CN118915195A - Regional extreme weather prediction method and storage medium - Google Patents

Abstract

The invention relates to the field of extreme weather prediction, in particular to a regional extreme weather prediction method and a storage medium; calculating third kinetic energy received by the lower wind wheel of the corresponding wind direction by acquiring fan blade data, selecting the third kinetic energy by calculating a kinetic energy ratio to generate a database, finally reconstructing a kinetic energy function between apeak pitch angles and the third kinetic energy, calculating the third kinetic energy corresponding to the maximum pitch angle, calculating the corresponding maximum wind speed by the third kinetic energy, comparing the wind speed and the wind direction in a future period issued by an weather table with the maximum wind speed of the corresponding wind direction, realizing that the weather of the strong wind which is larger than the maximum wind speed is listed as extreme strong wind weather, and giving an alarm, thereby saving operation and maintenance cost in the process of detecting and maintaining the topography and saving part of cost of the prediction of the extreme weather of the strong wind; the method solves the problems that in the prior art, whether the wind farm has extreme weather or not is predicted through meteorological data and a topographic map, and the prediction cost is relatively high.

Description

A regional extreme weather prediction method and storage medium

Technical Field

The present invention relates to the field of extreme weather prediction, and in particular to a regional extreme weather prediction method and storage medium.

Background Art

At present, further forecasts for regional meteorological conditions are still based on meteorological data released by the Meteorological Observatory. Wind farms generate electricity through wind power, and there are certain requirements for the terrain of wind turbines to ensure greater wind energy. Therefore, in the same area, areas with wind farms generally have stronger winds, and they are commonly installed on hillsides in mountainous areas. However, when wind turbines are generating electricity, once the wind is too strong, the fan blades may be damaged, such as under the influence of typhoon weather. Therefore, when typhoon weather is predicted, it is generally necessary to protect the fan blades and other facilities in the wind farm.

However, the current mainstream method for predicting whether the wind force in the wind farm area is extreme wind weather that exceeds its tolerance is generally to construct a topographic map of the wind farm area and then combine meteorological data to predict whether the wind force reaches the level of extreme weather. When this method is used in mountainous areas, the tree density and distribution in the mountainous forest landforms and the hillside terrain are relatively complex and easy to change, resulting in the topographic map and ground friction coefficient and other basic parameters. If the topographic map is not continuously updated, it is easy to lead to unsatisfactory prediction accuracy. Therefore, the prediction cost of predicting through topographic maps is relatively high.

Summary of the invention

In view of the shortcomings of the prior art, the present invention provides a regional extreme weather prediction method and storage medium, which solves the problem of relatively high prediction cost in the prior art of predicting whether extreme weather will occur in a wind farm through meteorological data and topographic maps.

To achieve the above object, the present invention provides the following technical solutions:

A regional extreme weather prediction method, the method comprising:

S1. Obtain historical meteorological data including historical wind speed and wind direction of the area to be monitored, and obtain blade data including blade speed, blade area, pitch angle, rotor plane and number of blades of each wind turbine at a time corresponding to the historical meteorological data to generate basic data;

S2. Calculate the third kinetic energy of each wind turbine rotor along the wind direction when the wind turbine rotor rotates according to the basic data, and calculate the ratio of the third kinetic energy of each wind turbine rotor to obtain a kinetic energy ratio, and select the blade data within the kinetic energy ratio range to generate a database;

S3, extracting the blade data of several wind turbines with the largest third kinetic energy corresponding to each wind direction at any time from the database, and establishing a functional relationship model between the pitch angle and the third kinetic energy to obtain a kinetic energy function;

S4, calculating the third maximum kinetic energy under each wind direction when the pitch angle is maximum according to the kinetic energy function, and calculating the maximum wind speed of the natural wind when passing through the wind turbine blade according to the corresponding blade data;

S5. Obtain meteorological data of the monitored area for a period of time, and determine whether to output extreme weather alarm prompt information based on whether the corresponding wind speed in the corresponding wind direction is greater than the corresponding maximum wind speed;

If yes, then output the alarm prompt information of extreme wind weather and end;

If not, then end.

