CN118462505A - Intelligent early warning method, system, equipment and medium for abnormal yaw angle of wind turbine - Google Patents

Abstract

The present invention provides an intelligent early warning method, system, equipment and medium for abnormal yaw to wind angle of a wind turbine set, comprising the following steps: step 1, preprocessing the historical data of the target unit to obtain a matrix, wherein the first column of the matrix is the wind speed, the second column is the wind angle, and the third column is the active power; step 2, dividing the active power into bins using the wind speed and the wind angle to obtain a plurality of wind speed-angle bins; step 3, constructing a two-dimensional matrix and a three-dimensional matrix according to the obtained plurality of wind speed-angle bins, step 4, using the obtained two-dimensional matrix to judge whether the dynamic deviation of the wind angle is normal; using the three-dimensional matrix to judge whether the target unit is operating normally, wherein if the unit is operating abnormally, using the three-dimensional matrix to construct a four-dimensional matrix, and using the four-dimensional matrix to judge whether the static deviation of the wind angle is normal; the present invention can more comprehensively and accurately judge the problem of abnormal yaw to wind angle of the unit.

Description

An intelligent early warning method, system, equipment and medium for abnormal yaw angle of wind turbine

Technical Field

The present invention belongs to the technical field of wind turbine variable pitch motor fault warning, and specifically relates to a method, system, equipment and medium for intelligent warning of abnormal yaw angle of a wind turbine set to the wind.

Background Art

In recent years, smart operation and maintenance of wind farms has become a hot topic in the industry. However, in the process of smart operation and maintenance of wind farms, it is particularly important to be able to use various intelligent algorithms to warn of equipment failures in advance. Whether the unit's yaw to the wind is abnormal is related to the unit's absorption of wind energy, which directly affects the unit's power generation. In addition, abnormal dynamic deviation of the unit's wind angle will increase the unit's load, and long-term operation with problems will reduce the unit's life.

At present, although many different methods have been proposed at home and abroad for the abnormal warning of wind turbine angles, most of them are offline applications for small batches of units. The data collection and reading of large batches of units have poor fault tolerance. Online applications will affect the accuracy of the calculation results of the algorithm model, and in severe cases will cause the model to get stuck, disconnect and be unable to run. At present, the judgment of abnormal wind angles of units not only rarely pays attention to the dynamic deviation angle, but also the calculation method of the static deviation angle is usually to check the power at different wind angles at a specified wind speed, or to check the power curves at different wind angles, and analyze which curve is on top. Of these two methods, the first method only applies a small part of the unit data, does not fully tap the potential of the unit data, and the calculated results are less accurate. The second method currently does not solve the problem of power curve intersection, and there is no way to automatically and accurately calculate the wind angle deviation result.

Summary of the invention

The purpose of the present invention is to provide a method, system, equipment and medium for intelligent early warning of abnormal yaw to wind angle of a wind turbine, which solves the defect that the existing calculation of the wind angle has a large deviation, resulting in inaccurate judgment results of abnormal wind angle.

In order to achieve the above object, the technical solution adopted by the present invention is:

The present invention provides an intelligent early warning method for abnormal yaw angle of a wind turbine generator set to the wind, comprising the following steps:

Step 1, preprocessing the historical data of the target unit to obtain a matrix, wherein the first column of the matrix is the wind speed, the second column is the wind angle, and the third column is the active power;

Step 2, using wind speed and wind angle to divide active power into bins to obtain multiple wind speed-angle bins;

Step 3, constructing a two-dimensional matrix and a three-dimensional matrix respectively according to the obtained multiple wind speed-angle chambers;

Step 4, using the obtained two-dimensional matrix to determine whether the dynamic deviation of the wind angle is normal; using the three-dimensional matrix to determine whether the target unit is operating normally, wherein, if the unit is operating abnormally, the three-dimensional matrix is used to construct a four-dimensional matrix, and the four-dimensional matrix is used to determine whether the static deviation of the wind angle is normal.

