Construction method of wind turbine wind speed prediction model and wind speed prediction method and system

Abstract

The invention provides a construction method of a wind turbine wind speed prediction model and a wind speed prediction method and system. The construction method of the wind turbine wind speed prediction model comprises the steps of obtaining first simulation operation data of a first wind turbine and second simulation operation data of a second wind turbine under preset wind condition parameters; extracting a first dynamic characteristic parameter of the first wind turbine from the first simulation operation data, and extracting a second dynamic characteristic parameter of the second wind turbine from the second simulation operation data; based on the first dynamic characteristic parameter, the first thrust coefficient and the second dynamic characteristic parameter, a preset wake flow model and the distance between the first wind turbine and the second wind turbine are adjusted, and a target wake flow model is obtained; the target wake flow model is used for acquiring the predicted wind speed of the second wind turbine. The wake flow attenuation is calculated by using the impeller diameter after blade deformation and the thrust coefficient, the calculation error of wind power plant data is effectively reduced, and the wind power plant wake flow evaluation level is improved.

Description

Technical Field

[0001] The present disclosure relates to the technical field of wind farm data simulation, and in particular to a method for constructing a wind speed prediction model for a wind turbine, a wind speed prediction method and a system. Background Art

[0002] In the actual operation of a wind farm, the incoming wind in the wind farm will produce a wake effect on the downstream wind turbines, causing the wind speed and power generation of the downstream wind turbines to be attenuated. Therefore, accurately calculating the wake and power generation attenuation in the wind farm is of great significance to improving the economic benefits of the wind farm.

[0003] At present, common wind farm fluid simulation and post-processing software such as Meteodyn WT, WindSim and WindPro have built-in multiple wake models to evaluate the wake loss of wind farms. Among them, the Jensen wake model is one of the most famous and widely used wake models. It provides a simple equation for wind speed attenuation in the wake. Its calculation formula is concise and clear, and it can quickly and effectively evaluate the wind farm wake and power generation attenuation. Thanks to the good balance between calculation accuracy and calculation efficiency, this model has been widely used in engineering applications.

[0004] At present, the horizontal axis three-blade has become the most mainstream form of wind turbine generator set used in offshore and onshore wind farms. Under the background of the large-scale capacity of single units and the cost reduction and efficiency improvement of power generation equipment, the flexibility of blades has become more and more obvious. Under the impetus of different wind speeds, the blades of wind turbines equipped with flexible blades will produce different degrees of deformation, which will cause the impeller diameter of the wind turbine to change with the wind speed. At the same time, the thrust coefficient (CT) curve will also change to varying degrees.

[0005] Therefore, with flexible blades now widely used, existing models and computational evaluation methods use fixed geometric parameters that are not dependent on the operating environment conditions of the wind turbine as input, while ignoring the influence of wake coupling between wind turbines in a wind farm. The comprehensive evaluation accuracy deviates from the actual operation of the wind farm. Summary of the invention

[0006] The technical problem to be solved by the present invention is to overcome the defect of inaccurate prediction of the wake velocity of a wind turbine with flexible blades in the prior art, and to provide a method for constructing a wind turbine wind speed prediction model, a wind speed prediction method, a system, equipment, a medium and a program product.

[0007] The present invention solves the above technical problems through the following technical solutions:

[0008] In a first aspect, a method for constructing a wind speed prediction model for a wind turbine is provided, comprising at least two wind turbines, wherein a first wind turbine is located upwind of a second wind turbine, and the construction method comprises:

[0009] Acquire first simulation operation data of the first wind turbine and second simulation operation data of the second wind turbine under preset wind condition parameters;

[0010] Extracting a first dynamic characteristic parameter of the first wind turbine from the first simulation operation data, and extracting a second dynamic characteristic parameter of the second wind turbine from the second simulation operation data;

[0011] The first dynamic characteristic parameter includes a first equivalent dynamic impeller size and a first thrust coefficient of the first wind turbine under preset wind condition parameters, and the second dynamic characteristic parameter includes a second equivalent dynamic impeller size of the second wind turbine under preset wind condition parameters;

[0012] A preset wake model is adjusted based on the first dynamic characteristic parameter, the first thrust coefficient and the second dynamic characteristic parameter, as well as the distance between the first wind turbine and the second wind turbine to obtain a target wake model; the target wake model is used to obtain the predicted wind speed of the second wind turbine.

[0013] Preferably, the first dynamic characteristic parameter further includes a first projection area of ​​the first wind turbine on a vertical plane, the second dynamic characteristic parameter further includes a second projection area and a second thrust coefficient of the second wind turbine on a vertical plane, and the step of adjusting the preset wake model based on the first dynamic characteristic parameter and the second dynamic characteristic parameter to obtain a target wake model includes:

[0014] Constructing a first piecewise interpolation calculation function corresponding to the first dynamic characteristic parameter and a second piecewise interpolation calculation function corresponding to the second dynamic characteristic parameter;

[0015] The first piecewise interpolation calculation function is used as an input of the preset wake model, and the preset wake model is adjusted based on the first piecewise interpolation calculation function and the second piecewise interpolation calculation function to obtain the target wake model.

[0016] Preferably, the step of constructing a first piecewise interpolation calculation function corresponding to the first dynamic characteristic parameter and a second piecewise interpolation calculation function corresponding to the second dynamic characteristic parameter comprises:

[0017] A first piecewise interpolation calculation function corresponding to the first dynamic characteristic parameter and a second piecewise interpolation calculation function corresponding to the second dynamic characteristic parameter are constructed by linear interpolation or spline interpolation.

[0018] Preferably, the preset wake model is a Jensen wake model, and the formula of the target wake model is:

[0019]

[0020] Among them, WT1 is the first wind turbine, WT2 is the second wind turbine, U WT1 is the wind speed at the front hub of the first wind turbine impeller, U WT2 is the predicted wind speed of the second wind turbine, A overlap (U WT1 ,U WT2 ) is a piecewise interpolation calculation function for the vertical projection overlap area of ​​the wake of the first wind turbine along the incoming flow direction on the impeller surface of the second wind turbine, is a piecewise interpolation calculation function for the swept area of ​​the dynamic impeller surface corresponding to the second wind turbine under the preset wind condition, is a segmented interpolation calculation function for the first dynamic equivalent impeller radius of the first wind turbine, is a piecewise interpolation calculation function for the second dynamic equivalent impeller radius of the second wind turbine, is the first thrust coefficient segmented interpolation calculation function of the first wind turbine, k is the wake diffusion coefficient, d cw It is the center distance between the first wind turbine and the second wind turbine in the plane perpendicular to the incoming flow direction.

[0021] In a second aspect, a method for predicting wind speed of a wind turbine in a wind farm is provided, wherein the wind farm includes N wind turbines, where N≥2, and the method for predicting wind speed includes:

[0022] Obtaining the position order of all the wind turbines relative to the wind direction;

[0023] The wind turbine located upwind of the two adjacent wind turbines is used as a first wind turbine, and the other wind turbine is used as a second wind turbine;

[0024] Acquire a first dynamic characteristic parameter of the first wind turbine and a second dynamic characteristic parameter of the second wind turbine;

[0025] Inputting the first dynamic characteristic parameter and the second dynamic characteristic parameter into a target wake model to obtain a predicted wind speed of the second wind turbine;

[0026] Wherein, the target wake model is obtained based on the method for constructing the wind turbine wind speed prediction model described in the first aspect.