Preferably, in step S2, the following steps are specifically included:

S21, setting a plurality of wind directions to generate a plurality of wind direction groups;

S22, dividing the basic data into a plurality of wind direction groups according to wind directions to obtain a plurality of first basic data;

S23, calculating the second kinetic energy of each wind turbine blade in a direction perpendicular to the wind rotor plane according to the first basic data;

S24, calculating the third kinetic energy along the wind direction received by the wind rotor of the wind turbine according to the second kinetic energy;

S25, selecting a number of wind wheels with the largest third kinetic energy and corresponding fan blade data from the first basic data to generate second basic data;

S26, calculating the kinetic energy difference of the third kinetic energy of each wind rotor at any time in the second basic data, and selecting the third basic data according to the kinetic energy difference, and calculating the ratio of the kinetic energy difference of each wind rotor at any time according to the third basic data, and calculating the concentration density of the kinetic energy difference ratio;

S27. Setting a kinetic energy ratio range with the kinetic energy ratio having the largest aggregation density as the center, and selecting the fan blade data within the kinetic energy ratio range in the third basic data to generate a database.

Preferably, in step S23, the following steps are specifically included:

S231, calculating the first kinetic energy required for the wind wheel to rotate according to the fan blade data; the calculation formula of the first kinetic energy is:

In the above formula, _E1 represents the first kinetic energy required for the wind rotor to rotate, N represents the number of blades on a single wind rotor corresponding to the wind turbine, _r1 and _r2 represent the rotation radius of the two ends of a single blade when it rotates, M represents the weight of the blade per unit volume, w represents the angular velocity of the blade when it rotates, and r represents the radius at any position on the blade;

S232, constructing a wind rotor plane where the fan blades are rotating, and calculating a second kinetic energy perpendicular to the wind rotor plane according to the first kinetic energy and the fan blade deflection angle; the calculation formula of the second kinetic energy is:

In the above formula, _E2 is the second kinetic energy, _E1 is the first kinetic energy, and θ is the pitch angle.

Preferably, in step S24, the following steps are specifically included:

S241. An angular coordinate system located in a horizontal plane is constructed with the rotation axis of the fan blade as the center of the circle and the pitch angle as the positive value. The first angle between the wind direction and the normal direction of the wind rotor plane is calculated according to the historical meteorological data and the normal direction of the wind rotor plane. The calculation formula of the first angle is:

Δα ₁ =α ₁ -α ₂

In the above formula, _Δα1 is the first angle between the wind direction and the rotor plane, _α1 is the angle of the wind direction, and _α2 is the angle of the normal to the rotor plane;

S242, calculating a second angle between the wind direction and the normal direction of the blade surface according to the first angle and the pitch angle; the calculation formula of the second angle is:

Δα ₂ =θ-Δα ₁

In the above formula, Δα ₂ is the second angle between the wind direction and the blade surface, θ is the pitch angle of the blade, and Δα ₁ is the first angle between the wind direction and the normal direction of the rotor plane;

S243, calculating the third kinetic energy of the natural wind on the wind wheel according to the second angle and the second kinetic energy, the calculation formula of the third kinetic energy is:

In the above formula, _E3 represents the third kinetic energy of natural wind on the wind wheel, _E2 is the second kinetic energy, and _Δα2 is the second angle between the wind direction and the blade surface.

Preferably, in step S26, the following steps are specifically included:

S261, calculating the kinetic energy difference between the third kinetic energy of each wind wheel at the next moment and the previous moment; the calculation formula of the kinetic energy difference is:

In the above formula, ΔE ^i,i-1 represents the kinetic energy difference between any wind wheel at the i-th moment and the i-1-th moment. and are the third kinetic energy at the i-th moment and the i-1-th moment respectively;

S262, selecting the fan blade data at the time when the kinetic energy difference of the third kinetic energy at the same time in the second basic data is a positive value or a negative value, so as to generate the third basic data;

S263. Calculate the ratio of the kinetic energy difference between any two wind wheels in the third basic data to obtain a kinetic energy ratio. The calculation formula of the kinetic energy ratio is:

In the above formula, ΔE _n,m represents the kinetic energy ratio of the nth wind rotor and the mth wind rotor in the third basic data at any time, and ΔE _n and ΔE _m represent the kinetic energy difference between the nth wind rotor and the mth wind rotor in the third basic data respectively;

S264. Calculate the concentration density of the kinetic energy ratio between any two wind wheels in the third basic data.

Preferably, in step S3, the following steps are specifically included:

S31, extracting data of a number of fan blades with the largest third kinetic energy at any time in the database to obtain first sample data;

S32, calculating the average value of the third kinetic energy when the pitch angles in the first sample data are the same, to generate second sample data;

S33. Construct a kinetic energy function whose independent variable is the minimum to maximum value of the pitch angle according to the pitch angle of the fan blade in the second sample data and the corresponding third kinetic energy data.

