A method, system, computer device and storage medium for identifying execution deviation of wind turbine blade

Abstract

This invention belongs to the field of wind power generation technology and relates to a method for identifying blade execution deviations in wind turbine generators. First, historical data from the wind farm is acquired. The continuous SCADA data is then segmented according to preset time segments to obtain N sets of data. The pitch commands, pitch angles of the three blades, and wind speeds in each set are acquired and sorted according to the time sequence. The maximum pitch angle deviation, cumulative deviation, and wind speed turbulence value within each set are calculated. It is determined whether all pitch commands in each set are within the preset pitch angle range. If so, the maximum pitch angle deviation, cumulative deviation, and wind speed turbulence value for each set are acquired. A first threshold and a second threshold are determined. If X consecutive maximum pitch angle deviations exceed the first threshold and the cumulative deviation exceeds the second threshold, the blade angle execution deviation is deemed too large. This method solves the problems of low accuracy and the need for additional equipment in existing technologies.

Description

Technical Field

[0001] This invention belongs to the field of wind power generation technology, specifically relating to a method, system, computer equipment, and storage medium for identifying the execution deviation of wind turbine blades. Background Technology

[0002] The wind turbine generator set is equipped with three blades, which are controlled by a pitch control system. The main principle is to control the rotational speed of the wind turbine by controlling the torsion angle of the blades, thereby controlling the output power of the wind turbine, and can safely stop the wind turbine through aerodynamic braking.

[0003] Currently, most wind turbines on the market use a uniform pitch control system, meaning that the pitch controller issues consistent commands to all three blades. However, this is only an ideal scenario. Due to various reasons such as installation, pitch control execution, and blade damage, the actual aerodynamic angles of the three blades can deviate. Therefore, when a wind turbine experiences blade damage or impeller mass imbalance, it can cause increased tower vibration and affect the stability of the wind turbine's transmission system.

[0004] A search revealed that patent document CN112555102A discloses a method and apparatus for identifying blade pitch angle deviation and controlling a wind turbine generator set. The method for identifying blade pitch angle deviation includes: acquiring operating data of the wind turbine generator set; based on the acquired operating data, determining the energy amplitude of the vibration signal of the wind turbine generator set at one times the rotor's rotational frequency and at three times the rotor's rotational frequency; based on the determined energy amplitudes at one times and three times the rotor's rotational frequency, using a pre-established specific mathematical model to determine the current absolute deviation angle of the blade's pitch angle, where the current absolute deviation angle of the blade's pitch angle is the deviation between the current blade pitch angle and the optimal pitch angle. This patent primarily judges the execution deviation of the three blades through the vibration of the wind turbine, relying on indirect methods to determine the execution deviation, resulting in low accuracy.

[0005] Patent document CN111379673A discloses a method and apparatus for calculating the pitch angle deviation of wind turbine blades. The method includes: acquiring laser ranging data of the wind turbine rotor, wherein the laser ranging data is data obtained by a laser ranging device within at least one rotation cycle of the rotor; determining whether the acquired laser ranging data is valid laser ranging data; when it is determined that the acquired laser ranging data is valid laser ranging data, acquiring contour data of a specific region of each blade based on the acquired laser ranging data, wherein the specific region is the area on each blade where the laser is emitted during rotor rotation; and calculating the pitch angle deviation of each blade based on the acquired contour data. According to the method for calculating the pitch angle deviation of wind turbine blades, the pitch angle deviation of the blades can be accurately obtained, thereby adjusting the blade pitch angle to reduce rotor start-up imbalance.

[0006] This patent mainly detects the difference in blade angle of the unit through laser ranging data. It requires the addition of additional lidar equipment, and the data access work is also required later, which is too complicated and costly. Summary of the Invention

[0007] The purpose of this invention is to provide a method, system, computer equipment, and storage medium for identifying the performance deviation of wind turbine blades, which solves the problems of low accuracy and the need for additional equipment in the prior art.