[0027] Preferably, the step of obtaining the position order of all the wind turbines relative to the wind direction comprises:

[0028] Obtaining coordinate information of each wind turbine;

[0029] Selecting one of the wind turbines as a reference wind turbine;

[0030] Calculate the projection of the line vector between each of the remaining wind turbines and the reference wind turbine on the wind direction vector of the wind farm to obtain the projection distance between the corresponding wind turbine and the reference wind turbine;

[0031] In response to the projection distance being positive, the other wind turbine is located upwind of the reference wind turbine;

[0032] Based on the projection distance between each wind turbine and other wind turbines, a position ranking of all the wind turbines is obtained.

[0033] Preferably, the step of inputting the first dynamic characteristic parameter and the second dynamic characteristic parameter into a target wake model to obtain the predicted wind speed of the second wind turbine comprises:

[0034] Obtaining a static impeller size of the second wind turbine;

[0035] Using the static impeller size of the second wind turbine as an input of the target wake model, calculating an initial predicted wind speed of the second wind turbine;

[0036] Substituting the initial predicted wind speed into the target wake model, and calculating the predicted wind speed to be verified;

[0037] Perform residual convergence judgment on the predicted wind speed to be verified and the initial predicted wind speed to verify whether the predicted wind speed to be verified is true;

[0038] In response to a verification result of the predicted wind speed to be verified being true, the predicted wind speed to be verified is used as the predicted wind speed of the second wind turbine.

[0039] Preferably, the wind speed prediction method further includes:

[0040] Based on the position sorting of all the wind turbines, starting from the starting wind turbine located at the most upstream position, sequentially obtaining the wind speed loss of each wind turbine to each wind turbine located in the downstream wind direction;

[0041] The predicted wind speed is iteratively updated based on the wind speed loss to obtain a target predicted wind speed.

[0042] Preferably, the step of iteratively updating the predicted wind speed based on the wind speed loss to obtain a target predicted wind speed comprises:

[0043] Obtaining N-1 wind speed deficits of the N-1 upstream wind turbines in the upwind direction from the downstream wind turbine at the N-th position to the downstream wind turbine at the N-th position;

[0044] Superimposing N-1 wind speed deficits to obtain a superimposed wind speed deficit corresponding to the downstream wind turbine at the Nth position;

[0045] The predicted wind speed corresponding to the downstream wind turbine at the Nth position is updated based on the superimposed wind speed loss to obtain the target predicted wind speed.

[0046] In a third aspect, a system for constructing a wind turbine wind speed prediction model is provided, comprising at least two wind turbines, wherein a first wind turbine is located upwind of a second wind turbine, the construction system comprising a simulation data acquisition module, a dynamic parameter extraction module, and a target model adjustment module;

[0047] The simulation data acquisition module is used to acquire first simulation operation data of the first wind turbine and second simulation operation data of the second wind turbine under preset wind condition parameters;

[0048] The dynamic parameter extraction module is used to extract the first dynamic characteristic parameter of the first wind turbine from the first simulation operation data, and extract the second dynamic characteristic parameter of the second wind turbine from the second simulation operation data;

[0049] The first dynamic characteristic parameter includes a first equivalent dynamic impeller size of the first wind turbine under preset wind condition parameters, and the second dynamic characteristic parameter includes a second equivalent dynamic impeller size of the second wind turbine under preset wind condition parameters;

[0050] The target model adjustment module is used to adjust the preset wake model based on the first dynamic characteristic parameter and the second dynamic characteristic parameter to obtain a target wake model;

[0051] The target wake model is used to obtain the predicted wind speed of the second wind turbine.

[0052] In a fourth aspect, a wind speed prediction system for a wind turbine in a wind farm is provided, wherein the wind farm includes N wind turbines, where N≥2, and the wind speed prediction system includes a position acquisition module, a pairing module, a dynamic parameter acquisition module, and a predicted wind speed calculation module:

[0053] The position acquisition module is used to obtain the position order of all the wind turbines relative to the wind direction;

[0054] The pairing module is used to use the wind turbine located upwind of the two adjacent wind turbines as the first wind turbine and the other wind turbine as the second wind turbine;

[0055] The dynamic parameter acquisition module is used to acquire a first dynamic characteristic parameter of the first wind turbine and a second dynamic characteristic parameter of the second wind turbine;

[0056] The predicted wind speed calculation module is used to input the first dynamic characteristic parameter and the second dynamic characteristic parameter into a target wake model to obtain a predicted wind speed of the second wind turbine;

[0057] Wherein, the target wake model is obtained based on the construction system of the wind turbine wind speed prediction model described in the third aspect.

[0058] In a fifth aspect, an electronic device is provided, comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, wherein when the processor executes the computer program, it implements the method for constructing a wind speed prediction model for a wind turbine as described in the first aspect, or the method for predicting the wind speed of a wind turbine in a wind farm as described in the second aspect.

[0059] In a sixth aspect, a computer storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for constructing a wind speed prediction model for a wind turbine as described in the first aspect, or the method for predicting the wind speed of a wind turbine in a wind farm as described in the second aspect is implemented.

[0060] In a seventh aspect, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the method for constructing a wind speed prediction model for a wind turbine as described in the first aspect, or the method for predicting wind speed of a wind turbine in a wind farm as described in the second aspect.

[0061] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present disclosure.

[0062] The positive progressive effect of the present invention is that by considering different wind speeds, the impeller diameter and thrust coefficient after blade deformation are used to calculate the wake attenuation, thereby effectively reducing the calculation error of the actual wind speed and power generation of the wind farm, accurately understanding the actual operating conditions of the wind farm, and improving the level of wind farm wake assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A flow chart of a method for constructing a wind turbine wind speed prediction model provided by an exemplary embodiment of the present disclosure;

[0064] Figure 2 A schematic diagram of the dynamic equivalent impeller size of a wind turbine in a method for constructing a wind turbine wind speed prediction model provided by an exemplary embodiment of the present disclosure;

[0065] Figure 3 A flowchart of step S103 in a method for predicting wind speed of a wind turbine in a wind farm provided by an exemplary embodiment of the present disclosure;

[0066] Figure 4A first model schematic diagram of a target wake model in a method for predicting wind speed of a wind turbine in a wind farm provided by an exemplary embodiment of the present disclosure;

[0067] Figure 5 A second model schematic diagram of a target wake model in a method for predicting wind speed of a wind turbine in a wind farm provided by an exemplary embodiment of the present disclosure;

[0068] Figure 6 A flow chart of a method for predicting wind speed of a wind turbine in a wind farm provided by an exemplary embodiment of the present disclosure;

[0069] Figure 7 A flowchart of step S201 in a method for predicting wind speed of a wind turbine in a wind farm provided by an exemplary embodiment of the present disclosure;

[0070] Figure 8 A first schematic diagram of the position sorting of wind turbines in a method for predicting wind speed of wind turbines in a wind farm provided by an exemplary embodiment of the present disclosure;

[0071] Fig. 9 A second schematic diagram of wind turbine position sorting in a method for predicting wind speed of wind turbines in a wind farm provided by an exemplary embodiment of the present disclosure;

[0072] Fig.10 A flowchart of step S204 in a method for predicting wind speed of a wind turbine in a wind farm provided by an exemplary embodiment of the present disclosure;

[0073] Fig.11 A third schematic diagram of wind turbine position sorting in a method for predicting wind speed of wind turbines in a wind farm provided by an exemplary embodiment of the present disclosure;

[0074] Fig.12 A schematic diagram of post-wake predicted wind speed based on a traditional Jensen wake model in a method for predicting wind speed of a wind turbine in a wind farm provided by an exemplary embodiment of the present disclosure;

[0075] Fig.13 A schematic diagram of post-wake predicted wind speed based on a target wake model in a method for predicting wind speed of a wind turbine in a wind farm provided by an exemplary embodiment of the present disclosure;

[0076] Fig.14 A schematic diagram of modules of a system for constructing a wind turbine wind speed prediction model provided by an exemplary embodiment of the present disclosure;

[0077] Fig.15 A module schematic diagram of a wind speed prediction system for a wind turbine in a wind farm provided by an exemplary embodiment of the present disclosure;

[0078] Fig.16 A schematic diagram of the hardware structure of an electronic device provided by an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0079] The present invention is further described below by way of examples, but the present invention is not limited to the scope of the examples.

