the present invention. Figure 1 , Figure 2 and Figure 3 As shown, an embodiment of the present invention provides a method for diagnosing static yaw error of a wind turbine, comprising: S110: performing bin processing on the historical operation data of the target wind turbine generator set according to preset variable characteristics of the historical operation data of the target wind turbine generator set obtained in advance, and obtaining a plurality of first bin intervals and historical operation data of each first bin interval; wherein each first bin interval includes a plurality of second bin intervals; Among them, bin processing refers to classifying the historical operation data of the target wind turbine according to the preset variable characteristics to divide it into multiple intervals.

[0022] Specifically, the SCADA historical data of the target wind turbine is obtained as the pre-acquired historical operation data of the target wind turbine, and the features required for data preprocessing in the historical operation data of the target wind turbine are selected, including wind speed, wind direction, generator active power, nacelle position angle, generator speed, etc. Preprocessing is performed based on the selected features based on the actual operation of the wind turbine and related algorithms.

[0023] Among them, after obtaining the SCADA historical data of the target wind turbine, the formula is used Calculate the yaw error angle of a wind turbine , where is the wind direction angle, is the cabin position angle.

[0024] In some implementations of this embodiment, before the historical operating data of the target wind turbine group is processed in bins, the method also includes: preprocessing the historical operating data of the target wind turbine group, including: correcting the historical operating data of the target wind turbine group; performing preliminary screening of the historical operating data of the target wind turbine group according to preset data screening rules and the operating status data of the target wind turbine group to obtain the historical operating data after preliminary screening; and cleaning the historical operating data after preliminary screening.

[0025] Specifically, data preprocessing first considers the influence of factors such as air density to correct the historical operation data, that is, to standardize the wind speed, as shown in the formula , where is the normalized wind speed, is the cabin wind speed measured by SCADA, is the average air density over 10 minutes, is the reference air density, which is 1.225 kg / m at normal pressure. 3 Among them, the air density can be expressed as a function of altitude and temperature, as shown in the formula , where ρ is the air density (kg / m 3); z is the altitude of the wind turbine (m); T is the absolute temperature of the atmosphere on the Kelvin scale (k). Secondly, the historical operation data of the target wind turbine is preliminarily screened according to the data screening rules formulated by IEC 61400 and the actual situation of the wind turbine. The preliminary screening standards are as follows: (1) power>0.1kW; (2) blade angle<20°; (3) impeller speed>7.45r / min; (4) generator speed>100r / min; (5) wind speed>3m / s; (6) fault, power abandonment, and maintenance status are eliminated. Finally, the DBSCAN clustering algorithm is used in combination with the 3σ rule to clean the historical operation data after preliminary screening. DBSCAN is a density-based clustering algorithm that performs data screening by determining the density between sample data fields.

[0026] In some implementations of this embodiment, other data processing algorithms such as random forests may be used to pre-process the historical operation data.

[0027] In some implementations of the present embodiment, the preset variable characteristics of the historical operating data of the target wind turbine group include the yaw error angle of the target wind turbine group, the output power of the wind turbine group and the wind speed; the above-mentioned binning processing of the historical operating data of the target wind turbine group includes: binning the historical operating data of the target wind turbine group according to the wind speed size to obtain multiple first binning intervals; binning the historical operating data of each first binning interval according to the different yaw error angles corresponding to the historical operating data of the target wind turbine group to obtain multiple second binning intervals corresponding to each first binning interval.

[0028] Specifically, after preprocessing the historical operation data, three variable features, namely, yaw error angle, wind turbine output power, and wind speed, are selected, and the historical operation data is processed by wind speed binning based on the preprocessed historical operation data based on the size of the wind speed, to obtain multiple wind speed bins (wind speed binning is the first binning interval). Yaw error angle binning is performed according to different yaw error angles in each wind speed bin, to obtain multiple yaw bins (yaw binning is the second binning interval).

[0029] In the above implementation process, the three variable features after preprocessing are obtained, namely the yaw error angle , Wind turbine output power and wind speed , according to the formula The wind speed is divided into different ranges. is the lower limit of wind speed in the ith interval, is the upper limit of the wind speed in the ith interval. The historical operating data in each wind speed interval is further divided into sub-intervals (i.e., the second sub-interval) according to the yaw error angle. The sub-interval range is as follows: As shown, is the lower limit of the yaw error in the jth subinterval, is the upper limit of the yaw error in the jth subinterval.