[0008] This invention is achieved through the following technical solution:

[0009] A method for identifying performance deviations of wind turbine blades includes the following steps:

[0010] S1. Obtain historical data of wind farms, clean the historical data of wind farms, and obtain SCADA data that meets the requirement of continuity.

[0011] S2. Divide the continuous SCADA data into N sets of data according to preset time segments;

[0012] S3. Obtain the pitch command, pitch angle of the three blades and wind speed in each set of data. The pitch command, pitch angle of the three blades and wind speed are sorted according to the time sequence.

[0013] S4. Based on the time sequence of the pitch angle of the three blades, calculate the maximum pitch angle deviation and the cumulative deviation in each data set.

[0014] Based on the time order of wind speed, calculate the wind speed turbulence value in each data set to obtain N wind speed turbulence values;

[0015] S5. Determine whether all pitch commands in each set of data are within the preset pitch angle range. If not, continue to determine whether all pitch commands in the next set of data are within the preset pitch angle range. If yes, start S6.

[0016] S6. Obtain the maximum pitch angle deviation, cumulative deviation, and wind speed turbulence value corresponding to each set of data obtained in S4.

[0017] The first and second thresholds are determined based on the wind speed turbulence values;

[0018] If the maximum value of X consecutive pitch angle deviations is greater than the first threshold, and the cumulative deviation is greater than the second threshold, then the blade angle execution deviation is determined to be too large.

[0019] Furthermore, in S1, the data is cleaned, specifically as follows:

[0020] The time channel is divided into t min. If the number of sampling points within t min is less than the preset percentage of the number of sampling points, the data in that time period is removed.

[0021] Furthermore, in S3, the three blades are the first blade, the second blade, and the third blade;

[0022] Within a preset time segment, the pitch angle of the first blade is denoted as PA1j, j = 1, 2...L, and ordered in time sequence as PA11, PA12, ... PA1j, ... PA1L;

[0023] The pitch angle of the second blade is denoted as PA2j, j = 1, 2...L, and ordered in time sequence as PA21, PA22, ...PA2j, ...PA2L;

[0024] The pitch angle of the third blade is denoted as PA3j, j = 1, 2...L, and ordered in time sequence as PA31, PA32, ...PA3j, ...PA3L;

[0025] Wind speed is denoted as V, and sorted by time series as V1, V2, ... VL;

[0026] Where L is the number of sampling points within the preset time segment.

[0027] Furthermore, in S4, the maximum value and cumulative deviation of the pitch angle within each data set are calculated as follows:

[0028] First, calculate the maximum pitch angle deviation at each sampling time. The corresponding formula is:

[0029] PAmaxj=Max(PA1j, PA2j, PA3j)-Min(PA1j, PA2j, PA3j);

[0030] Each set of data can yield L maximum pitch angle deviation values, denoted as PAmax1, PAmax2, ..., PAmaxL;

[0031] Sum the L maximum pitch angle deviation values ​​to obtain the cumulative deviation SumPAi for each data set, SumPAi = PAmax1 + PAmax2 + ... + PAmaxL; then obtain the cumulative deviations SumPA1, SumPA2, ... SumPAi, ... SumPAN for N data sets.

[0032] The maximum pitch angle deviation for each set of data is MaxPAi, where MaxPAi = max(PAmax1, PAmax2, ..., PAmaxL); thus, the maximum pitch angle deviations for N sets of data are obtained as: MaxPA1, MaxPA2, ..., MaxPAi, ..., MaxPAN.

[0033] Furthermore, in S4, the expression for the wind speed turbulence value is:

[0034] VTuri = VSDi / Vavgi, where VSDi is the standard deviation of wind speed, Vavg is the mean wind speed within a preset time segment; i is the numerical sorting of the i-th data group, i = 1, 2, ... N;

[0035] L represents the number of sampling points within a preset time segment, and Vj represents the wind speed at the j-th sampling moment.

[0036] Furthermore, in S5, the preset pitch angle range is [PA0+0.5,30], where PA0 represents the optimal pitch angle.