[0080] Prefixes such as "first" and "second" are used in the embodiments of the present disclosure only to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers to distinguish description objects in the embodiments of the present disclosure does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and no unnecessary limitation should be constituted due to the use of such prefixes. In addition, in the description of the present embodiment, unless otherwise specified, the meaning of "plurality" is two or more.

[0081] Example 1

[0082] This embodiment provides a method for constructing a wind speed prediction model for a wind turbine, comprising at least two wind turbines, wherein a first wind turbine is located upwind of a second wind turbine, such as Figure 1 As shown, the construction method includes:

[0083] S101, obtaining first simulation operation data of the first wind turbine and second simulation operation data of the second wind turbine under preset wind condition parameters;

[0084] S102, extracting a first dynamic characteristic parameter of the first wind turbine from the first simulation operation data, and extracting a second dynamic characteristic parameter of the second wind turbine from the second simulation operation data;

[0085] The first dynamic characteristic parameter includes a first equivalent dynamic impeller size of the first wind turbine under preset wind condition parameters, and the second dynamic characteristic parameter includes a second equivalent dynamic impeller size of the second wind turbine under preset wind condition parameters;

[0086] S103, adjusting a preset wake model based on the first dynamic characteristic parameter, the first thrust coefficient, and the second dynamic characteristic parameter, and the distance between the first wind turbine and the second wind turbine to obtain a target wake model;

[0087] The target wake model is used to obtain the predicted wind speed of the second wind turbine.

[0088] In step S101, a database of wind turbine operating parameters for evaluating wind farms under different incoming wind conditions, including turbulence, wind shear and / or wind speed, is obtained through load flexible modal simulation. The blades are simplified into non-uniform cantilever beams and their deformations are calculated using geometrically accurate beam theory. Combined with blade element momentum theory, a nonlinear structural dynamics equation of the blades considering aeroelasticity is established to achieve dynamic response calculation of deformation of large wind turbine blades. Compared with traditional methods, this method reflects nonlinear factors more accurately, and the calculated deformation is closer to actual working conditions.

[0089] In step S102, the dynamic load simulation results of the wind turbine at different inflow wind speeds under preset wind condition parameters are calculated and extracted from the simulation operation data, wherein the preset wind speed covers the design cut-in wind speed to the design cut-out wind speed of the wind turbine. Figure 2 As shown in the figure, the x-axis represents the horizontal direction of the wind farm ground along the wind flow direction, the z-axis represents the vertical ground direction of the wind farm perpendicular to the wind flow direction, θ is the angle between the impeller and the z-axis, φ is the pitch angle of the wind turbine relative to the x-axis, the gray non-standard ellipse in the figure is the projection surface of the nominal impeller radius along the x-axis, and the dotted circle is the projection circle of the equivalent impeller radius along the x-axis. Since the projection area of ​​the impeller along the x-axis is a non-standard ellipse, the dynamic impeller equivalent size under the corresponding wind condition and inflow speed, such as the dynamic impeller equivalent diameter or the dynamic impeller equivalent radius, is used as the geometric parameter input of the actual wind turbine wake model.

[0090] In step S103, the static geometric impeller size is used in the preset wake model, and the dynamic impeller equivalent size is adjusted to the static geometric impeller size parameter corresponding to the preset wake model to obtain a target wake model that takes into account the correction of blade flexibility characteristics.

[0091] The target wake model corrected by considering the flexible characteristics of the blades is used to solve the predicted wind speed of the second wind turbine located in the rear row of the first wind turbine after being affected by the wake; wherein the predicted wind speed may be the wind speed after the wake at the hub height of the second wind turbine.

[0092] In this scheme, by considering different wind speeds, the impeller diameter and thrust coefficient after blade deformation are used to calculate the wake attenuation, which effectively reduces the calculation error of the actual wind speed and power generation of the wind farm, accurately understands the actual operating conditions of the wind farm, and improves the level of wind farm wake assessment.

[0093] As an implementable manner, the first dynamic characteristic parameter further includes a first projection area of ​​the first wind turbine on a vertical plane, and the second dynamic characteristic parameter further includes a second projection area and a second thrust coefficient of the second wind turbine on a vertical plane, such as Figure 3 As shown, step S103 includes:

[0094] S1031, constructing a first piecewise interpolation calculation function corresponding to the first dynamic characteristic parameter and a second piecewise interpolation calculation function corresponding to the second dynamic characteristic parameter;

[0095] S1032: Using the first piecewise interpolation calculation function as an input of the preset wake model, adjusting the preset wake model based on the first piecewise interpolation calculation function and the second piecewise interpolation calculation function to obtain the target wake model.

[0096] In this scheme, according to the discrete step length results of the inverse calculation and considering the data continuity of the actual application scenario, each wind turbine constructs a piecewise interpolation calculation function for dynamic parameters: the piecewise interpolation calculation function of the impeller projection area perpendicular to the incoming flow direction is recorded as A(V i ), the segmented interpolation calculation function of the dynamic equivalent impeller diameter is recorded as D(V i ) and the piecewise interpolation calculation function of the thrust coefficient is denoted as C T (V i ). We can also construct a piecewise interpolation calculation function for power, denoted as P(V i ).

[0097] As an implementable manner, the step of constructing a first piecewise interpolation calculation function corresponding to the first dynamic characteristic parameter and a second piecewise interpolation calculation function corresponding to the second dynamic characteristic parameter includes:

[0098] A first piecewise interpolation calculation function corresponding to the first dynamic characteristic parameter and a second piecewise interpolation calculation function corresponding to the second dynamic characteristic parameter are constructed by linear interpolation or spline interpolation.

[0099] In this solution, the linear interpolation method is adopted, which is based on the first-order polynomial, and the calculation formula is simple and easy to implement. When two dynamic parameter data points are known, the interpolation result of any position between the two points can be quickly calculated. The function image obtained by linear interpolation is smooth, avoiding the discontinuous step phenomenon between the data points. In the process of linear interpolation, the position accuracy of the interpolation point is relatively high, which can meet the needs of most application scenarios; the spline interpolation method performs low-order interpolation on each interval and splices it into a piecewise function as the interpolation function. It can ensure that the entire interpolation curve is smooth and there is no interpolation cusp, thereby improving the accuracy and smoothness of the interpolation result. The spline interpolation method has good numerical stability. When there are many data points or the data distribution is more complex, the spline interpolation method can still give stable and reliable interpolation results.

[0100] As an achievable manner, the preset wake model is the Jensen wake model, and the formula of the target wake model is:

[0101]

[0102] Among them, WT1 is the first wind turbine, WT2 is the second wind turbine, U WT1 is the wind speed at the front hub of the first wind turbine impeller, U WT2 is the predicted wind speed of the second wind turbine, A overlap (U WT1 ,U WT2 ) is a piecewise interpolation calculation function for the vertical projection overlap area of ​​the wake of the first wind turbine along the incoming flow direction on the impeller surface of the second wind turbine, is a piecewise interpolation calculation function for the swept area of ​​the dynamic impeller surface corresponding to the second wind turbine under the preset wind condition, is a segmented interpolation calculation function for the first dynamic equivalent impeller radius of the first wind turbine, is a piecewise interpolation calculation function for the second dynamic equivalent impeller radius of the second wind turbine, is the first thrust coefficient segmented interpolation calculation function of the first wind turbine, k is the wake diffusion coefficient, d cw It is the center distance between the first wind turbine and the second wind turbine in the plane perpendicular to the incoming flow direction.