Preferably, in step S4, the following steps are specifically included:

S41, calculating the third maximum kinetic energy of the wind turbine generator under each wind direction when the blade pitch angle is maximum according to the kinetic energy function;

S42. Calculate the maximum wind speed of the natural wind when passing through the wind turbine rotor according to the third maximum kinetic energy.

Preferably, in step S264, the calculation formula of the aggregation density is:

in,

In the above formula, Mn _,m represents the clustering density of the nth wind rotor and the mth wind rotor at any time, ΔEn _,m represents the kinetic energy ratio of the nth wind rotor and the mth wind rotor at any time, R represents the statistical radius, μ represents the sign function, and j represents the kinetic energy ratio data of j moments in the third basic data.

Preferably, in step S42, the maximum wind speed is calculated as follows:

In the above formula, V _max represents the maximum wind speed of natural wind when passing through the wind turbine rotor, E ₃ (max) represents the maximum value of the third kinetic energy of the wind turbine under any wind direction when the blade pitch angle is maximum, ρ represents the air density, S represents the area of the blade, Δα ₂ is the second angle between the wind direction and the blade surface, and τ is the safety factor.

The present invention also provides a computer storage medium storing a computer program, which implements the steps of the regional extreme weather prediction method when executed.

Compared with the prior art, the present invention provides a regional extreme weather prediction method and storage medium, which has the following beneficial effects:

1. Calculate the third kinetic energy received by the windward rotor under the corresponding wind direction by obtaining the fan blade data, and then select some third kinetic energies with larger values and higher data reliability by calculating the kinetic energy ratio to generate a database, and finally establish a kinetic energy function between the pitch angle and the third kinetic energy, calculate the third kinetic energy corresponding to the maximum pitch angle, and then calculate the corresponding maximum wind speed through the third kinetic energy. After that, compare the wind speed and wind direction in the future period released by the meteorological station with the maximum wind speed in the corresponding wind direction, so as to classify the strong wind weather greater than the maximum wind speed as extreme strong wind weather and issue an alarm, thereby saving the operation and maintenance costs in the process of terrain detection and maintenance, and saving part of the cost of forecasting strong winds and extreme weather.

2. The present invention divides the fan blade data into several first basic data according to the wind direction, so as to analyze the third kinetic energy of different wind wheels under different wind directions, and then selects several third kinetic energies with the largest values for analysis, thereby saving subsequent data calculation.

3. The present invention first calculates the kinetic energy difference, selects the third kinetic energy and the corresponding blade data whose kinetic energy difference is positive or negative at any time, and then further calculates the kinetic energy ratio of any two wind wheels in the third basic data at any time, and then determines the final kinetic energy ratio between the two wind wheels through the clustering density, and sets the kinetic energy ratio range to select more reliable third kinetic energy data and corresponding blade data from the third kinetic energy data at each time to generate a database.

4. The present invention generates a corresponding kinetic energy function by fitting according to the fan blade data and the third kinetic energy in the database, and then calculates the third kinetic energy under a certain wind direction and at the maximum pitch angle according to the kinetic energy function, and then infers the corresponding maximum wind speed, which is compared with the wind speed and wind direction in the meteorological data released by the meteorological station to determine whether extreme strong wind weather that may cause harm to the wind farm occurs.

BRIEF DESCRIPTION OF THE DRAWINGS

The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

FIG1 is a flow chart of a regional extreme weather prediction method according to the present invention;

FIG2 is a schematic diagram of a wind wheel of the present invention;

FIG. 3 is a schematic diagram showing the forces acting on the blades of the wind wheel of the present invention.

DETAILED DESCRIPTION

In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific implementation methods, so that the implementation process of how the present application uses technical means to solve technical problems and achieve technical effects can be fully understood and implemented accordingly.

Those skilled in the art can understand that all or part of the steps in the following embodiments can be completed by instructing the relevant hardware through a program, so the present application can be in the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application can be in the form of a computer program 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.

For the control of wind turbine speed, variable pitch angle control is a more mainstream control method. When the wind rotor can reach the rated speed driven by wind, if the wind force continues to increase, the speed of the wind rotor is controlled by controlling the pitch angle of the fan blades on the wind rotor to achieve maximum power generation while protecting the wind power generation equipment. However, the pitch angle also has its upper limit, so the wind force that can be adapted is also within a certain range. If the wind force exceeds the tolerance range of the wind rotor, the wind rotor may be damaged.