[0037] Furthermore, in S6, a first threshold Ki and a second threshold Pi are determined based on the wind speed turbulence value, and both thresholds increase as the turbulence increases;

[0038] The relationship is expressed as: Ki = f1(Vturi), Pi = f2(Vturi), where f1 and f2 are piecewise functions, Vturi is the wind speed turbulence value, and i is the numerical sorting corresponding to the i-th group of data, i = 1, 2, ... N;

[0039] Different Vturi values ​​correspond to different K and P values, which are determined by looking up a table.

[0040] This invention discloses a system for identifying the performance deviation of wind turbine blades, comprising:

[0041] The data acquisition module is used to acquire historical data from wind farms;

[0042] The data cleaning module is used to clean historical data from wind farms to obtain SCADA data that meets continuity requirements.

[0043] The time segmentation module is used to segment SCADA data that meets the continuity requirement according to preset time segments to obtain N sets of data;

[0044] The time sorting module is used to obtain the pitch command, the pitch angle of the three blades and the wind speed in each data set. The pitch command, the pitch angle of the three blades and the wind speed are all sorted according to the time sequence.

[0045] The first data processing module is used to calculate the maximum value and cumulative deviation of the pitch angle in each data set based on the time sorting of the pitch angles of the three blades.

[0046] The second data processing module is used to sort the wind speed by time, calculate the wind speed turbulence value in each group of data, and obtain N wind speed turbulence values.

[0047] The warning trigger judgment module is used to determine whether all the pitch commands in each set of data are within the preset pitch angle range. If not, it continues to determine whether all the pitch commands in the next set of data are within the preset pitch angle range. If so, it starts the threshold lookup module and the execution deviation judgment module.

[0048] The threshold lookup module is used to obtain the wind speed turbulence value corresponding to each set of data, and determine the first threshold and the second threshold based on the wind speed turbulence value;

[0049] The execution deviation judgment module is used to obtain the maximum value and cumulative deviation of the pitch angle corresponding to each set of data. If the maximum value of the pitch angle deviation is greater than the first threshold for X consecutive times and the cumulative deviation is greater than the second threshold for X consecutive times, it is judged that the blade angle execution deviation is too large.

[0050] The present invention also discloses a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for identifying the execution deviation of wind turbine blades.

[0051] The present invention also discloses a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the method for identifying the execution deviation of wind turbine blades.

[0052] Compared with the prior art, the present invention has the following beneficial technical effects:

[0053] This invention discloses a method for identifying execution deviations of wind turbine blades. It evaluates the execution accuracy of three blades, with a key protection point being the initial screening based on pitch angle. Evaluation of all three blades only begins when the pitch command is within a preset pitch angle range (when the turbine is in pitch control). This is because the pitch angle is constant in non-pitch conditions, rendering evaluation meaningless and increasing data processing workload. Considering the varying execution accuracy of pitch angles under drastic wind speed changes, potentially leading to significant deviations, the alarm threshold is dynamically adjusted based on the severity of wind speed variations. Higher wind speed turbulence values ​​indicate greater wind fluctuations and decreased pitch execution accuracy, necessitating a higher threshold for more accurate warnings. In addition to judging the maximum pitch angle deviation, the cumulative pitch angle execution deviation is also assessed, with both conditions met before issuing a warning to prevent false alarms. This invention primarily assesses the operational deviation of the three blades. Based on big data analytics, it monitors the balance of the blades over a period of time, identifying areas where significant anomalies in all three blades are detected during wind turbine operation. This triggers an early warning system, guiding on-site maintenance and inspection. Unlike traditional wind turbine control systems that alarm for deviations in pairs of blades, this method uses big data to observe and warn of operational deviations in all three blades over a long period, allowing for early detection of potential problems and preventing major safety incidents.