Preferably, in step 1, the historical data of the target unit is preprocessed to obtain a matrix, and the specific method is:

S11, the historical data includes unit status, wind speed, active power, pitch angle and wind angle; obtain configuration parameters of the target unit, the configuration parameters include cut-in wind speed, rated wind speed and rated power;

S12, filtering out from historical data the data of wind speed greater than the cut-in wind speed and less than the rated wind speed, active power greater than zero, unit status of normal power generation, and pitch angle less than 2, and forming a matrix.

Preferably, in step 2, the active power is divided into bins with a width of 1 using the wind speed and the wind angle to obtain a plurality of wind speed-angle bins.

Preferably, in step 3, a two-dimensional matrix is constructed according to the obtained multiple wind speed-angle chambers, and the specific method is:

The data volume of active power corresponding to each wind angle in each wind speed-angle chamber is counted, and the wind angle and active power data volume are combined to form a two-dimensional matrix.

Preferably, in step 3, the obtained two-dimensional matrix is used to determine whether the dynamic deviation of the wind angle is normal, and the specific method is:

Obtain the wind angle corresponding to the maximum amount of data from all the data in the two-dimensional matrix;

If the absolute value of the pair of wind angles is greater than or equal to the set threshold, the dynamic deviation of the wind angle of the target unit is abnormal; otherwise, the dynamic deviation of the wind angle of the target unit is normal.

Preferably, in step 3, a three-dimensional matrix is constructed according to the obtained multiple wind speed-angle chambers, and the specific method is:

Count the amount of active power in each wind speed-angle compartment;

The wind speed-angle bins corresponding to the data volume less than the set value are deleted to obtain the remaining wind speed-angle bins;

Calculate the power mean value between all active powers corresponding to each remaining wind speed-angle compartment;

The wind speed, wind angle and power mean values in all remaining wind speed-angle chambers are combined to form a three-dimensional matrix;

In step 3, a four-dimensional matrix is constructed using a three-dimensional matrix. The specific method is:

Obtain the maximum power mean corresponding to each wind speed from the three-dimensional matrix;

Obtain the wind angle corresponding to the maximum power average;

Obtain all power means when the wind angle corresponding to each wind speed is zero from the three-dimensional matrix, and calculate the mean corresponding to all power means;

Calculate the power difference between each maximum power mean and the mean;

Obtain the sum of the data of the power mean corresponding to each wind speed;

The wind speed and wind angle in the three-dimensional matrix, as well as the sum of the calculated data and the power difference are combined to form a four-dimensional matrix.

Preferably, in step 3, a four-dimensional matrix is used to determine whether the static deviation of the wind angle is normal. The specific method is:

Calculate the power difference mean corresponding to all power differences;

The obtained power difference mean is compared with the set threshold value, wherein, if the power difference mean is greater than the set threshold value, the static deviation of the wind angle is calculated using the four-dimensional matrix; otherwise, the target unit operates normally;

The obtained absolute value of the static deviation of the wind angle is compared with the threshold value, wherein if the absolute value of the static deviation of the wind angle is greater than the threshold value, the static deviation of the wind angle is abnormal; otherwise, the static deviation of the wind angle is normal.

An intelligent early warning system for abnormal yaw angle of a wind turbine generator set to the wind, comprising:

A data acquisition unit is used to pre-process the historical data of the target unit to obtain a matrix, wherein the first column of the matrix is the wind speed, the second column is the wind angle, and the third column is the active power;

A compartment division unit is used to divide the active power into compartments according to the wind speed and the wind angle to obtain a plurality of wind speed-angle compartments;

The matrix construction unit is used to construct a two-dimensional matrix and a three-dimensional matrix according to the obtained multiple wind speed-angle chambers.

The abnormality judgment unit is used to use the obtained two-dimensional matrix to judge whether the dynamic deviation of the wind angle is normal; and use the three-dimensional matrix to judge whether the operation of the target unit is normal. If the unit is operating abnormally, the three-dimensional matrix is used to construct a four-dimensional matrix, and the four-dimensional matrix is used to judge whether the static deviation of the wind angle is normal.