[0103] In this scheme, if Figure 4 and Figure 5 As shown, Figure 4 and Figure 5 Schematic diagram of the wake effect of the Jensen wake model modified to take into account the flexibility of the blade. Figure 4 The x-axis represents the horizontal direction of the wind farm ground along the wind flow direction, and the y-axis represents the horizontal direction of the wind farm ground perpendicular to the wind flow direction. Figure 5 The y-axis and Figure 4 The z-axis represents the vertical ground direction of the wind farm perpendicular to the wind flow direction. The dynamic impeller equivalent size is adjusted to the corresponding static geometric impeller size parameters in the preset wake model. At the same time, the vertical projection area of ​​the dynamic impeller surface of the wind turbines in the upwind and downwind directions is changed into the correlation function of the central wind speed of the front hub of the first wind turbine impeller and the predicted wind speed of the second wind turbine, and the dynamic swept area of ​​the second wind turbine in the downwind direction. The Jensen wake model corrected by considering the flexible characteristics of the blades is obtained, which effectively reduces the calculation error of the actual wind speed and power generation of the wind farm, accurately understands the actual operation status of the wind farm, and improves the level of wind farm wake assessment.

[0104] The method for constructing a wind turbine wind speed prediction model provided in this embodiment calculates the wake attenuation using the impeller diameter and thrust coefficient after blade deformation under different wind speeds, adjusts the preset wake model, and the obtained target wake model can adapt to the changes in the wind turbine impeller and output accurate prediction results.

[0105] Example 2

[0106] This embodiment provides a method for predicting the wind speed of a wind turbine in a wind farm. Figure 6 As shown, the wind farm includes N wind turbines, N≥2, and the wind speed prediction method includes:

[0107] S201, obtaining the position order of all the wind turbines relative to the wind direction;

[0108] S202, using the wind turbine located upwind of the two adjacent wind turbines as a first wind turbine and the other wind turbine as a second wind turbine;

[0109] S203, obtaining a first dynamic characteristic parameter of the first wind turbine and a second dynamic characteristic parameter of the second wind turbine;

[0110] S204, inputting the first dynamic characteristic parameter and the second dynamic characteristic parameter into a target wake model to obtain a predicted wind speed of the second wind turbine;

[0111] Wherein, the target wake model is obtained based on the method for constructing the wind turbine wind speed prediction model described in Example 1.

[0112] In this solution, after sorting the wind farm based on wind direction, two adjacent wind turbines are based on the target wake model in Example 1. By considering different wind speeds, the impeller diameter and thrust coefficient after blade deformation are used to calculate the wake attenuation, and the predicted wind speed of the second wind turbine located downwind after being affected by the wake of the first wind turbine is predicted, thereby effectively reducing the calculation error of the actual wind speed and power generation of the wind farm, accurately understanding the actual operating conditions of the wind farm, and improving the level of wind farm wake assessment.

[0113] As a feasible approach, Figure 7 As shown, step S201 includes:

[0114] S2011, obtaining coordinate information of each wind turbine;

[0115] S2012, selecting one of the wind turbines as a reference wind turbine;

[0116] S2013, calculating the projection of the line vector between each of the remaining wind turbines and the reference wind turbine on the wind direction vector of the wind farm, to obtain the projection distance between the corresponding wind turbine and the reference wind turbine;

[0117] S2014: In response to the projection distance being positive, the other wind turbine is located upwind of the reference wind turbine;

[0118] S2015: Obtaining a position ranking of all the wind turbines based on the projection distance between each wind turbine and the other wind turbines.

[0119] In this scheme, the scope of application includes but is not limited to flat terrain on land, offshore wind farms, and complex mountain wind farms. For this purpose, it is necessary to introduce the concept of grid wind acceleration factor in the wind farm, and construct the theoretical hub height inflow wind speed relationship between the machine sites of the wind farm through the wind acceleration factor.

[0120] The specific method is to use CFD (Computational Fluid Dynamics) or linear wind flow model commonly used in wind resource micro-site selection work, taking into account the influence of terrain and landform to calculate and obtain the wind farm The wake vortices at each aircraft station in the sector direction affect the front wind acceleration factors a1, a2, ...a n Assuming that the reference point is U0, and the wind acceleration factor is a0, the wind speed of the n wind turbines in the field can be obtained by extrapolation. T1~T in sector direction n The wind speed scalar U1~U2 before the wake at the hub height of the engine station n It can be expressed as:

[0121]

[0122] like Figure 8 As shown, assuming that there are n wind turbines in a wind farm, for any simulation calculation of the wind flow direction S in the sector, the direction vector is recorded as Get the plane coordinates (x m ,y m ) is denoted as WT m , and the coordinates (x0, y0) of any current wind turbine are recorded as WT0, WT0 is used as the reference wind turbine, where m = 1, 2, 3, ..., n.

[0123] First, calculate the connection between all wind turbines in the field and the reference wind turbine WT0. m Connection to reference wind turbine WT0 Vector in The projection of the direction vector is the direction of the wind flow between the two wind turbines. Projection distance:

[0124]

[0125] Among them, θ m It is the difference between the sector wind direction angle and the azimuth of the line connecting the centers of the impellers at the upstream and downstream positions. m is positive, indicating that the wind turbine WTm The position of the machine is upwind of the reference wind turbine WT0; if the projection distance L m is negative, indicating that the wind turbine WT m The position of the wind turbine is downwind of the reference wind turbine WT0, and WT m Wind direction with WT0 The upstream and downstream position relationship of the machine location below.

[0126] like Fig. 9 As shown, all wind turbines in the field are arranged at a projection distance L m Sort from large to small. If the values ​​are equal, sort them in the order of calculation. Finally, the wind turbines are arranged along the direction of the wind flow. Sort from upstream to downstream in the horizontal plane and renumber all n wind turbines as T1, T2, ...T n .

[0127] Iterative calculation from upstream to downwind The influence of wakes between n wind turbines in the sector direction. By sorting the positions of wind turbines, the predicted wind speed of each wind turbine after being affected by the wake of the wind turbine in the upwind direction can be calculated in turn, and the predicted wind speed of all wind turbines in the field can be calculated. Where i=1,2,3,…,n.

[0128] This scheme provides a physical process that is more in line with the gradual conduction and superposition of the wake from upstream to downstream of a wind farm, ensuring that the hub center height wind speed participating in the wake calculation of each wind turbine generator set during the calculation process is the wind speed after considering the influence of the wake of all the wind turbines in the front row, so that the wake influence process between the machine sites from upstream to downstream in the wind farm can be more accurately characterized.

[0129] As a feasible approach, Fig.10 As shown, step S204 includes:

[0130] S2041. Obtain the static impeller size of the second wind turbine;

[0131] S2042, using the static impeller size of the second wind turbine as an input of the target wake model, and calculating an initial predicted wind speed of the second wind turbine;

[0132] S2043, substituting the initial predicted wind speed into the target wake model to calculate and obtain the predicted wind speed to be verified;

[0133] S2044, performing residual convergence judgment between the predicted wind speed to be verified and the initial predicted wind speed, and verifying whether the predicted wind speed to be verified is true;

[0134] S2045: In response to a verification result of the predicted wind speed to be verified being true, using the predicted wind speed to be verified as the predicted wind speed of the second wind turbine.