Therefore, at present, it is generally based on the regional meteorological data predicted by the meteorological station. When the wind force in the meteorological data reaches the extreme wind weather standard beyond the tolerance range of the wind rotor, it is necessary to take corresponding protective measures in advance for the stationary wind power generation components. However, the installation location of the wind power generation equipment is generally selected according to the local terrain in an uninhabited area with strong wind, such as a hillside. However, when the same wind force passes through the hillside, due to the interference of the hillside terrain on the wind force, the wind force at different locations on the hillside will also be different. The wind force in some areas may be relatively large, and the wind force of the same magnitude but different wind direction may change when passing through the hillside. Therefore, at present, according to the wind force forecast information released by the meteorological station and the topographic map, Wind simulation is a commonly used method to calculate the wind force at the maximum wind speed on the hillside, so as to determine whether the wind force exceeds the bearing limit of the wind turbine rotor in the corresponding area. However, this method requires frequent terrain detection to update the topographic map, which is troublesome and requires additional drone detection costs and topographic map update costs. Otherwise, due to landslides in mountains and forests or the growth of trees in four seasons, the topographic map and the surface friction coefficient will change, which will also affect the calculation results and cause poor calculation accuracy. Without continuous updating of the topographic map, generally only a more conservative protection strategy can be adopted, such as taking protective measures for the wind rotor and other components before the wind force reaches the bearing limit of the wind rotor, which will undoubtedly cause a large waste of electricity.

In order to solve the problem that the existing method of predicting whether extreme weather will occur in a wind farm by using meteorological data and topographic maps has a relatively high prediction cost, the present invention provides a regional extreme weather prediction method, which calculates the maximum wind force in the wind farm area according to meteorological station data in another way. As shown in FIG1 , the prediction method includes the following steps:

S1. Obtain historical meteorological data including historical wind speed and wind direction of the area to be monitored, and obtain blade data including blade speed, blade area, pitch angle, rotor plane and number of blades of each wind turbine at a time corresponding to the historical meteorological data to generate basic data;

S2. Calculate the third kinetic energy of each wind turbine rotor along the wind direction when the rotor rotates according to the basic data, and calculate the ratio of the third kinetic energy of each wind turbine rotor to obtain the kinetic energy ratio, and select the blade data within the kinetic energy ratio range to generate a database; by calculating the third kinetic energy, the corresponding relationship between the third kinetic energy and the pitch angle can be obtained when the wind turbine rotates at a certain speed and a certain pitch angle, but the calculation result of the third kinetic energy may be abnormal, such as the difference between the pitch angle setting value and the actual value of individual wind rotors, etc. At this time, it is necessary to screen it and select the third kinetic energy and the corresponding blade data with higher reliability, so as to finally generate a reliable database. Therefore, in step S2, the following steps are specifically included:

S21, setting a number of wind directions to generate a number of wind direction groups; because in different directions, even if the wind force is the same, when passing through the terrain of the wind farm area, the area where the maximum wind force is generated may be different, therefore, in actual operation, it is initially divided into 8 directions, i.e. 8 wind direction groups;

S22, dividing the basic data into a plurality of wind direction groups according to wind directions to obtain a plurality of first basic data;

S23, calculating the second kinetic energy of each wind turbine blade in a direction perpendicular to the wind rotor plane according to the first basic data; the second kinetic energy is the component of the kinetic energy in a direction perpendicular to the wind rotor plane when the wind blows along the wind direction, so in step S23, the following steps are specifically included:

S231, calculating the first kinetic energy required for the wind wheel to rotate according to the fan blade data; the calculation formula of the first kinetic energy is:

In the above formula, _E1 represents the first kinetic energy required for the wind rotor to rotate, N represents the number of blades on a single wind rotor corresponding to the wind turbine, _r1 and _r2 represent the rotation radius of the two ends of a single blade when it rotates, M represents the weight of the blade per unit volume, w represents the angular velocity of the blade when it rotates, and r represents the radius at any position on the blade;

S232, constructing a wind rotor plane where the fan blades are rotating, and calculating a second kinetic energy perpendicular to the wind rotor plane according to the first kinetic energy and the pitch angle; the calculation formula of the second kinetic energy is:

In the above formula, _E2 is the second kinetic energy, _E1 is the first kinetic energy, and θ is the pitch angle.