A processing device comprises at least a processor and a memory, wherein a computer program is stored in the memory, and when the processor runs the computer program, the computer program is executed to implement the steps of the method.

A computer storage medium having computer readable instructions stored thereon, the computer readable instructions being executable by a processor to implement the steps of the method

Compared with the prior art, the present invention has the following beneficial effects:

The present invention provides an intelligent early warning method for abnormal yaw to wind angle of a wind turbine set, which calculates the static deviation and dynamic deviation of the wind angle respectively, and can more comprehensively and accurately judge the problem of abnormal yaw to wind angle of the set. In the process of judging the static deviation of the wind angle, a four-dimensional matrix constructed by wind speed, wind angle, sum of data volume and power difference is used, and then the static deviation of the wind angle is calculated using the four-dimensional matrix. The process is combined with the operation mechanism of the set. For example, when the blade length, air density and main control program of the set are unchanged during the power climbing stage, the output power of the set is mainly related to the wind speed and wind angle. The multi-parameter automatic weighted method is used, which not only effectively calculates the static deviation of the wind angle, but also avoids a large number of parameter adjustments in the later stage of the calculation of the static deviation of the wind angle, saves a lot of manpower and time, and thus improves the accuracy of the abnormal wind angle judgment result.

Furthermore, the present invention preprocesses the historical data of the target unit so that the method can be applied to online early warning of large-scale units. It has a certain fault-tolerant function and avoids the problem of abnormal calculation results of the algorithm model caused by abnormal data collection and reading in large-scale unit applications to a great extent.

The wind turbine set yaw angle abnormal intelligent early warning system provided by the present invention calculates the static deviation and dynamic deviation of the wind angle respectively, and can more comprehensively and accurately judge the problem of abnormal yaw angle of the set.

BRIEF DESCRIPTION OF THE DRAWINGS

FIG. 1 is a schematic diagram of the process of the present invention.

DETAILED DESCRIPTION

In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, integers, steps, operations, elements and/or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and/or combinations thereof.

It should also be understood that the term “and/or” used in the specification and appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

Example 1

As shown in FIG1 , the present embodiment provides an intelligent early warning method for abnormal yaw angle of a wind turbine, comprising the following steps:

Step 1, preprocessing the historical data of the target unit to obtain a matrix, wherein the first column of the matrix is the wind speed, the second column is the wind angle, and the third column is the active power;

Step 2, using wind speed and wind angle to divide active power into bins to obtain multiple wind speed-angle bins;

Step 3, construct a two-dimensional matrix and a three-dimensional matrix according to the obtained multiple wind speed-angle chambers.

Step 4, using the obtained two-dimensional matrix to determine whether the dynamic deviation of the wind angle is normal; using the three-dimensional matrix to determine whether the target unit is operating normally, wherein, if the unit is operating abnormally, the three-dimensional matrix is used to construct a four-dimensional matrix, and the four-dimensional matrix is used to determine whether the static deviation of the wind angle is normal.

This embodiment calculates the static deviation and dynamic deviation of the wind angle respectively, which can more comprehensively and accurately determine the problem of abnormal yaw wind angle of the unit.

Example 2

Step 1, read the 1-minute SCADA data of the unit for three months, the SCADA data including the unit status, wind speed, active power, pitch angle and wind angle; at the same time, obtain the unit cut-in wind speed, rated wind speed and rated power in the unit configuration.

Step 2, calculate the data volume of the SCADA data to be read. When the data volume is greater than or equal to 116640, perform normal data screening before full transmission. Otherwise, report that the original data is insufficient and the calculation ends.

Step 3, filter out the data with wind speed greater than the cut-in wind speed and less than the rated wind speed, power greater than 0, unit status of normal power generation, and pitch angle less than 2, to form a three-dimensional matrix Q1 containing wind speed, wind angle and active power;

Step 4, calculate the data volume of the three-dimensional matrix Q1. When the data volume is greater than or equal to 51840, perform bin calculation on the three-dimensional matrix Q1 data. Otherwise, it is reported that there is insufficient useful data and the calculation ends.