[0135] In this scheme, different from the traditional Jensen model, in solving the predicted wind speed of the second wind turbine, the geometric parameter input of the first wind turbine in the upwind direction is changed from the static impeller size parameter to the dynamic equivalent impeller size parameter, considering that the vertical projection area of ​​the dynamic impeller surface of the wind turbines in the upwind and downwind directions becomes a correlation function between the central wind speed of the front hub of the impeller of the first wind turbine and the predicted wind speed of the second wind turbine, the dynamic swept area of ​​the second wind turbine in the downwind direction also needs to be solved by the predicted wind speed of the second wind turbine, that is, it is necessary to obtain the dynamic equivalent impeller radius of the first wind turbine and the dynamic equivalent impeller diameter of the second wind turbine through the interpolation function of the corresponding dynamic parameters of the model in the simulation operation data, and then complete the calculation of the segmented interpolation calculation function of the vertical projection overlapping area of ​​the wake of the first wind turbine along the incoming flow direction on the impeller surface of the second wind turbine and the segmented interpolation calculation function of the dynamic impeller surface swept area corresponding to the second wind turbine under the preset wind conditions.

[0136] The specific solution steps are as follows:

[0137] First, assume that the rotor diameter of the second wind turbine WT2 at the downstream position is the static size D 2steady Perform initialization calculations so that The term can be simplified to Direct calculation.

[0138] Substitution The calculation formula is used to solve the initial static solution of the wake wind speed at the hub height of the initial WT2 wind turbine:

[0139]

[0140] The initial static solution U WT2 0 The target wake model considering the flexible characteristics of the blade is brought back to continue the calculation to solve the predicted wind speed to be verified

[0141]

[0142] Based on further solution results, use the residual convergence judgment method to judge Is it true, where residual1 is the preset solution residual.

[0143] If the residual judgment condition is not met, continue to Back and Calculate the iterative predicted wind speed Continue to judge Is it true? Repeat the above loop iteration until the residual judgment requirement is met or the maximum number of iterations it is reached. max1 .

[0144] If the residual judgment condition is met, the predicted wind speed to be verified is The predicted wind speed of the second wind turbine is

[0145] Finally, the predicted wind speed of the second wind turbine in the rear row behind the wake is obtained after considering the dynamic parameter characteristics of the front and rear wind turbine impellers.

[0146] As an achievable manner, the wind speed prediction method further includes:

[0147] Based on the position sorting of all the wind turbines, starting from the starting wind turbine located at the most upstream position, sequentially obtaining the wind speed loss of each wind turbine to each wind turbine located in the downstream wind direction;

[0148] The predicted wind speed is iteratively updated based on the wind speed loss to obtain a target predicted wind speed.

[0149] In this scheme, the physical process of the gradual conduction and superposition of the wake from upstream to downstream of the wind farm is followed, which ensures that the hub center height wind speed of each wind turbine participating in the wake calculation during the calculation process is the wind speed after considering the influence of the wake of all the wind turbines in the front row. This allows a more accurate portrayal of the wake influence process between machine sites from upstream to downstream in the wind farm, thereby achieving accurate prediction of the wind speed of the wind turbine.

[0150] As an achievable manner, the step of iteratively updating the predicted wind speed based on the wind speed loss to obtain a target predicted wind speed includes:

[0151] Obtaining N-1 wind speed deficits of the N-1 upstream wind turbines in the upwind direction from the downstream wind turbine at the N-th position to the downstream wind turbine at the N-th position;

[0152] Superimposing N-1 wind speed deficits to obtain a superimposed wind speed deficit corresponding to the downstream wind turbine at the Nth position;

[0153] The predicted wind speed corresponding to the downstream wind turbine at the Nth position is updated based on the superimposed wind speed loss to obtain the target predicted wind speed.

[0154] In this scheme, when the number of wind turbines in the wind farm is greater than two, the calculation is performed iteratively from upstream to downstream. The wake effect between n wind turbines in the sector direction, and the wind speed after the wake of all wind turbines in the sector are calculated Where i=1,2,3,…,n.

[0155] In the first step, according to the wind speed before the wake of the T1 wind turbine in the S sector, the interpolation function of the dynamic parameters corresponding to the model in the table is obtained through the preset dynamic characteristic table under the environmental conditions of the wind turbine site, and the inflow wind speed of the T1 wind turbine is calculated. The dynamic equivalent impeller diameter D1(U1) and thrust coefficient of the unit under

[0156] In the second step, the wake loss caused by the T1 wind turbine to the downstream n-1 wind turbines is set as:

[0157]

[0158] in,

[0159] Use T1 downstream wind turbine Simplified to

[0160] The initialization parameters complete the preliminary calculation.

[0161] Calculate the wind speed loss δV caused by the wake effect of wind turbine T1 on all downstream wind turbines 1→i 0 , then the wind speed after the wake of all downstream wind turbines after considering the influence of the wake of wind turbine T1 can be expressed as:

[0162]

[0163] Update T2~T n Wind speed of the wind turbine after being affected by the wake of wind turbine T1 Where i=2,3,…,n.

[0164] The third step is to calculate the wind speed after the wake of the T2 wind turbine. Calculate the wake effect of T2 wind turbine on all downstream wind turbines:

[0165]

[0166] in,

[0167] Use T2 downstream wind turbine Simplified to The initialization parameters are used to complete the initial iteration.

[0168] The wake wind speed effects caused by wind turbines T1 and T2 can be superimposed using the linear sum or square sum wake superposition method.

[0169] In this scheme, the linear and superposition methods are used to illustrate that the wind speed after the wake of the downstream wind turbine after considering the influence of the wake of the wind turbines T1 and T2 can be expressed as Update T3~T n The wind speed after the wind turbine wake, where i = 3, 4, ..., n.

[0170] Step 4: By analogy, finally according to T n-1 The wind speed behind the wake is calculated as T n-1 Wind turbine to T n The wake of the wind turbine affects δV n-1→n 0 , T n Wind speed after the wind turbine wake Update T n The wind speed behind the wind turbine's wake.

[0171] The fifth step is to calculate the wake wind speed of all aircraft positions obtained through the first round of initialization. Re-substitute into steps 1 to 4 and update the downstream wind turbine at each step is the wind speed after the wake of the above-mentioned aircraft positions The result value is used for the second round of downwind wake calculation iteration.

[0172] Update the wake loss calculation expression to a dynamic expression:

[0173]

[0174] Among them, j = 1, 2, ..., n-1, i = j + 1, ..., n. The wind speed after the wake of the whole field station obtained by the second round of calculation is Determine the position of any machine for two rounds of iterations Is it true, where residual2 is the preset solution residual.

[0175] If the residual judgment condition is not met, continue to Back band δV j→i Repeat the iteration until the wind speed difference after two rounds of iterative wake vortex at any station meets the residual accuracy requirement, or the maximum number of iteration steps it is reached. max2 .

[0176] The final solution is the wind speed after the wake of the whole station:

[0177] The working principle of the wind speed prediction method for wind turbines in a wind farm of this embodiment is specifically described below with an example:

[0178] The wind turbine generator set is taken as the object of the wind turbine wake calculation method considering the correction of blade flexibility characteristics. Among them, the nominal static impeller diameter D of the wind turbinesteady is 230m, corresponding to the nominal static impeller radius r steady The design cut-in wind speed V cutin =3m / s, to cut-out wind speed V cutout =25m / s.

[0179] Through load flexible modal simulation, a database of wind turbine operating parameters for evaluating wind farms under different incoming wind conditions including turbulence, wind shear and / or wind speed is obtained. From the wind turbine operating parameter database, the dynamic load simulation results of wind turbines at different inflow wind speeds under preset wind condition parameters are calculated and extracted from the simulation operation data, and the dynamic data of the dynamic characteristics table of wind turbine site environmental parameters in Table 1 are obtained.