S24, calculating the third kinetic energy along the wind direction received by the wind rotor of the wind turbine according to the second kinetic energy; most of the wind rotors can rotate circumferentially around their support rods to adapt to different wind directions. Since the angle between the surface of the fan blade and the wind direction may be fixed during the rotation of the fan blade, the plane of the wind rotor is used as the transfer medium for angle calculation. In step S24, the following steps are specifically included:

S241. An angular coordinate system located in a horizontal plane is constructed with the rotation axis of the fan blade as the center of the circle and the pitch angle as the positive value. The first angle between the wind direction and the normal direction of the wind rotor plane is calculated according to the historical meteorological data and the normal direction of the wind rotor plane. The calculation formula of the first angle is:

Δα ₁ =α ₁ -α ₂

In the above formula, _Δα1 is the first angle between the wind direction and the normal direction of the wind rotor plane, which is generally 0, _α1 is the angle of the wind direction, which can be obtained from the data of the meteorological bureau, and _α2 is the angle of the normal direction of the wind rotor plane, which is adjusted and set by the control system of the wind power generation;

S242, calculating a second angle between the wind direction and the normal direction of the blade surface according to the first angle and the pitch angle; the calculation formula of the second angle is:

Δα ₂ =θ-Δα ₁

In the above formula, Δβ ₂ is the second angle between the wind direction and the blade surface, θ is the pitch angle of the blade, and Δα ₁ is the first angle between the wind direction and the normal of the rotor plane. Therefore, when the first angle is generally 0, the second angle and the pitch angle are generally equal.

S243, calculating the third kinetic energy of the natural wind on the wind wheel according to the second angle and the second kinetic energy, the calculation formula of the third kinetic energy is:

In the above formula, _E3 represents the third kinetic energy of natural wind on the wind wheel, _E2 is the second kinetic energy, and _Δα2 is the second angle between the wind direction and the blade surface, as shown in Figures 2 and 3. Figure 3 shows a top view of the blade in the vertical direction of Figure 2.

S25. Select several wind rotors with the largest third kinetic energy and corresponding fan blade data from the first basic data to generate second basic data. This step is to reduce the number of data in the second basic data, so as to facilitate subsequent calculations, because the third kinetic energy corresponds to the maximum wind force. As long as the wind rotor here can withstand the external wind force under a specific wind direction, other wind rotors can also withstand it. Therefore, the fan blade data corresponding to several wind rotors with the largest third kinetic energy are used for subsequent calculations to reduce the amount of calculations.

S26, calculating the kinetic energy difference of the third kinetic energy of each wind rotor at any time in the second basic data, and selecting the third basic data according to the kinetic energy difference, and calculating the ratio of the kinetic energy difference of each wind rotor at any time according to the third basic data, and calculating the aggregation density of the kinetic energy difference ratio; the calculated third kinetic energy may be wrong, for example, when the pitch angle set on the wind rotor is different from the actual pitch angle, the value of the third kinetic energy may be too large, so it is necessary to eliminate this part of the erroneous data, and further select the blade data that can reflect the corresponding relationship between the blade data and the third kinetic energy. In step S26, the following steps are specifically included:

S261, calculating the kinetic energy difference between the third kinetic energy of each wind wheel at the next moment and the previous moment; the calculation formula of the kinetic energy difference is:

In the above formula, ΔE ^i,i-1 represents the kinetic energy difference between any wind wheel at the i-th moment and the i-1-th moment. and are the third kinetic energy at the i-th moment and the i-1-th moment respectively;

S262. Select the blade data at the moment when the kinetic energy difference of the third kinetic energy at the same moment in the second basic data is a positive value or a negative value, so as to generate the third basic data, that is, select the blade data with the consistent increase or decrease state of the third kinetic energy at any moment from the second basic data. Because with the change of wind force, the third kinetic energy of all blades should theoretically increase or decrease at any moment. When the third kinetic energy on the wind wheel corresponding to the blade data contained in the second basic data at any moment does not increase or decrease at the same time, it means that at this moment, the reliability of the third kinetic energy corresponding to all blade data is not high and needs to be eliminated.

S263. Calculate the ratio of the kinetic energy difference between any two wind wheels in the third basic data to obtain a kinetic energy ratio. The calculation formula of the kinetic energy ratio is:

In the above formula, ΔE _n,m represents the kinetic energy ratio of the nth wind rotor and the mth wind rotor in the third basic data at any time, and ΔE _n and ΔE _m represent the kinetic energy difference between the nth wind rotor and the mth wind rotor in the third basic data respectively;

S264. Calculate the concentration density of the kinetic energy ratio between any two wind wheels in the third basic data. Here, instead of selecting a kinetic energy ratio from a large amount of kinetic energy ratio data by calculating the average value, the kinetic energy ratio at the center of the area where the kinetic energy ratio is most concentrated is selected, so as to more accurately reflect the change trend of the kinetic energy ratio. The calculation formula of the concentration density is:

in,

In the above formula, Mn _,m represents the clustering density of the nth wind rotor and the mth wind rotor at any time, ΔEn _,m represents the kinetic energy ratio of the nth wind rotor and the mth wind rotor at any time, R represents the statistical radius, μ represents the sign function, and j represents the kinetic energy ratio data of j moments in the third basic data.

