CN116227357A - Wind power plant wake prediction method, model and system thereof - Google Patents
Wind power plant wake prediction method, model and system thereof Download PDFInfo
- Publication number
- CN116227357A CN116227357A CN202310236517.XA CN202310236517A CN116227357A CN 116227357 A CN116227357 A CN 116227357A CN 202310236517 A CN202310236517 A CN 202310236517A CN 116227357 A CN116227357 A CN 116227357A
- Authority
- CN
- China
- Prior art keywords
- wake
- wind
- flow
- model
- far
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/06—Wind turbines or wind farms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Computational Linguistics (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Biomedical Technology (AREA)
- Geometry (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a wind power plant wake flow prediction method, a model and a system thereof, and belongs to the technical field of new energy wind power. The invention comprises the following steps: dividing a wake flow area of the wind turbine into a near wake flow area and a far wake flow area according to the distance between the wake flow section and the wind turbine; respectively constructing wake models of a near wake area and a far wake area of the wind turbine; introducing a wake superposition method to construct a full-field wake model; obtaining an optimal wake parameter dataset; training a machine learning model by taking wind farm incoming flow data as input and wake flow parameter data as output, establishing a relation between incoming flow information and wake flow characteristics, and constructing a self-adaptive wind farm engineering wake flow model; according to the input incoming flow information, the wake expansion rate is obtained through prediction of a trained machine learning model, the wake expansion rate is combined with an analysis wake model, wake correlation calculation in a wind power plant is executed, the influence of near wake development characteristics on far wake is further considered, and the speed loss calculation accuracy of a wake area is effectively improved.
Description
Technical Field
The invention belongs to the technical field of new energy wind power, and particularly relates to a wind power plant wake flow prediction method, a model and a system thereof.
Background
In order to obtain higher generated energy, besides the large-scale wind turbine generator and the continuous improvement of the single-machine capacity of the wind turbine generator, the scale of the wind power plant is also required to be enlarged to arrange more wind turbine generators. However, under the normal condition, the increase of the number of the wind turbines is not in direct proportion to the increase of the generated energy, and when the number of the wind turbines reaches a certain number, the increase of the number of the wind turbines can lead to the decrease of the generated energy of the wind farm, because of the wake effect in the wind farm, the wind speed captured by the wind turbines at the downstream is lower, the turbulence intensity is increased, and the generated energy is decreased. In addition, the wake effect of the wind turbine generator simultaneously increases the fatigue load and the failure probability of the downstream wind turbine generator, thereby increasing the operation and maintenance cost of the wind power plant.
In order to reduce the influence of wake effects on the wind turbine, improve the economic effects and safe operation of the wind farm, and research on wake characteristics and wake flow field details of the wind turbine is necessary. The method has the advantages that the widely accepted high-efficiency engineering wake model is provided in the early stage, only the far wake area is analyzed, the influence mechanism of the speed distribution of the near wake area on the far wake is not considered, meanwhile, the existing engineering wake model only works well under the specific experimental condition, and a large error still exists in the actual wind power plant. In addition, considering the influence of complex inflow atmospheric boundary layer flow fields on meteorological factors such as wind speed, wind direction, stability and the like, the wake flow speed distribution of a wind power field needs to be considered on the whole, and intelligent algorithms such as machine learning and the like are introduced, so that the calculation accuracy of an engineering wake flow model is further improved.