[0180] Table 1: Dynamic characteristics of wind turbine site environmental parameters

[0181] 25 39117.8 223.17 0.0150 -2.97

[0182] Build as Fig.11 The example of the front and back arrangement of the four wind turbines shown in the figure has an inflow free stream wind speed of 8.0 m / s, and the front and rear spacing of the wind turbines in the x-axis direction is 5 times the nominal rotor diameter. Turbine1 is under the influence of the full wake of Turbine0, Turbine2 is affected by the full wake of Turbine0 and the partial wake of Turbine1, and Turbine3 is under the influence of the full wake of Turbine0 and the partial wake of Turbine1 and Turbine2, covering the full wake and partial wake conditions in common wind farms.

[0183] The algorithm for superimposing the wind speed loss of the front and rear wind turbines is linear and. Based on the traditional Jensen wake model, the static impeller size is used and the wind speed before the wake of the wind turbine hub center is substituted into the wake model to calculate the wind speed after the wake of the rear wind turbine. Fig.12 shown.

[0184] Then, the target wake model considering the flexible characteristics of the blades in this embodiment is adopted, and the downwind wake transfer iterative algorithm is used. The calculation results of the dynamic impeller parameters corresponding to the wind speed after the real wake at the hub center of the wind turbine are as follows: Fig.13 shown.

[0185] The difference between the calculation results of the predicted wind speed of the second wind turbine after the wake of this embodiment and the calculation results of the existing calculation method is shown in Table 2:

[0186] Table 2: Comparison of the results of the predicted wind speed calculation methods for the second wind turbine after the wake

[0187]

[0188] Among them, the thrust coefficient of Turbine0 (C T ) is 0.6708, the thrust coefficient of Turbine1 is 0.7649, the thrust coefficient of Turbine2 is 0.7776, and the thrust coefficient of Turbine3 is 0.7666.

[0189] In this embodiment, a target wake model that takes into account the flexibility characteristics of blades is used to effectively reduce the calculation error of the actual wind speed and power generation of the wind farm, accurately understand the actual operating conditions of the wind farm, and improve the level of wind farm wake assessment.

[0190] The wind speed prediction method for wind turbines in a wind farm provided in this embodiment calculates the wake attenuation using the impeller diameter and thrust coefficient after blade deformation under different wind speeds, thereby effectively reducing the calculation error of the actual wind speed and power generation of the wind farm, accurately understanding the actual operating conditions of the wind farm, and improving the level of wind farm wake assessment.

[0191] Example 3

[0192] This embodiment provides a system 100 for constructing a wind turbine wind speed prediction model, comprising at least two wind turbines, wherein a first wind turbine is located upwind of a second wind turbine. Fig.14 As shown, the construction system 100 includes a simulation data acquisition module 101, a dynamic parameter extraction module 102 and a target model adjustment module 103;

[0193] The simulation data acquisition module 101 is used to acquire first simulation operation data of the first wind turbine and second simulation operation data of the second wind turbine under preset wind condition parameters;

[0194] The dynamic parameter extraction module 102 is used to extract the first dynamic characteristic parameter of the first wind turbine from the first simulation operation data, and to extract the second dynamic characteristic parameter of the second wind turbine from the second simulation operation data;

[0195] The first dynamic characteristic parameter includes a first equivalent dynamic impeller size of the first wind turbine under preset wind condition parameters, and the second dynamic characteristic parameter includes a second equivalent dynamic impeller size of the second wind turbine under preset wind condition parameters;

[0196] The target model adjustment module 103 is used to adjust the preset wake model based on the first dynamic characteristic parameter and the second dynamic characteristic parameter to obtain a target wake model;

[0197] The target wake model is used to obtain the predicted wind speed of the second wind turbine.

[0198] As an implementable manner, the first dynamic characteristic parameter further includes a first projection area of ​​the first wind turbine on a vertical plane, the second dynamic characteristic parameter further includes a second projection area and a second thrust coefficient of the second wind turbine on a vertical plane, and the target model adjustment module 103 includes a piecewise interpolation calculation unit and an adjustment unit;

[0199] A piecewise interpolation calculation unit, used to construct a first piecewise interpolation calculation function corresponding to the first dynamic characteristic parameter and a second piecewise interpolation calculation function corresponding to the second dynamic characteristic parameter;

[0200] An adjustment unit is used to use the first piecewise interpolation calculation function as an input of the preset wake model, and adjust the preset wake model based on the first piecewise interpolation calculation function and the second piecewise interpolation calculation function to obtain the target wake model.

[0201] As an implementable manner, the piecewise interpolation calculation unit is further used to construct a first piecewise interpolation calculation function corresponding to the first dynamic characteristic parameter and a second piecewise interpolation calculation function corresponding to the second dynamic characteristic parameter by linear interpolation or spline interpolation.

[0202] As an achievable manner, the preset wake model is the Jensen wake model, and the formula of the target wake model is:

[0203]

[0204] Among them, WT1 is the first wind turbine, WT2 is the second wind turbine, U WT1 is the wind speed at the front hub of the first wind turbine impeller, U WT2 is the predicted wind speed of the second wind turbine, A overlap (U WT1 ,U WT2 ) is a piecewise interpolation calculation function for the vertical projection overlap area of ​​the wake of the first wind turbine along the incoming flow direction on the impeller surface of the second wind turbine, is a piecewise interpolation calculation function for the swept area of ​​the dynamic impeller surface corresponding to the second wind turbine under the preset wind condition, is a segmented interpolation calculation function for the first dynamic equivalent impeller radius of the first wind turbine, is a piecewise interpolation calculation function for the second dynamic equivalent impeller radius of the second wind turbine, is the first thrust coefficient segmented interpolation calculation function of the first wind turbine, k is the wake diffusion coefficient, d cw is the center distance between the first wind turbine and the second wind turbine in the plane perpendicular to the incoming flow direction, and F is.

[0205] As for the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The system embodiment described above is only illustrative, wherein the units described as separate components may or may not be physically separated, and the components as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the disclosed solution.

[0206] The wind speed prediction system for wind turbines in a wind farm provided in this embodiment calculates the wake attenuation using the impeller diameter and thrust coefficient after blade deformation under different wind speeds, thereby effectively reducing the calculation error of the actual wind speed and power generation of the wind farm, accurately understanding the actual operating conditions of the wind farm, and improving the level of wind farm wake assessment.

[0207] Example 4

[0208] This embodiment provides a wind speed prediction system 200 for wind turbines in a wind farm. Fig.15 As shown, the wind farm includes N wind turbines, N≥2, and the wind speed prediction system includes a position acquisition module 201, a pairing module 202, a dynamic parameter acquisition module 203, and a predicted wind speed calculation module 204:

[0209] The position acquisition module 201 is used to obtain the position order of all the wind turbines relative to the wind direction;

[0210] The pairing module 202 is used to use the wind turbine located upwind of the two adjacent wind turbines as the first wind turbine and the other wind turbine as the second wind turbine;

[0211] The dynamic parameter acquisition module 203 is used to acquire a first dynamic characteristic parameter of the first wind turbine and a second dynamic characteristic parameter of the second wind turbine;

[0212] The predicted wind speed calculation module 204 is used to input the first dynamic characteristic parameter and the second dynamic characteristic parameter into a target wake model to obtain a predicted wind speed of the second wind turbine;

[0213] Wherein, the target wake model is obtained based on the construction system of the wind turbine wind speed prediction model described in Example 3.