S27. Set a kinetic energy ratio range with the kinetic energy ratio with the largest aggregation density as the center, and select the fan blade data within the kinetic energy ratio range in the third basic data to generate a database, so as to eliminate some wind wheels with abnormal kinetic energy ratios. For example, although the wind wheels m and n of the chain are increasing, the increase of wind wheel m is extremely large, while the increase of wind wheel n is extremely small, then at least one of the wind wheels may be abnormal. Therefore, this part of the data is eliminated, and finally a database with higher reliability is obtained.

S3. Extract the blade data of several wind turbines with the largest third kinetic energy corresponding to each wind direction at any time according to the database, and establish a functional relationship model between the pitch angle and the third kinetic energy to obtain the kinetic energy function; the blade data and the third kinetic energy in the database are relatively reliable, but the data points corresponding to the pitch angle and the third kinetic energy are still distributed in a discrete state, so it is necessary to count the rules to predict the corresponding third kinetic energy when the pitch angle is the largest, which generally corresponds to about 7-8 winds, and of course it is related to the size and manufacturing process of the wind wheel. When the pitch angle is the largest, the corresponding third kinetic energy on the hillside cannot be measured in advance. In the absence of data for verification when strong winds and extreme weather come, it is necessary to continuously count the third kinetic energy corresponding to different pitch angles under normal wind conditions in actual use, so as to predict the third kinetic energy corresponding to the maximum pitch angle when used on the hillside. In step S3, the following steps are specifically included:

S31, extracting data of a number of fan blades with the largest third kinetic energy at any time in the database to obtain first sample data;

S32. Calculate the average value of the third kinetic energy when the pitch angles in the first sample data are the same to generate the second sample data. That is, due to measurement errors or slight changes in the environment, different pitch angles may sometimes correspond to different third kinetic energies. At this time, different third kinetic energies with the same pitch angle are merged by taking the average value.

S33. Construct a kinetic energy function with the independent variable being the minimum to maximum pitch angle according to the pitch angle of the fan blade in the second sample data and the corresponding third kinetic energy data. The kinetic energy function can be constructed according to the second sample data using methods such as regression equation prediction method, grayscale prediction method and convolutional neural network. The accuracy of different methods will not be further discussed here, as their accuracy is closely related to the specific data processing process.

S4, calculating the maximum third kinetic energy under each wind direction when the pitch angle is maximum according to the kinetic energy function, and calculating the maximum wind speed of the natural wind when passing through the wind turbine rotor according to the corresponding blade data; under different wind directions, the wind rotor with the maximum third kinetic energy may be different, so it is necessary to calculate the maximum wind speed according to different wind directions. In step S4, the following steps are specifically included:

S41, calculating the third maximum kinetic energy of the wind turbine generator under each wind direction when the blade pitch angle is maximum according to the kinetic energy function;

S42. Calculate the maximum wind speed of the natural wind when it passes through the wind turbine rotor according to the maximum value of the third kinetic energy; the calculation formula of the maximum wind speed is:

In the above formula, V _max represents the maximum wind speed of natural wind when passing through the wind turbine rotor, E ₃ (max) represents the maximum value of the third kinetic energy of the wind turbine under any wind direction when the blade pitch angle is maximum, ρ represents the air density, S represents the area of the blade, Δα ₂ is the second angle between the wind direction and the blade surface, and τ is the safety factor, for example, it is set to 1.2 to compensate for the speed loss caused by friction.

S5. Obtain meteorological data of the monitored area within a period of time, and determine whether to output extreme weather alarm prompt information based on whether the corresponding wind speed under the corresponding wind direction is greater than the corresponding maximum wind speed. That is, if the meteorological data gives the wind direction and corresponding wind speed at a certain time, the object of comparison should also be the maximum wind speed of the fan blade data under the corresponding wind direction;

If yes, then output the alarm prompt information of extreme wind weather and end;

If not, then end.