[0054] Furthermore, the preset pitch angle range is designed as [PA0+0.5, 30]. When the pitch command is less than 30 degrees, the shutdown state is excluded before the evaluation of the three blades begins. This is because when the blade pitch angle is too large (usually in the shutdown state, the angle is around 90 degrees), the wind turbine load is significantly reduced, the requirement for blade execution accuracy is reduced, and the evaluation is meaningless at this time, and it will increase the data processing task. Attached Figure Description

[0055] Figure 1 This is a flowchart of a method for identifying the execution deviation of wind turbine blades according to the present invention;

[0056] Figure 2 This is a schematic diagram of a system for identifying the execution deviation of wind turbine blades according to the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of the present invention clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention; that is, the described embodiments are only a part of the embodiments of the present invention, and not all of them.

[0058] The components described and illustrated in the accompanying drawings and embodiments of this invention can be arranged and designed in various different configurations. Therefore, the detailed description of the embodiments of the invention provided in the following drawings is not intended to limit the scope of the claimed invention, but merely to illustrate one selected embodiment of the invention. All other embodiments obtained by those skilled in the art based on the accompanying drawings and embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0059] The features and performance of the present invention will be further described in detail below with reference to embodiments.

[0060] This invention, based on a SCADA big data set, quantitatively analyzes and issues early warnings regarding the execution of three pitch control functions of a generator unit under high wind conditions. The research includes: data cleaning, algorithm implementation, and early warning.

[0061] like Figure 1 As shown, this invention discloses a method for identifying the performance deviation of wind turbine blades, comprising the following steps:

[0062] S1. Obtain historical data of wind farms, clean the historical data of wind farms, and obtain SCADA data that meets the requirement of continuity.

[0063] S2. Divide the continuous SCADA data into N sets of data according to preset time segments;

[0064] S3. Obtain the pitch command, pitch angle of the three blades and wind speed in each set of data. The pitch command, pitch angle of the three blades and wind speed are sorted according to the time sequence.

[0065] S4. Based on the time sorting of the pitch angles of the three blades, calculate the maximum value and cumulative deviation of the pitch angle in each data set.

[0066] Based on the time order of wind speed, calculate the wind speed turbulence value in each data set to obtain N wind speed turbulence values;

[0067] S5. Determine whether all pitch commands in each set of data are within the preset pitch angle range. If not, continue to determine whether all pitch commands in the next set of data are within the preset pitch angle range. If yes, start S6.

[0068] S6. Obtain the maximum pitch angle deviation, cumulative deviation, and wind speed turbulence value corresponding to this set of data;

[0069] The first and second thresholds are determined based on the wind speed turbulence values;

[0070] If the maximum value of X consecutive pitch angle deviations is greater than the first threshold, and the cumulative deviation is greater than the second threshold, then the blade angle execution deviation is determined to be too large.

[0071] Example 1

[0072] This invention discloses a method for identifying the performance deviation of wind turbine blades, specifically including the following steps:

[0073] S1. Data preparation: Obtain historical data of wind farms, clean the historical data of wind farms, and obtain SCADA data that meets the requirements of continuity.

[0074] 1) Collect and store the operating data of each turbine unit at the target wind farm, requiring at least one month's worth of data;

[0075] 2) Store the data on the server according to the specified location and number;

[0076] 3) Clean the data according to its availability to obtain SCADA data that meets the requirement of continuity.

[0077] The time channel is divided into 1-minute intervals. If the number of points within 1 minute is less than 85% of the required sampling, the points are removed, and this rule is considered invalid. (For example, if the data requirement is 1 second interval, 60 points should be collected in 1 minute, but the actual number of points should be no less than 51).

[0078] S2. Divide the cleaned SCADA data that meets the continuity requirement into segments of 1 minute each. Assume that the acquired data can be divided into N groups.

[0079] S3. Extract the pitch command, pitch angle of the first blade, pitch angle of the second blade, pitch angle of the third blade, and wind speed for each 1-minute interval, and sort them in time sequence:

[0080] The first blade pitch angle within 1 minute: PA11, PA12, ... PA1j, ... PA1L;

[0081] The second blade pitch angles are PA21, PA22, ... PA2j, ... PA2L;

[0082] The third blade pitch angle is PA31, PA32, ... PA3j, ... PA3L;

[0083] Wind speed time series sorting: V1, V2, ... VL, where L is the number of sampling points within 1 minute. For example, if sampling is performed once per second, then L = 60.