[0030] In some implementations of this embodiment, after the sub-intervals are divided, the average power of the wind turbine generator set of each data point of the historical operation data in each sub-interval is calculated as the power performance index of the sub-interval to measure the power performance in each sub-interval, as shown in Formula shown.

[0031] S120: after smoothing the historical operation data of each second sub-bin interval, perform yaw power curve fitting on the smoothed historical operation data of each second sub-bin interval to obtain a yaw power curve corresponding to each second sub-bin interval; In some implementations of the present embodiment, the above-mentioned rules for smoothing the historical operating data of each second sub-warehouse interval include: smoothing the historical operating data of each second sub-warehouse interval based on the XGBoost model optimized by the NRBO algorithm; wherein, the optimization rules of the XGBoost model include: setting the NRBO algorithm in the output layer of the XGBoost model to optimize the output results of the XGBoost model using the NRBO algorithm.

[0032] Specifically, this method smoothes the yaw bin data (i.e., the historical operation data of the second bin interval) based on the XGBoost model optimized by the NRBO algorithm, and stabilizes the yaw bin data based on an NRBO-optimized XGBoost algorithm. The specific algorithm implementation process is as follows: The Newton-Raphson-based optimizer (NRBO) uses the Newton-Raphson search rule (NRSR) to improve the exploration ability of NRBO and accelerate the convergence speed, and also introduces the trap avoidance operator (TAO) to avoid local optimal traps. The algorithm implementation process is as follows: (1) Population initialization: NRBO starts the search for the optimal solution by generating an initial random population within the boundary of candidate solutions. For a population with a given number of individuals Np, assume that the parameters to be optimized have dim dimensions. The position of the initial solution of the randomly generated population is given by ,in , , is the position of the nth individual in the jth dimension; j∈[1,dim], n∈[1,Np]; and are the lower and upper limits of the parameters to be optimized; rand is a random number between (0,1); (2) Calculate the initial fitness value: According to the set fitness function, calculate the fitness value of each individual, and select the best fitness value and the worst fitness value and their corresponding position x b and x w ; (3) Apply the NRSR rule to explore new solutions: For the nth individual in the tth iteration, NRSR is applied to explore the individual position, and the new position is expressed as , is the new position explored by applying the NRSR rule; t and n are the number of iterations and the individual sequence number, respectively; and Respectively represent random numbers between (0, 1); , , They are the three positions updated by NRBO from the current position in order to enhance the local search performance and the global search performance. The expressions are: , , , where Nr is the value obtained by applying the NRSR search rule, xb is the current best position, and Rho is a step factor that guides the population in the right direction. is the adaptive coefficient that changes with the number of iterations, which is used to avoid local optimality and reduce the amount of calculation. The corresponding calculation formula is: , , , , where randn is a random number between (0, 1), yw and yb are Two positions generated by applying the NRSR search rule results are used to further enhance the NRBO search performance; is the range of exploration, a and b represent random numbers between (0, 1), a1 and a2 represent two unequal random numbers between [1, Np]; T is the maximum number of iterations.

[0033] (3) Trap Avoidance Operation (TAO): In order to improve the quality of the solution and avoid the local optimal trap, TAO is introduced to combine the optimal position xb and the vector position obtained by NRSR. To produce solutions with enhanced quality . By comparing the (0, 1) random number rand with the DF value, the DF value is usually 0.6. The new value is: , , where and are random numbers between (-1, 1) and (-0.5, 0.5), and is a random number, using a random number Δ between (0, 1) and 0.5 for comparison. If Δ ≥ 0.5, and Assign a value of 1, otherwise calculate according to the following formula, that is, .

[0034] Among them, XGBoost is an efficient and flexible ensemble learning method that can be used for data processing, prediction, regression and classification tasks. It improves model accuracy by iteratively building a decision tree model and learning the errors of the previous model in each iteration. The core idea is to build an additive model to minimize the loss function by continuously adding trees. Specifically, the objective function of XGBoost can be expressed as: ,in, is the loss function used to measure the predicted value With the true value The difference between ;Ω is the regularization term used to control the complexity of the model; is the model of the kth tree.