[0214] As an implementable manner, the position acquisition module 201 includes a coordinate acquisition unit, a wind turbine selection unit, a projection calculation unit, a position determination unit and a position sorting unit;

[0215] A coordinate acquisition unit, used to acquire coordinate information of each wind turbine;

[0216] A wind turbine selection unit, used for selecting one of the wind turbines as a reference wind turbine;

[0217] a projection calculation unit, used to calculate the projection of the line vector between each of the remaining wind turbines and the reference wind turbine on the wind direction vector of the wind farm, and obtain the projection distance between the corresponding wind turbine and the reference wind turbine;

[0218] a position determination unit, configured to determine, in response to the projection distance being positive, that the other wind turbine is located upwind of the reference wind turbine;

[0219] A position sorting unit is used to obtain the position sorting of all the wind turbines based on the projection distance between each wind turbine and other wind turbines.

[0220] As an implementable manner, the predicted wind speed calculation module 204 includes a static parameter acquisition unit, an initial prediction unit, a to-be-verified calculation unit, a convergence judgment unit, and a determination unit;

[0221] A static parameter acquisition unit, used to acquire the static impeller size of the second wind turbine;

[0222] an initial prediction unit, configured to calculate an initial predicted wind speed of the second wind turbine using the static impeller size of the second wind turbine as an input of the target wake model;

[0223] A calculation unit to be verified, used for substituting the initial predicted wind speed into the target wake model to calculate the predicted wind speed to be verified;

[0224] A convergence judgment unit, used for performing residual convergence judgment on the predicted wind speed to be verified and the initial predicted wind speed, to verify whether the predicted wind speed to be verified is true;

[0225] A determination unit is configured to, in response to a verification result of the predicted wind speed to be verified being true, use the predicted wind speed to be verified as the predicted wind speed of the second wind turbine.

[0226] As an implementable manner, the wind speed prediction system further includes a wind speed iteration module, and the wind speed iteration module includes a wind speed loss unit and a wind speed adjustment unit:

[0227] A wind speed deficit unit, configured to sequentially obtain the wind speed deficit of each wind turbine to each wind turbine located in the downstream wind direction, starting from the starting wind turbine located at the most upstream position, based on the position sorting of all the wind turbines;

[0228] The wind speed adjustment unit is used to iteratively update the predicted wind speed based on the wind speed loss to obtain a target predicted wind speed.

[0229] As an implementable manner, the wind speed deficit unit is further used to obtain N-1 wind speed deficits of the downstream wind turbine at the Nth position and the N-1 upstream wind turbines in the upwind direction to the downstream wind turbine at the Nth position;

[0230] The wind speed deficit unit is further used to superimpose N-1 wind speed deficits to obtain a superimposed wind speed deficit corresponding to the downstream wind turbine at the Nth position;

[0231] The wind speed adjustment unit is further used to update the predicted wind speed corresponding to the downstream wind turbine at the Nth position based on the superimposed wind speed loss to obtain the target predicted wind speed.

[0232] The wind speed prediction system for wind turbines in a wind farm provided in this embodiment calculates the wake attenuation using the impeller diameter and thrust coefficient after blade deformation under different wind speeds, thereby effectively reducing the calculation error of the actual wind speed and power generation of the wind farm, accurately understanding the actual operating conditions of the wind farm, and improving the level of wind farm wake assessment.

[0233] Example 5

[0234] Fig.16 This is a structural schematic diagram of an electronic device shown in an example embodiment of the present disclosure, the electronic device includes a memory, a processor, and a computer program stored in the memory and used to run on the processor, when the processor executes the computer program, it implements the method for constructing a wind speed prediction model for a wind turbine described in any of the above embodiments, or the method for predicting the wind speed of a wind turbine in a wind farm. Fig.16 The electronic device 90 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0235] like Fig.16 As shown, the electronic device 90 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 90 may include, but are not limited to: at least one processor 91, at least one memory 92, and a bus 93 connecting different system components (including the memory 92 and the processor 91).

[0236] The bus 93 includes a data bus, an address bus, and a control bus.

[0237] The memory 92 may include a volatile memory, such as a random access memory (RAM) 921 and / or a cache memory 922 , and may further include a read-only memory (ROM) 923 .

[0238] The memory 92 may also include a program tool 925 (or utility) having a set (at least one) of program modules 924, such program modules 924 including but not limited to: an operating system, one or more application programs, other program modules and program data, each of which or some combination may include an implementation of a network environment.

[0239] The processor 91 executes various functional applications and data processing by running the computer program stored in the memory 92, such as the method for constructing a wind speed prediction model for a wind turbine provided in any of the above embodiments, or the method for predicting the wind speed of a wind turbine in a wind farm.

[0240] The electronic device 90 may also communicate with one or more external devices 94 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 95. Furthermore, the electronic device 90 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 96. As shown, the network adapter 96 communicates with other modules of the electronic device 90 via a bus 93. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 90, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0241] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0242] Example 6

[0243] The embodiments of the present disclosure also provide a computer-readable storage medium having a computer program stored thereon. When the program is executed by a processor, the method for constructing a wind turbine wind speed prediction model or the method for predicting wind speed of wind turbines in a wind farm provided in any of the above embodiments is implemented.

[0244] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0245] Example 7

[0246] The embodiments of the present disclosure also provide a computer program product, including a computer program, which, when executed by a processor, implements any of the above-mentioned methods for constructing a wind speed prediction model for a wind turbine, or a method for predicting wind speed for a wind turbine in a wind farm.

[0247] Among them, the program code for executing the computer program product of the present disclosure can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0248] Although the specific embodiments of the present disclosure are described above, those skilled in the art should understand that this is only an example, and the protection scope of the present disclosure is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present disclosure, but these changes and modifications all fall within the protection scope of the present disclosure.

Claims

1. A method for constructing a wind turbine wind speed prediction model, characterized in that: The invention comprises at least two wind turbines, wherein a first wind turbine is located upwind of a second wind turbine, and the construction method comprises: Acquire first simulation operation data of the first wind turbine and second simulation operation data of the second wind turbine under preset wind condition parameters; Extracting a first dynamic characteristic parameter of the first wind turbine from the first simulation operation data, and extracting a second dynamic characteristic parameter of the second wind turbine from the second simulation operation data; The first dynamic characteristic parameter includes a first equivalent dynamic impeller size and a first thrust coefficient of the first wind turbine under preset wind condition parameters, and the second dynamic characteristic parameter includes a second equivalent dynamic impeller size of the second wind turbine under preset wind condition parameters; Adjusting a preset wake model based on the first dynamic characteristic parameter, the first thrust coefficient, and the second dynamic characteristic parameter, and a distance between the first wind turbine and the second wind turbine to obtain a target wake model; The target wake model is used to obtain the predicted wind speed of the second wind turbine.

2. The method for constructing a wind turbine wind speed prediction model according to claim 1, characterized in that: The first dynamic characteristic parameter also includes a first projection area of ​​the first wind turbine on a vertical plane, and the second dynamic characteristic parameter also includes a second projection area and a second thrust coefficient of the second wind turbine on a vertical plane. The step of adjusting the preset wake model based on the first dynamic characteristic parameter and the second dynamic characteristic parameter to obtain a target wake model includes: Constructing a first piecewise interpolation calculation function corresponding to the first dynamic characteristic parameter and a second piecewise interpolation calculation function corresponding to the second dynamic characteristic parameter; The first piecewise interpolation calculation function is used as an input of the preset wake model, and the preset wake model is adjusted based on the first piecewise interpolation calculation function and the second piecewise interpolation calculation function to obtain the target wake model.