[0084] S4, 4.1 Calculate the maximum pitch angle deviation and cumulative deviation within each data set:

[0085] The pitch angle deviation at the j-th sampling time is specifically the maximum value of the three blades minus the minimum value at the same sampling time, expressed as:

[0086] PAmaxj=Max(PA1j, PA2j, PA3j)-Min(PA1j, PA2j, PA3j);

[0087] Within 1 minute, L maximum pitch angle deviation values ​​can be obtained, denoted as PAmax1, PAmax2, ..., PAmaxL;

[0088] The cumulative deviation within 1 minute is: SumPAi=PAmax1+PAmax2+…PAmaxL, which gives N cumulative deviation values ​​SumPA1, SumPA2, …SumPAi, …SumPAN; i=1, 2, 3……N.

[0089] The maximum pitch angle deviation within 1 minute is:

[0090] MaxPAi = max(PAmax1, PAmax2, ..., PAmaxL); then a series of maximum pitch angle deviations can be obtained: MaxPA1, MaxPA2, ..., MaxPAi, ..., MaxPAN.

[0091] 4.2 Calculate the wind speed turbulence value for each 1-minute interval:

[0092] VTuri = VSDi / Vavgi, where VTuri is the standard deviation of wind speed. Vavg is the average wind speed over 1 minute; L is the number of sampling points within the preset time segment; and Vj is the wind speed at the j-th sampling time. This yields a series (here, N segments) VTur1, VTur2, ..., VTurN.

[0093] S5, Warning Trigger Judgment

[0094] Judgment: When all PADj within 1 minute are within [PA0+0.5,30], a warning trigger judgment is performed.

[0095] PA0 represents the optimal pitch angle, which is usually 0; PAD is the pitch control command, which is the position where the pitch angle required by the wind turbine main control should be executed.

[0096] The pitch control deviation fluctuation threshold is dynamically set. Different thresholds Ki and Pi are determined based on the turbulence value. The thresholds increase as the turbulence increases. The relationship can be expressed as: Ki = f1(Vturi), Pi = f2(Vturi). f1 and f2 can be piecewise functions. For example, based on experience, different values ​​of K and P are determined for different Vturi values, and the determination is made by looking up a table.

[0097] An alarm will be triggered if MaxPAi > Ki and SumPAi > Pi for three consecutive times. The alarm indicates that the blade angle execution deviation is too large, prompting on-site maintenance personnel to conduct an inspection.

[0098] Example 2

[0099] like Figure 2 As shown, this invention discloses a system for identifying the execution deviation of wind turbine blades, comprising:

[0100] The data acquisition module is used to acquire historical data from wind farms;

[0101] The data cleaning module is used to clean historical data from wind farms to obtain SCADA data that meets continuity requirements.

[0102] The time segmentation module is used to segment SCADA data that meets the continuity requirement according to preset time segments to obtain N sets of data;

[0103] The time sorting module is used to obtain the pitch command, the pitch angle of the three blades and the wind speed in each data set. The pitch command, the pitch angle of the three blades and the wind speed are all sorted according to the time sequence.

[0104] The first data processing module is used to calculate the maximum value and cumulative deviation of the pitch angle in each data set based on the time sorting of the pitch angles of the three blades.

[0105] The second data processing module is used to sort the wind speed by time, calculate the wind speed turbulence value in each group of data, and obtain N wind speed turbulence values.

[0106] The warning trigger judgment module is used to determine whether all the pitch commands in each set of data are within the preset pitch angle range. If not, it continues to determine whether all the pitch commands in the next set of data are within the preset pitch angle range. If so, it starts the threshold lookup module and the execution deviation judgment module.