The present invention obtains blade data and groups them according to wind direction to obtain a number of first basic data, then calculates the third kinetic energy received by the wind rotor under the corresponding wind direction, and then selects some third kinetic energies with larger values and higher data reliability by calculating the kinetic energy ratio, and corresponds the third kinetic energy to the pitch angle to obtain a number of groups of data to generate a database, and finally establishes a kinetic energy function between the pitch angle and the third kinetic energy, and calculates the third kinetic energy corresponding to the maximum pitch angle through the kinetic energy function, that is, the maximum third kinetic energy that the wind rotor can withstand, and then calculates the corresponding maximum wind speed through the third kinetic energy, so as to correspond the maximum third kinetic energy that the wind rotor can withstand under a certain wind direction with the wind speed, and then compares the wind speed and wind direction in a future period of time released by the meteorological station with the maximum wind speed in the corresponding wind direction, so as to realize that the strong wind weather greater than the maximum wind speed is classified as extreme strong wind weather, and an alarm is issued, so as to facilitate the operation and maintenance personnel to take necessary protective measures in time, thereby saving the operation and maintenance costs in the process of terrain detection and maintenance, and saving part of the cost of forecasting strong winds and extreme weather.

Corresponding to the regional extreme weather prediction method provided in the above embodiment, the present invention also provides a computer storage medium storing a computer program, which implements the steps of the regional extreme weather prediction method when executed.

The above implementation methods have been described in detail. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims (10)

1. A method of regional extreme weather prediction, the method comprising:

s1, acquiring historical meteorological data comprising the historical wind speed and the wind direction of a region to be monitored, and acquiring fan blade data comprising the fan blade rotating speed, the fan blade area, the pitch angle, the wind wheel plane and the number of the fan blades of each wind driven generator at a time corresponding to the historical meteorological data so as to generate basic data;

S2, calculating third kinetic energy in the wind direction when each wind turbine of the wind driven generator rotates according to the basic data, calculating the ratio of the third kinetic energy of each wind turbine of the wind driven generator to obtain a kinetic energy ratio, and selecting fan blade data in the kinetic energy ratio range to generate a database;

S3, extracting fan blade data of a plurality of wind driven generators with the maximum third kinetic energy corresponding to each wind direction at any moment according to a database, and establishing a functional relation model of pitch angles and the third kinetic energy to obtain a kinetic energy function;

S4, calculating a third maximum value of kinetic energy in each wind direction when the pitch angle is maximum according to the kinetic energy function, and calculating the maximum wind speed of natural wind when passing through the blades of the wind driven generator according to corresponding blade data;

S5, acquiring meteorological data in a period of time of the area to be monitored, and judging whether to output extreme weather alarm prompt information according to whether the corresponding wind speed in the corresponding wind direction is greater than the corresponding maximum wind speed;

if yes, outputting alarm prompt information of extremely strong wind weather, and ending;

if not, ending.

2. The extreme weather prediction method according to claim 1, characterized in that in step S2, it specifically comprises the steps of:

s21, setting a plurality of wind directions to generate a plurality of wind direction groups;

s22, dividing the basic data into a plurality of wind direction groups according to wind directions to obtain a plurality of first basic data;

S23, calculating second kinetic energy of each wind driven generator blade in the direction perpendicular to the plane of the wind wheel according to the first basic data;

s24, calculating third kinetic energy along the wind direction born by the wind wheel of the wind driven generator according to the second kinetic energy;

S25, selecting a plurality of wind wheels with the maximum third kinetic energy and corresponding fan blade data from the first basic data to generate second basic data;

s26, calculating the kinetic energy difference of the third kinetic energy of each wind wheel in the second basic data at any moment, selecting the third basic data according to the kinetic energy difference, calculating the ratio of the kinetic energy difference of each wind wheel at any moment according to the third basic data, and calculating the aggregation density of the kinetic energy difference ratio;

S27, setting a kinetic energy ratio range by taking the kinetic energy ratio with the maximum aggregation density as the center, and picking out fan blade data in the kinetic energy ratio range in the third basic data to generate a database.

3. The extreme weather prediction method according to claim 2, characterized in that in step S23, it specifically comprises the steps of:

S231, calculating first kinetic energy required by rotation of the wind wheel according to the fan blade data; the calculation formula of the first kinetic energy is as follows:

In the above formula, E ₁ represents the first kinetic energy required by the rotation of the wind wheel, N represents the number of blades on a single wind wheel corresponding to the wind driven generator, r ₁ and r ₂ respectively represent the rotation radius of the two end parts of the single blade when the single blade rotates, M represents the weight of the blade in unit volume, w represents the angular speed of the blade when the blade rotates, and r represents the radius of any position on the blade;

S232, constructing a wind wheel plane where the fan blades are positioned when rotating, and calculating second kinetic energy perpendicular to the wind wheel plane according to the first kinetic energy and the deflection angle of the fan blades; the calculation formula of the second kinetic energy is as follows:

In the above formula, E ₂ is the second kinetic energy, E ₁ is the first kinetic energy, and θ is the pitch angle.