[0035] In some implementations of this embodiment, the rule for fitting the yaw power curve to the historical operating data of each second bin interval after smoothing includes: fitting the yaw power curve to the historical operating data of each second bin interval using a Gaussian function fitting model; wherein the Gaussian function fitting model is: , f (x) represents the yaw power curve, a represents the height of the yaw power curve, b represents the mean of the yaw power curve, c represents the standard deviation of the yaw power curve, and x represents the historical operation data.

[0036] Specifically, after smoothing the historical operation data of each second sub-bin interval, the yaw power data is fitted based on the Gaussian function. The Gaussian function fitting can fit the yaw power data in all historical operation data as a whole, and can better reflect the overall change of the yaw power data. The optimized yaw power data is fitted with the Gaussian curve algorithm to fit the yaw power curve. After using the Gaussian function for curve fitting to fit the yaw power curve in each yaw interval, the static yaw error of each wind speed interval (i.e., the first sub-bin interval) is diagnosed according to the fitted yaw power curve.

[0037] In some implementations of this embodiment, a fitting algorithm based on machine learning, such as Gaussian process regression, may be used to fit the yaw power curve.

[0038] S130: Based on the yaw power curves of each second sub-bin interval under each first sub-bin interval, respectively determine the static yaw error data of each first sub-bin interval; Exemplarily, for each first binning interval, the yaw error data corresponding to the yaw power data that appears most frequently in the first binning interval may be selected as the static yaw error data of the current first binning interval.

[0039] S140: The static yaw error data of each first sub-bin interval is integrated to obtain final static yaw error data corresponding to the target wind turbine group.

[0040] Specifically, the method performs binning processing on the historical operation data of the target wind turbine group according to the preset variable characteristics of the historical operation data of the target wind turbine group obtained in advance, so as to obtain multiple first binning intervals, historical operation data of each first binning interval, multiple second binning intervals contained in each first binning interval, and historical operation data of each second binning interval. After smoothing the historical operation data of each second binning interval, the smoothed historical operation data of each second binning interval is fitted with a yaw power curve to obtain the yaw power curve corresponding to each second binning interval, so as to reflect the overall change of the yaw power data corresponding to the second binning interval through the yaw power curve. According to the yaw power curve corresponding to each second binning interval corresponding to each first binning interval, the static yaw error data of each first binning interval is determined. Therefore, the static yaw error data of each first binning interval is combined to obtain the final static yaw error data corresponding to the target wind turbine group, thereby achieving the purpose of accurately identifying the yaw angle interval and specific error where the static yaw error is located.

[0041] In some implementations of the present embodiment, the above-mentioned static yaw error data of each first sub-bin interval is integrated to obtain the final static yaw error data corresponding to the target wind turbine generator set, including: for each first sub-bin interval, the wind speed with the highest frequency in the first sub-bin interval is used as the representative wind speed of the current first sub-bin interval; based on the representative wind speed of each first sub-bin interval, the interval weight of each first sub-bin interval is calculated; based on the interval weight of each first sub-bin interval and the frequency of occurrence corresponding to the representative wind speed, the comprehensive wind speed weight of each first sub-bin interval is calculated; based on the comprehensive wind speed weight of each first sub-bin interval, the static yaw error data of each first sub-bin interval is weightedly processed to obtain the final static yaw error data corresponding to the target wind turbine generator set.

[0042] Specifically, the method uses a wind speed weighting method that takes into account the frequency of occurrence of wind speed to weight the static yaw error data of each wind speed interval (i.e., the first bin interval) to obtain the final static yaw error data corresponding to the target wind turbine, that is, weighted processing is performed on the static yaw error data diagnosed in each wind speed interval based on the improved wind speed weighting method. The specific algorithm establishment standard is as follows: there is a nonlinear relationship between the power of the wind turbine and the wind speed, and the power is proportional to the cube of the wind speed. The higher the wind speed, the greater the contribution. However, in actual situations, if the frequency of occurrence of wind speed in a wind speed interval is higher, it will also affect the static yaw error data of the final diagnosis. Therefore, this method considers the influence of the frequency of occurrence of wind speed in different wind speed intervals and proposes an improvement to the wind speed weighting method. This method uses the calculation formula of interval weight, the calculation formula of comprehensive wind speed weight, and the calculation formula of the final static yaw error data corresponding to the target wind turbine to calculate the final static yaw error data corresponding to the target wind turbine based on the representative yaw error (representative yaw error, i.e., static yaw error data) of different first bin intervals.