[0107] The threshold lookup module is used to obtain the wind speed turbulence value corresponding to each set of data, and determine the first threshold and the second threshold based on the wind speed turbulence value;

[0108] The execution deviation judgment module is used to obtain the maximum value and cumulative deviation of the pitch angle corresponding to each set of data. If the maximum value of the pitch angle deviation is greater than the first threshold for X consecutive times and the cumulative deviation is greater than the second threshold for X consecutive times, it is judged that the blade angle execution deviation is too large.

[0109] Example 3

[0110] A computer device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the steps of a method for identifying deviations in wind turbine blades. The memory may include main memory, such as high-speed random access memory (RAM), and may also include non-volatile memory, such as at least one disk storage device. The processor, network interface, and memory are interconnected via an internal bus, which may be an industry-standard architecture bus, a peripheral component interconnection standard bus, or an extended industry-standard architecture bus. The bus may be categorized as an address bus, data bus, or control bus. The memory stores the program; specifically, the program may include program code, which includes computer operation instructions. The memory may include main memory and non-volatile memory, and provides instructions and data to the processor.

[0111] Example 4

[0112] A computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the method for identifying deviations in wind turbine blades. Specifically, the computer-readable storage medium includes, but is not limited to, volatile memory and / or non-volatile memory. The volatile memory may include random access memory (RAM) and / or cache memory, etc. The non-volatile memory may include read-only memory (ROM), hard disk, flash memory, optical disk, magnetic disk, etc.

[0113] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0114] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1A device that provides the functions specified in one or more boxes.

[0115] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0116] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0117] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A method of identifying execution deviation of wind turbine blades, characterized in that, The method comprises the following steps: S1, obtaining wind farm historical data, cleaning the wind farm historical data, and obtaining SCADA data meeting continuity; S2, segmenting the SCADA data meeting continuity according to a preset time segment to obtain N groups of data; S3, obtaining a variable pitch instruction, a variable pitch angle of three blades, and a wind speed in each group of data, and the variable pitch instruction, the variable pitch angle of three blades, and the wind speed are sorted according to a time sequence; S4, calculating a maximum variable pitch angle deviation and an accumulated deviation amount in each group of data according to the time sorting of the variable pitch angle of three blades; calculating a wind speed turbulence value in each group of data according to the time sorting of the wind speed to obtain N wind speed turbulence values; S5, judging whether the variable pitch instructions in each group of data are all within a preset variable pitch angle range, if not, continuing to judge whether the variable pitch instructions in the next group of data are all within the preset variable pitch angle range, and if yes, starting S6; S6, obtaining the maximum variable pitch angle deviation, the accumulated deviation amount, and the wind speed turbulence value corresponding to each group of data obtained in S4; determining a first threshold value and a second threshold value according to the wind speed turbulence value; when the maximum variable pitch angle deviation is greater than the first threshold value for X consecutive times, and the accumulated deviation amount is greater than the second threshold value for X consecutive times, it is judged that the blade angle execution deviation is too large; In S3, the three blades are a first blade, a second blade, and a third blade; In a preset time segment, the variable pitch angle of the first blade is denoted as PA1j, j=1, 2…L, and is sorted according to a time sequence as PA11, PA12, …PA1j, …PA1L; the variable pitch angle of the second blade is denoted as PA2j, j=1, 2…L, and is sorted according to a time sequence as PA21, PA22, …PA2j, …PA2L; the variable pitch angle of the third blade is denoted as PA3j, j=1, 2…L, and is sorted according to a time sequence as PA31, PA32, …PA3j, …PA3L; the wind speed is denoted as V, and is sorted according to a time sequence as V1, V2, …VL; wherein, L is the number of sampling points in the preset time segment; In S4, the maximum variable pitch angle deviation and the accumulated deviation amount in each group of data are calculated as follows: first, the maximum variable pitch angle deviation at each sampling time is calculated, and the corresponding formula is: PAmaxj=Max(PA1j, PA2j, PA3j)-Min(PA1j, PA2j, PA3j); L maximum variable pitch angle deviation values in each group of data are obtained, denoted as PAmax1, PAmax2, …PAmaxL; the L maximum variable pitch angle deviation values are summed to obtain the accumulated deviation amount SumPAi in each group of data, SumPAi=PAmax1+PAmax2+…PAmaxL; and the accumulated deviation amounts SumPA1, SumPA2, …SumPAi, …SumPAN corresponding to the N groups of data are obtained. The maximum pitch angle deviation of each group of data is MaxPAi, and MaxPAi=max(PAmax1, PAmax2, …, PAmaxL). The maximum pitch angle deviation of N groups of data is MaxPA1, MaxPA2, …, MaxPAi, …, MaxPAN.