Step 5, calculate the data in the three-dimensional matrix Q1:

S51, binning the active power using wind speed and wind angle, with a width of 1, to obtain multiple wind speed-angle bins, where the wind speed and wind angle in each wind speed-angle bin are _Vi and _αj respectively;

S52, calculating the data amount of active power in each wind speed-angle compartment;

S53, deleting the wind speed-angle bins corresponding to the data amount less than 50, and obtaining the remaining wind speed-angle bins, wherein the wind speed and the wind angle in the remaining wind speed-angle bins are V _ii and α _jj respectively;

S54, calculating the power mean value W _ii-jj of the active power corresponding to each remaining wind speed-angle compartment;

S55: Combine the wind speeds V _ii , wind angles α _jj and power averages W _ii-jj corresponding to all remaining wind speed-angle compartments to form a three-dimensional matrix Q2.

Step 6, counting the amount of active power data _nj corresponding to each wind angle _αj in each wind speed-angle chamber, combining the wind angle and the amount of active power data to form a two-dimensional matrix recorded as Q4;

Obtain the wind angle α _n corresponding to the maximum data amount from all data amounts n _j in the matrix Q4;

Step 7: If the absolute value of the wind angle _αn is greater than or equal to 5, the dynamic deviation of the wind angle of the unit is abnormal, otherwise the dynamic deviation is normal;

Step 8, calculate the three-dimensional matrix Q2:

S81, obtaining the maximum power mean W ^MAX _ii corresponding to each wind speed V _ii from the three-dimensional matrix Q2; and obtaining the wind angle α _ii corresponding to the maximum power W ^MAX _ii ;

S82, obtaining the mean value W ^O _ii of all power mean values W _ii-jj when the wind angle corresponding to each wind speed V _ii is 0 from the three-dimensional matrix Q2;

S83, calculating the power difference W _ii between the maximum power W ^MAX _ii corresponding to each wind speed V _ii and the average W ^O _ii ;

S84, calculating the power difference mean W _μ between all power differences W _ii in the three-dimensional matrix Q2;

S85, calculating the sum N _ii of the data volume corresponding to each wind speed V _ii ;

S86, combining the obtained wind speed V _ii , wind angle α _ii , the sum of data amounts N _ii and the power difference W _ii to form a four-dimensional matrix Q3.

Step 9: If the power mean W _μ is greater than 5% of the rated power, proceed to step 10 to calculate the static angle deviation; otherwise, if the power deviation is small, the unit is normal;

Step 10, using the data of the four-dimensional matrix Q3 to calculate the static angle deviation β, the calculation formula is as follows:

Among them, N _ii is the sum of the data volume; W _ii is the power difference; β _ii is the static angle deviation corresponding to the i-th row of the four-dimensional matrix; ii is (1, 2, 3, 4, ..., n); n is the number of rows of the four-dimensional matrix.

Step 11: If the absolute value of the static angle deviation β is greater than the empirical value (the empirical value is 8), an abnormal static angle deviation is reported; otherwise, the static angle deviation of the unit is normal.

In the process of calculating the static deviation of the wind angle, this embodiment combines the operation mechanism of the unit. For example, when the unit is in the power climbing stage, the blade length, air density and main control program remain unchanged, and the output power of the unit is mainly related to the wind speed and the wind angle. The multi-parameter automatic weighted method is used, which not only effectively calculates the static deviation of the wind angle, but also avoids a large number of parameter adjustments in the later stage of the static deviation calculation of the wind angle, saves a lot of manpower and time, and thus improves the accuracy of the abnormal judgment results of the wind angle.

Example 3

This embodiment provides an intelligent early warning system for abnormal yaw angle of a wind turbine, which is characterized by comprising:

A data acquisition unit is used to pre-process the historical data of the target unit to obtain a matrix, wherein the first column of the matrix is the wind speed, the second column is the wind angle, and the third column is the active power;

A compartment division unit is used to divide the active power into compartments according to the wind speed and the wind angle to obtain a plurality of wind speed-angle compartments;

The matrix construction unit is used to construct a two-dimensional matrix and a three-dimensional matrix according to the obtained multiple wind speed-angle chambers.