[0043] In some implementations of this embodiment, the calculation formula of the above interval weight is: ; The calculation formula for the comprehensive wind speed weight is: ; The calculation formula for the final static yaw error data corresponding to the target wind turbine is: ;in, is the interval weight of the first sub-warehouse interval of the i-th interval, is the frequency of occurrence of the representative wind speed in the first bin interval of the i-th bin, is the static yaw error data of the first bin interval of the i-th bin, is the comprehensive wind speed weight of the first compartment of the i-th interval, is the representative wind speed of the i-th first bin interval, α is the final static yaw error data corresponding to the target wind turbine, and N is the number of the first bin intervals.

[0044] In some implementations of this embodiment, the impact of environmental factors on the yaw error may also be analyzed.

[0045] Please refer to Figure 4 , Figure 4It is a flow chart of a static yaw error diagnosis algorithm provided by an embodiment of the present invention. The method first pre-processes the SCADA data (including wind speed correction, initial screening of SCADA data, and data cleaning using DBSCAN clustering and 3σ rule), then performs wind speed binning and yaw angle binning in sequence, and then stabilizes the binned yaw data based on the proposed machine learning algorithm (i.e., the XGBoost model optimized based on the NRBO algorithm), and then uses Gaussian curve fitting to build a model, and diagnoses the static yaw error in combination with the proposed improved wind speed weighting method. The method can accurately diagnose the static yaw error of the wind turbine based on the data-driven machine learning algorithm, eliminating the expensive cost of relying on high-precision sensors, and can subsequently make corresponding corrections for the problem units to improve the power generation capacity of the wind turbine. And after binning the yaw and power of each wind speed interval, in order to eliminate the influence of high-frequency noise and unsteady factors, the method proposes to optimize the XGBoost algorithm with NRBO (Newton-Raphson optimization algorithm), and use this regression algorithm to stabilize the binned data, and reasonably use the characteristics of the regression algorithm to process data. Compared with the traditional wind speed weighting method, the wind speed weighting method used in this method takes into account the frequency of wind speeds in different wind speed ranges, which is more in line with the actual situation. According to the above steps, this method can accurately diagnose the yaw static error of the wind turbine based on the machine learning algorithm, and the diagnosis results can be used for actual field equipment. By modifying the main control coefficient of the yaw control system or installing high-precision sensors, practical problems can be solved to enhance the power generation capacity of the wind turbine.

[0046] Figure 5 FIG. 1 is a block diagram of a wind turbine static yaw error diagnostic system provided by an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention provides a static yaw error diagnosis system for a wind turbine, comprising: A bin processing module, for binning the historical operation data of the target wind turbine generator set according to preset variable characteristics of the historical operation data of the target wind turbine generator set obtained in advance, to obtain a plurality of first bin intervals and historical operation data of each first bin interval; wherein each first bin interval includes a plurality of second bin intervals; A yaw power curve fitting module is used to perform yaw power curve fitting on the historical operating data of each second bin interval after smoothing, so as to obtain a yaw power curve corresponding to each second bin interval; A static yaw error data determination module, configured to determine the static yaw error data of each first sub-bin interval based on the yaw power curves of each second sub-bin interval under each first sub-bin interval; The data integration module is used to integrate the static yaw error data of each first sub-bin interval to obtain the final static yaw error data corresponding to the target wind turbine group.

[0047] Specifically, the system performs binning processing on the historical operation data of the target wind turbine group according to the preset variable characteristics of the historical operation data of the target wind turbine group obtained in advance, so as to obtain multiple first binning intervals, historical operation data of each first binning interval, multiple second binning intervals contained in each first binning interval, and historical operation data of each second binning interval. After smoothing the historical operation data of each second binning interval, the smoothed historical operation data of each second binning interval is fitted with a yaw power curve to obtain the yaw power curve corresponding to each second binning interval, so as to reflect the overall change of the yaw power data corresponding to the second binning interval through the yaw power curve. According to the yaw power curve corresponding to each second binning interval corresponding to each first binning interval, the static yaw error data of each first binning interval is determined. Therefore, the static yaw error data of each first binning interval is combined to obtain the final static yaw error data corresponding to the target wind turbine group, thereby achieving the purpose of accurately identifying the yaw angle interval and specific error where the static yaw error is located.