2. A method of identifying execution deviation of wind turbine blade according to claim 1, characterized in that, In S1, the data is cleaned, specifically: The time channel is divided into t min segments. If the number of sampling points in t min is less than the preset percentage of the number of sampling points, the data of the time segment is removed.

3. A method of identifying execution deviation of wind turbine blade according to claim 1, characterized in that, In S4, the expression of the wind speed turbulence value is: VTuri=VSDi / Vavgi, where VSDi is the wind speed standard deviation, Vavg is the average wind speed in the preset time segment, and i is the numerical order corresponding to the i th group of data, i=1, 2…N. VSDi= L is the number of sampling points in a preset time segment, is the wind speed corresponding to the jth sampling moment.

4. A method of identifying execution deviation of wind turbine blade according to claim 1, characterized in that, In S5, the preset pitch angle range is [PA0+0.5, 30], and PA0 represents the optimal pitch angle.

5. A method of identifying execution deviation of wind turbine blade according to claim 1, characterized in that, In S6, the first threshold Ki and the second threshold Pi are determined according to the wind speed turbulence value, and the two thresholds increase with the increase of turbulence. The relationship is expressed as: Ki=f1(Vturi), Pi=f2(Vturi), f1 and f2 are piecewise functions, Vturi is the wind speed turbulence value, and i is the numerical order corresponding to the i th group of data, i=1, 2…N. Different Vturi values correspond to different K values and P values, which are determined in the form of a lookup table.

6. A system for identifying blade execution deviation of a wind turbine generator set according to any one of claims 1 to 5, characterized in that, It includes: a data acquisition module for acquiring wind farm historical data; a data cleaning module for cleaning the wind farm historical data to obtain SCADA data that meets continuity; a time segmentation module for segmenting the SCADA data that meets continuity according to a preset time segment to obtain N groups of data; a time sorting module for obtaining the pitch command, the pitch angle of the three blades, and the wind speed in each group of data, which are sorted in time sequence; a first data processing module for calculating the maximum pitch angle deviation and the cumulative deviation amount in each group of data according to the time sorting of the pitch angle of the three blades; a second data processing module for calculating the wind speed turbulence value in each group of data according to the time sorting of the wind speed, and obtaining N wind speed turbulence values; an early warning trigger judgment module for judging whether the pitch command in each group of data is within the preset pitch angle range. If not, it continues to judge whether the pitch command in the next group of data is within the preset pitch angle range. If yes, it starts the threshold lookup module and the execution deviation judgment module; a threshold lookup module for obtaining the wind speed turbulence value corresponding to each group of data, and determining the first threshold and the second threshold according to the wind speed turbulence value; an execution deviation judgment module for obtaining the maximum pitch angle deviation and the cumulative deviation amount corresponding to each group of data. When the maximum pitch angle deviation of X consecutive groups is greater than the first threshold, and the cumulative deviation amount of X consecutive groups is greater than the second threshold, it is judged that the blade angle execution deviation is too large.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program to realize the steps of the method for identifying the blade execution deviation of a wind turbine generator set according to any one of claims 1 to 5. The processor executes the computer program to realize the steps of the method for identifying the blade execution deviation of a wind turbine generator set according to any one of claims 1 to 5.

8. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 7. The computer program, when executed by a processor, implements the steps of the method for identifying execution deviations of wind turbine blades according to any one of claims 1 to 5.

Images