The abnormality judgment unit is used to use the obtained two-dimensional matrix to judge whether the dynamic deviation of the wind angle is normal; and use the three-dimensional matrix to judge whether the operation of the target unit is normal. If the unit is operating abnormally, the three-dimensional matrix is used to construct a four-dimensional matrix, and the four-dimensional matrix is used to judge whether the static deviation of the wind angle is normal.

This system can more comprehensively and accurately identify abnormal yaw angles of the unit to the wind.

Example 4

This embodiment provides a processing device corresponding to the intelligent early warning method for abnormal yaw angle of a wind turbine set to wind provided in this embodiment 1. The processing device can be a processing device for a client, such as a mobile phone, a laptop computer, a tablet computer, a desktop computer, etc., to execute the method of embodiment 1.

The processing device includes a processor, a memory, a communication interface and a bus, and the processor, the memory and the communication interface are connected through the bus to complete mutual communication. The memory stores a computer program that can be run on the processor, and the processor executes an intelligent early warning method for abnormal yaw angle of a wind turbine set to wind provided in this embodiment 1 when running the computer program.

In some embodiments, the memory may be a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory.

In other embodiments, the processor may be a central processing unit (CPU), a digital signal processor (DSP), or other general-purpose processors of various types, which are not limited herein.

Example 5

The method for intelligently warning of abnormal yaw angle of a wind turbine set to the wind in Example 1 can be specifically implemented as a computer program product. The computer program product may include a computer-readable storage medium on which computer-readable program instructions for executing the method for intelligently warning of abnormal yaw angle of a wind turbine set to the wind in Example 1 are loaded.

Computer readable storage media may be tangible devices that hold and store instructions for use by instruction execution devices.

The computer-readable storage medium may be, for example but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any combination of the foregoing.

The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims (10)

1. An intelligent early warning method for yaw diagonal angle abnormality of a wind turbine generator is characterized by comprising the following steps:

Step 1, preprocessing the obtained historical data of the target unit to obtain a matrix, wherein a first column of the matrix is wind speed, a second column of the matrix is opposite wind angle and a third column of the matrix is active power;

Step 2, dividing active power into bins by utilizing wind speed and opposite wind angle to obtain a plurality of wind speed-angle bins;

step 3, respectively constructing a two-dimensional matrix and a three-dimensional matrix according to the obtained wind speed-angle bins;

step 4, judging whether the dynamic deviation of the wind angle is normal or not by using the obtained two-dimensional matrix; judging whether the target unit operates normally or not by using the three-dimensional matrix, wherein if the unit operates abnormally, constructing a four-dimensional matrix by using the three-dimensional matrix, and judging whether the static deviation of the wind angle is normal or not by using the four-dimensional matrix.

2. The intelligent early warning method for yaw versus wind angle abnormality of a wind turbine generator set according to claim 1 is characterized in that in step 1, the obtained historical data of a target turbine generator set is preprocessed to obtain a matrix, and the specific method comprises the following steps:

s11, the historical data comprise a unit state, wind speed, active power, a pitch angle and a wind angle; acquiring configuration parameters of a target unit, wherein the configuration parameters comprise cut-in wind speed, rated wind speed and rated power;

S12, screening data of wind speed larger than cut-in wind speed smaller than rated wind speed, active power with power larger than zero, normal power generation of a unit state and pitch angle smaller than 2 from historical data to form an obtained matrix.

3. The intelligent early warning method for yaw diagonal angle abnormality of a wind turbine generator set according to claim 1 is characterized in that in step 2, active power is divided into bins with the width of 1 by utilizing wind speed and diagonal angle to obtain a plurality of wind speed-angle bins.

4. The intelligent early warning method for yaw versus wind angle abnormality of a wind turbine generator set according to claim 1, wherein in step 3, a two-dimensional matrix is constructed according to a plurality of obtained wind speed-angle bins, and the specific method is as follows:

And counting the data quantity of the active power corresponding to each opposite wind angle in each wind speed-angle bin, and combining the opposite wind angle and the active power data quantity to form a two-dimensional matrix.