[0048] The embodiment of the present invention further provides a machine-readable storage medium, on which instructions are stored. When the instructions are executed by the processor 100, the processor 100 is configured to execute the above-mentioned wind turbine static yaw error diagnosis method.

[0049] Machine-readable storage media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0050] An embodiment of the present invention further provides an electronic device 10, which includes a memory 101, a processor 100, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the above-mentioned wind turbine static yaw error diagnosis method is implemented.

[0051] like Figure 6 FIG. 1 is a schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 6 As shown, the electronic device 10 of this embodiment includes: a processor 100, a memory 101, and a computer program 102 stored in the memory 101 and executable on the processor 100. When the processor 100 executes the computer program 102, the steps in the above method embodiment are implemented. Alternatively, when the processor 100 executes the computer program 102, the functions of each module / unit in the above device embodiment are implemented.

[0052] Exemplarily, the computer program 102 may be divided into one or more modules / units, one or more modules / units are stored in the memory 101, and are executed by the processor 100 to complete the present invention. One or more modules / units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program 102 in the electronic device 10. For example, the computer program 102 may be divided into a bin processing module, a yaw power curve fitting module, a static yaw error data determination module, and a data integration module.

[0053] The electronic device 10 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 10 may include, but is not limited to, a processor 100 and a memory 101. Those skilled in the art will appreciate that Figure 6 It is only an example of the electronic device 10 and does not constitute a limitation of the electronic device 10. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device may also include input and output devices, network access devices, buses, etc.

[0054] The processor 100 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.

[0055] The memory 101 may be an internal storage unit of the electronic device 10, such as a hard disk or memory of the electronic device 10. The memory 101 may also be an external storage device of the electronic device 10, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card (FlashCard), etc. equipped on the electronic device 10. Further, the memory 101 may also include both an internal storage unit of the electronic device 10 and an external storage device. The memory 101 is used to store computer programs and other programs and data required by the electronic device 10. The memory 101 may also be used to temporarily store data that has been output or is to be output.

[0056] The technicians in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0057] It should be understood by those skilled in the art that the embodiments of the present application may be provided as methods, systems, or computer program 102 products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program 102 product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0058] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program 102 products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by the computer program 102 instructions. These computer program 102 instructions can be provided to a processor 100 of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor 100 of the computer or other programmable data processing device generate instructions for implementing the processes in the flowcharts. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0059] These computer program 102 instructions may also be stored in a computer readable memory 101 that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory 101 produce an article of manufacture including an instruction device that implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0060] These computer program 102 instructions may also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for executing on the computer or other programmable device to implement the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0061] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0062] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for diagnosing static yaw error of a wind turbine, characterized in that: include: According to the preset variable characteristics of the historical operation data of the target wind turbine group obtained in advance, the historical operation data of the target wind turbine group is processed by binning to obtain a plurality of first binning intervals and historical operation data of each first binning interval; wherein each first binning interval includes a plurality of second binning intervals; After smoothing the historical operating data of each second sub-bin interval, a yaw power curve is fitted on the smoothed historical operating data of each second sub-bin interval to obtain a yaw power curve corresponding to each second sub-bin interval; Based on the yaw power curves of each second sub-bin interval under each first sub-bin interval, respectively determine the static yaw error data of each first sub-bin interval; The static yaw error data of each first sub-bin interval is integrated to obtain the final static yaw error data corresponding to the target wind turbine.

2. The wind turbine static yaw error diagnosis method according to claim 1, characterized in that: Before performing bin-by-bin processing on the historical operation data of the target wind turbine generator set, the method further includes: Preprocess the historical operation data of the target wind turbine, including: Correct the historical operation data of the target wind turbine; According to the preset data screening rules and the operating data of the target wind turbine generator set, the historical operating data of the target wind turbine generator set is preliminarily screened to obtain the historical operating data after the preliminarily screening; Clean the historical operation data after preliminary screening.