4. The extreme weather prediction method according to claim 2, characterized in that in step S24, it specifically comprises the steps of:

s241, constructing an angle coordinate system positioned on a horizontal plane by taking the rotation axis of the fan blade as a circle center and taking the pitch angle as a positive value, and calculating a first included angle between the wind direction and the normal direction of the wind wheel plane according to historical meteorological data and the normal direction of the wind wheel plane; the calculation formula of the first included angle is as follows:

Δα₁＝α₁-α₂

In the above formula, Δα ₁ is a first angle between the wind direction and the wind wheel plane, α ₁ is an angle of the wind direction, and α ₂ is an angle normal to the wind wheel plane;

S242, calculating a second included angle between the wind direction and the normal direction of the blade surface according to the first included angle and the pitch angle; the calculation formula of the second included angle is as follows:

Δα₂＝θ-Δα₁

in the above formula, Δα ₂ is a second angle between the wind direction and the blade surface, θ is the pitch angle of the blade, and Δα ₁ is a first angle between the wind direction and the normal direction of the wind wheel plane;

S243, calculating third kinetic energy of the natural wind to the wind wheel according to the second included angle and the second kinetic energy, wherein a calculation formula of the third kinetic energy is as follows:

in the above formula, E ₃ represents the third kinetic energy of the natural wind to the wind wheel, E ₂ represents the second kinetic energy, and Δα ₂ represents the second included angle between the wind direction and the blade surface.

5. The extreme weather prediction method according to claim 2, characterized in that in step S26, it specifically comprises the steps of:

S261, calculating the kinetic energy difference of the third kinetic energy of each wind wheel at the next moment and the last moment; the calculation formula of the kinetic energy difference is as follows:

in the above formula, delta E ^i,i-1 represents the kinetic energy difference of any wind wheel at the ith moment and the (i-1) th moment, AndThird kinetic energy at i-th moment and i-1-th moment respectively;

s262, selecting fan blade data at the moment corresponding to the moment when the kinetic energy difference of the third kinetic energy at the same moment in the second basic data is positive or negative so as to generate third basic data;

S263, calculating the ratio of the kinetic energy difference between any two wind wheels in the third basic data to obtain a kinetic energy ratio, wherein the calculation formula of the kinetic energy ratio is as follows:

In the above formula, Δe _n,m represents the kinetic energy ratio of the nth wind wheel and the mth wind wheel in the third basic data at any time, and Δe _n and Δe _m represent the kinetic energy difference of the nth wind wheel and the mth wind wheel in the third basic data respectively;

s264, calculating the aggregation density of the kinetic energy ratio between any two wind wheels in the third basic data.

6. The extreme weather prediction method according to claim 1, characterized in that in step S3, it specifically comprises the steps of:

S31, extracting a plurality of fan blade data with the maximum third kinetic energy at any moment in a database to obtain first sample data;

S32, calculating an average value of third kinetic energy when the pitch angles in the first sample data are the same, so as to generate second sample data;

s33, constructing a kinetic energy function with independent variables from the minimum value to the maximum value of the pitch angle according to the pitch angle of the fan blades in the second sample data and the corresponding third kinetic energy data.

7. The extreme weather prediction method according to claim 1, characterized in that in step S4, it specifically comprises the steps of:

S41, calculating a third maximum kinetic energy of the wind driven generator in each wind direction when the pitch angle of the fan blade is maximum according to the kinetic energy function;

S42, calculating the maximum wind speed of the natural wind when the natural wind passes through the wind wheel of the wind driven generator according to the third maximum value of the kinetic energy.

8. The extreme weather prediction method according to claim 5, wherein in step S264, the calculation formula of the aggregate density is:

wherein,

In the above formula, M _n,m represents the aggregation density of the nth wind wheel and the mth wind wheel at any time, Δe _n,m represents the kinetic energy ratio of the nth wind wheel and the mth wind wheel at any time, R represents the statistical radius, μ represents the sign function, and j represents the kinetic energy ratio data of j times in the third basic data.

9. The extreme weather prediction method according to claim 7, wherein in step S42, the calculation formula of the maximum wind speed is:

In the above formula, V _max represents the maximum wind speed of natural wind when passing through the wind wheel of the wind power generator, E ₃ (max) represents the third maximum kinetic energy of the wind power generator in any wind direction when the blade pitch angle is maximum, ρ represents the air density, S represents the area of the blade, Δα ₂ is the second included angle between the wind direction and the blade surface, and τ is the safety factor.

10. A computer storage medium, characterized in that a computer program is stored, which computer program, when executed, implements the steps of the regional extreme weather prediction method according to any of claims 1 to 9.