3. The method for constructing a wind turbine wind speed prediction model according to claim 2, characterized in that: The step of constructing a first piecewise interpolation calculation function corresponding to the first dynamic characteristic parameter and a second piecewise interpolation calculation function corresponding to the second dynamic characteristic parameter comprises: A first piecewise interpolation calculation function corresponding to the first dynamic characteristic parameter and a second piecewise interpolation calculation function corresponding to the second dynamic characteristic parameter are constructed by linear interpolation or spline interpolation.

4. The method for constructing a wind turbine wind speed prediction model according to claim 3, characterized in that: The preset wake model is in the form of a Jensen wake model, and the formula of the target wake model is: Among them, WT1 is the first wind turbine, WT2 is the second wind turbine, U WT1 is the wind speed at the front hub of the first wind turbine impeller, U WT2 is the predicted wind speed of the second wind turbine, A overlap (U WT1 , U WT2 ) is a piecewise interpolation calculation function for the vertical projection overlap area of ​​the wake of the first wind turbine along the incoming flow direction on the impeller surface of the second wind turbine, is a piecewise interpolation calculation function for the swept area of ​​the dynamic impeller surface corresponding to the second wind turbine under the preset wind condition, is a piecewise interpolation calculation function for the first dynamic equivalent impeller radius of the first wind turbine, is a piecewise interpolation calculation function for the second dynamic equivalent impeller radius of the second wind turbine, is the first thrust coefficient segmented interpolation calculation function of the first wind turbine, k is the wake diffusion coefficient, d cw It is the center distance between the first wind turbine and the second wind turbine in the plane perpendicular to the incoming flow direction.

5. A method for predicting wind speed of a wind turbine in a wind farm, characterized in that: The wind farm includes N wind turbines, N≥2, and the wind speed prediction method includes: Obtaining the position order of all the wind turbines relative to the wind direction; The wind turbine located upwind of the two adjacent wind turbines is used as a first wind turbine, and the other wind turbine is used as a second wind turbine; Acquire a first dynamic characteristic parameter of the first wind turbine and a second dynamic characteristic parameter of the second wind turbine; Inputting the first dynamic characteristic parameter and the second dynamic characteristic parameter into a target wake model to obtain a predicted wind speed of the second wind turbine; Wherein, the target wake model is obtained based on the method for constructing a wind turbine wind speed prediction model according to any one of claims 1-4.

6. The method for predicting wind speed of a wind turbine in a wind farm according to claim 5, characterized in that: The step of obtaining the position order of all the wind turbines relative to the wind direction comprises: Obtaining coordinate information of each wind turbine; Selecting one of the wind turbines as a reference wind turbine; Calculate the projection of the line vector between each of the remaining wind turbines and the reference wind turbine on the wind direction vector of the wind farm to obtain the projection distance between the corresponding wind turbine and the reference wind turbine; In response to the projection distance being positive, the other wind turbine is located upwind of the reference wind turbine; Based on the projection distance between each wind turbine and other wind turbines, a position ranking of all the wind turbines is obtained.

7. The method for predicting wind speed of a wind turbine in a wind farm according to claim 5, characterized in that: The step of inputting the first dynamic characteristic parameter and the second dynamic characteristic parameter into a target wake model to obtain a predicted wind speed of the second wind turbine comprises: Obtaining a static impeller size of the second wind turbine; Using the static impeller size of the second wind turbine as an input of the target wake model, calculating an initial predicted wind speed of the second wind turbine; Substituting the initial predicted wind speed into the target wake model, and calculating the predicted wind speed to be verified; Perform residual convergence judgment on the predicted wind speed to be verified and the initial predicted wind speed to verify whether the predicted wind speed to be verified is true; In response to a verification result of the predicted wind speed to be verified being true, the predicted wind speed to be verified is used as the predicted wind speed of the second wind turbine.

8. The method for predicting wind speed of a wind turbine in a wind farm according to claim 5, characterized in that: The wind speed prediction method further comprises: Based on the position sorting of all the wind turbines, starting from the starting wind turbine located at the most upstream position, sequentially obtaining the wind speed loss of each wind turbine to each wind turbine located in the downstream wind direction; The predicted wind speed is iteratively updated based on the wind speed loss to obtain a target predicted wind speed.

9. The method for predicting wind speed of a wind turbine in a wind farm according to claim 8, characterized in that: The step of iteratively updating the predicted wind speed based on the wind speed loss to obtain a target predicted wind speed comprises: Obtaining N-1 wind speed deficits of the N-1 upstream wind turbines in the upwind direction from the downstream wind turbine at the N-th position to the downstream wind turbine at the N-th position; Superimposing N-1 wind speed deficits to obtain a superimposed wind speed deficit corresponding to the downstream wind turbine at the Nth position; The predicted wind speed corresponding to the downstream wind turbine at the Nth position is updated based on the superimposed wind speed loss to obtain the target predicted wind speed.

10. A system for constructing a wind turbine wind speed prediction model, characterized in that: At least two wind turbines are included, wherein a first wind turbine is located upwind of a second wind turbine, and the construction system includes a simulation data acquisition module, a dynamic parameter extraction module, and a target model adjustment module; The simulation data acquisition module is used to acquire first simulation operation data of the first wind turbine and second simulation operation data of the second wind turbine under preset wind condition parameters; The dynamic parameter extraction module is used to extract the first dynamic characteristic parameter of the first wind turbine from the first simulation operation data, and extract the second dynamic characteristic parameter of the second wind turbine from the second simulation operation data; The first dynamic characteristic parameter includes a first equivalent dynamic impeller size of the first wind turbine under preset wind condition parameters, and the second dynamic characteristic parameter includes a second equivalent dynamic impeller size of the second wind turbine under preset wind condition parameters; The target model adjustment module is used to adjust the preset wake model based on the first dynamic characteristic parameter and the second dynamic characteristic parameter to obtain a target wake model; The target wake model is used to obtain the predicted wind speed of the second wind turbine.

11. A wind speed prediction system for a wind turbine in a wind farm, characterized in that: The wind farm includes N wind turbines, N≥2, and the wind speed prediction system includes a position acquisition module, a pairing module, a dynamic parameter acquisition module, and a predicted wind speed calculation module: The position acquisition module is used to obtain the position order of all the wind turbines relative to the wind direction; The pairing module is used to use the wind turbine located upwind of the two adjacent wind turbines as the first wind turbine and the other wind turbine as the second wind turbine; The dynamic parameter acquisition module is used to acquire a first dynamic characteristic parameter of the first wind turbine and a second dynamic characteristic parameter of the second wind turbine; The predicted wind speed calculation module is used to input the first dynamic characteristic parameter and the second dynamic characteristic parameter into a target wake model to obtain a predicted wind speed of the second wind turbine; Wherein, the target wake model is obtained based on the construction system of the wind turbine wind speed prediction model described in claim 10.

12. An electronic device comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, characterized in that: When the processor executes the computer program, the method for constructing a wind speed prediction model for a wind turbine as claimed in any one of claims 1 to 4 or the method for predicting wind speed for a wind turbine in a wind farm as claimed in any one of claims 5 to 9 is implemented.

13. A computer storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for constructing a wind speed prediction model for a wind turbine according to any one of claims 1 to 4 or the method for predicting wind speed for a wind turbine in a wind farm according to any one of claims 5 to 9 is implemented.

14. A computer program product comprising a computer program, characterized in that When the computer program is executed by a processor, the method for constructing a wind speed prediction model for a wind turbine as claimed in any one of claims 1 to 4 or the method for predicting wind speed for a wind turbine in a wind farm as claimed in any one of claims 5 to 9 is implemented.

Images