5. The intelligent early warning method for yaw versus wind angle abnormality of a wind turbine generator set according to claim 4, wherein in step 3, whether dynamic deviation to wind angle is normal is judged by using the obtained two-dimensional matrix, and the specific method is as follows:

acquiring a wind angle corresponding to the maximum data volume from all the data volumes in the two-dimensional matrix;

If the absolute value of the pair of opposite wind angles is larger than or equal to a set threshold value, the dynamic deviation of the opposite wind angles of the target unit is abnormal; otherwise, the dynamic deviation of the opposite wind angle of the target unit is normal.

6. The intelligent early warning method for yaw versus wind angle abnormality of a wind turbine generator set according to claim 1 is characterized in that in step 3, a three-dimensional matrix is constructed according to a plurality of obtained wind speed-angle bins, and the specific method is as follows:

counting the data quantity of active power in each wind speed-angle bin;

Deleting the wind speed-angle bin corresponding to the data volume smaller than the set value to obtain a residual wind speed-angle bin;

calculating the power average value among all the active powers corresponding to each wind speed-angle bin;

Combining the wind speeds, wind angles and power average values in all the rest wind speed-angle bins to form a three-dimensional matrix;

In the step 3, a four-dimensional matrix is constructed by utilizing a three-dimensional matrix, and the specific method is as follows:

obtaining a maximum power average value corresponding to each wind speed from the three-dimensional matrix;

Obtaining a wind angle corresponding to the maximum power average value;

Acquiring all power average values when the wind angle corresponding to each wind speed is zero from the three-dimensional matrix, and calculating the average value corresponding to all power average values;

calculating the power difference between each maximum power average value and each average value;

acquiring the sum of data amounts of power mean values corresponding to each wind speed;

And combining the wind speed and the wind angle in the three-dimensional matrix and the sum and the power difference of the calculated data quantity to form a four-dimensional matrix.

7. The intelligent early warning method for yaw diagonal angle abnormality of a wind turbine generator set according to claim 6 is characterized in that in step 3, whether static deviation of the diagonal angle is normal is judged by using a four-dimensional matrix, and the specific method is as follows:

Calculating the average value of the power differences corresponding to all the power differences;

Comparing the obtained power difference average value with a set threshold value, wherein if the power difference average value is larger than the set threshold value, calculating the static deviation of the wind angle by using a four-dimensional matrix; otherwise, the target unit operates normally;

comparing the obtained absolute value of the static deviation of the opposite wind angle with a threshold value, wherein if the absolute value of the static deviation of the opposite wind angle is larger than the threshold value, the static deviation of the opposite wind angle is abnormal; otherwise, the static deviation of the wind angle is normal.

8. An intelligent early warning system for yaw wind angle anomaly of a wind turbine generator, comprising:

The data acquisition unit is used for preprocessing the obtained historical data of the target unit to obtain a matrix, wherein the first column of the matrix is wind speed, the second column of the matrix is opposite wind angle and the third column of the matrix is active power;

The bin dividing unit is used for dividing the active power into bins by utilizing wind speed and opposite wind angle to obtain a plurality of wind speed-angle bins;

a matrix construction unit for constructing a two-dimensional matrix and a three-dimensional matrix according to the obtained wind speed-angle bins,

The anomaly judging unit is used for judging whether the dynamic deviation of the wind angle is normal or not by utilizing the obtained two-dimensional matrix; judging whether the target unit operates normally or not by using the three-dimensional matrix, wherein if the unit operates abnormally, constructing a four-dimensional matrix by using the three-dimensional matrix, and judging whether the static deviation of the wind angle is normal or not by using the four-dimensional matrix.

9. A processing device comprising at least a processor and a memory, the memory having stored thereon a computer program, characterized in that the processor executes to implement the steps of the method of any of claims 1 to 7 when the computer program is run by the processor.

10. A computer storage medium having stored thereon computer readable instructions executable by a processor to implement the steps of the method according to any of claims 1 to 7.