3. The method for diagnosing static yaw error of a wind turbine according to claim 1, characterized in that: The preset variable characteristics of the historical operation data of the target wind turbine generator set include the yaw error angle of the target wind turbine generator set, the output power of the wind turbine generator set and the wind speed; The binning processing of the historical operation data of the target wind turbine generator set includes: According to the wind speed, the historical operation data of the target wind turbine is processed into wind speed bins to obtain a plurality of first bin intervals; According to different yaw error angles corresponding to historical operation data of the target wind turbine generator set, yaw error angle binning processing is performed on the historical operation data of each first binning interval to obtain multiple second binning intervals corresponding to each first binning interval.

4. The method for diagnosing static yaw error of a wind turbine according to claim 1, characterized in that: The rules for smoothing the historical operation data of each second warehouse interval include: The historical operation data of each second sub-warehouse interval is smoothed based on the XGBoost model optimized by the NRBO algorithm; Among them, the optimization rules of the XGBoost model include: The NRBO algorithm is set in the output layer of the XGBoost model to optimize the output results of the XGBoost model using the NRBO algorithm.

5. The method for diagnosing static yaw error of a wind turbine according to claim 1, characterized in that: The rules for fitting the yaw power curve to the smoothed historical operating data of each second bin interval include: The Gaussian function fitting model is used to fit the yaw power curve to the historical operation data of each second compartment interval; Wherein, the Gaussian function fitting model is: , f (x) represents the yaw power curve, a represents the height of the yaw power curve, b represents the mean of the yaw power curve, c represents the standard deviation of the yaw power curve, and x represents the historical operation data.

6. The method for diagnosing static yaw error of a wind turbine according to claim 1, characterized in that: The step of synthesizing the static yaw error data of each first sub-bin interval to obtain the final static yaw error data corresponding to the target wind turbine generator set includes: For each first sub-bin interval, the wind speed with the highest frequency in the first sub-bin interval is used as the representative wind speed of the current first sub-bin interval; Based on the representative wind speed of each first sub-bin interval, calculate the interval weight of each first sub-bin interval; Based on the interval weight of each first sub-bin interval and the corresponding occurrence frequency of the representative wind speed, the comprehensive wind speed weight of each first sub-bin interval is calculated; Based on the comprehensive wind speed weight of each first sub-bin interval, the static yaw error data of each first sub-bin interval is weighted to obtain the final static yaw error data corresponding to the target wind turbine group.

7. The method for diagnosing static yaw error of a wind turbine according to claim 6, characterized in that: The calculation formula of the interval weight is: ； The calculation formula of the comprehensive wind speed weight is: ； The calculation formula for the final static yaw error data corresponding to the target wind turbine group is: ； in, is the interval weight of the first sub-warehouse interval of the i-th interval, is the frequency of occurrence of the representative wind speed in the first bin interval of the i-th bin, is the static yaw error data of the first bin interval of the i-th bin, is the comprehensive wind speed weight of the first compartment of the i-th interval, is the representative wind speed of the i-th first bin interval, α is the final static yaw error data corresponding to the target wind turbine, and N is the number of the first bin intervals.

8. A wind turbine static yaw error diagnostic system, characterized in that: include: A bin processing module, for binning the historical operation data of the target wind turbine generator set according to preset variable characteristics of the historical operation data of the target wind turbine generator set obtained in advance, to obtain a plurality of first bin intervals and historical operation data of each first bin interval; wherein each first bin interval includes a plurality of second bin intervals; A yaw power curve fitting module is used to perform yaw power curve fitting on the historical operating data of each second bin interval after smoothing, so as to obtain a yaw power curve corresponding to each second bin interval; A static yaw error data determination module, configured to determine the static yaw error data of each first sub-bin interval based on the yaw power curves of each second sub-bin interval under each first sub-bin interval; The data integration module is used to integrate the static yaw error data of each first sub-bin interval to obtain the final static yaw error data corresponding to the target wind turbine group.

9. A machine-readable storage medium having instructions stored thereon, characterized in that: When the instruction is executed by a processor, the processor is configured to execute the static yaw error diagnosis method for a wind turbine set as claimed in any one of claims 1 to 7.

10. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the static yaw error diagnosis method for a wind turbine set according to any one of claims 1 to 7 is implemented.

Images