Disclosure of Invention
The invention aims to provide a wind power plant wake prediction method, a model and a system thereof, which effectively improve the speed loss calculation precision of wake areas and better serve the optimization layout work by further considering the influence of near wake development characteristics on far wake, and solve the problem of larger errors in the aspects of power calculation and the like applied to actual wind power plants in the prior art.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to a wind farm wake prediction method, which comprises the following steps:
s1: dividing a wake flow area of the wind turbine into a near wake flow area and a far wake flow area according to the distance between the wake flow section and the wind turbine;
s2: respectively constructing wake models of a near wake area and a far wake area of the wind turbine;
s3: introducing a wake superposition method to construct a full-field wake model;
s4, the wake expansion rates k and k of the far wake region and the near wake region are reduced * As undetermined parameters, SCADA data of a wind power plant are selected, wake characteristic extraction is carried out on the data of each time point, and an optimal wake expansion rate data set is obtained;
s5, training a machine learning model by taking wind farm incoming flow data as input and wake flow parameter data as output, and establishing a relation between incoming flow information and wake flow characteristics to construct a self-adaptive wind farm engineering wake flow model;
s6, predicting wake parameters through a trained machine learning model according to the input information of the wake, combining the wake parameters with an analysis wake model, and executing wake-related calculation in the wind power plant.
Further, the wake distribution of the near wake region presents a double Gaussian rule, the wake distribution of the far wake region presents a single Gaussian rule, and the demarcation point of the far wake region and the near wake region can be determined by the following formula:
wherein a=0.58, b=0.077, c is a proportionality coefficient, and is determined according to the condition of the practical application wind field; TI (TI) x,hub The flow direction turbulence intensity at the height of the hub is D is rotationDiameter of wheel, C T Is a thrust coefficient;
the distance from the wake flow section to the wind turbine is expressed by x, and when x is less than x d When the wake flow of the near wake flow area is distributed in double gauss.
Further, the near-wake region wake is in a double gaussian distribution, and the gaussian shape function f (r (y, z), σ (x)) can be expressed as:
wherein r is 0 The radial distance between the minimum value point of wake wind speed and the central line of the hub, sigma represents an expansion function, y represents the radial distance between the central position of the hub and the space point in the horizontal direction by taking the central position of the hub as the zero point, z represents the height difference between the space point and the ground in the vertical direction by taking the ground as the zero point, and z h Representing the hub height.
Further, the far wake region wake is in a single gaussian distribution, and the gaussian shape function f (r (y, z), σ (x)) can be expressed as:
where r represents the distance from any position in the wake cross section to the wake centerline and σ represents the spread function.
Further, the feature extraction step of the wake model comprises the following steps of
S4.1, determining the layout condition of a wind power plant and basic parameters of a wind motor;
s4.2: determining wind speed, wind direction and output power data of each unit, and determining wake expansion rates k and k of a far wake region and a near wake region * Setting the variable parameters;
s4.3: establishing a relation between the wake expansion rate and the calculated generated energy by combining the data set in the step 2;
s4.4: comparing the actual output power of the wind power plant with the power calculated by the wake model, and evaluating whether the wake expansion rate meets the requirement;
s4.5: optimizing the problems by using a genetic algorithm to obtain an optimal wake expansion rate;
s4.6: the above steps are performed for each recording instant of SCADA data to establish a wake feature set.
Further, the basic parameters of the wind turbine include rotor diameter, hub height, thrust coefficient curve and power curve.
Further, the wake expansion rate parameter is determined specifically by comparing the power quantity of the SCADA data record and the power calculated by the wake model, and evaluating the power quantity by adopting Root Mean Square Error (RMSE).
The invention has the following beneficial effects:
1. according to the invention, the influence of the near wake development characteristics on the far wake is further considered, a machine learning method is introduced, the incoming flow characteristics influencing wake distribution are extracted, the relation between the incoming flow information and the wake characteristics is established, and the self-adaptive wind farm engineering wake model is constructed, so that the speed loss calculation precision of a wake area is effectively improved, and the optimization layout work is better served;
2. the invention determines the wake expansion rate through genetic algorithm, solves the problems that complex inflow wind condition conditions cannot be fully considered in the process of determining the wake expansion rate, and the engineering wake model has good performance on experimental data, but has larger error in the aspects of power calculation and the like applied to an actual wind power plant due to a plurality of simplifying assumptions in the process of constructing the model in the prior art
Of course, it is not necessary for any one product to practice the invention to achieve all of the advantages set forth above at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of an intelligent wake prediction method for wake evolution features of a wind farm;
FIG. 2 is a schematic diagram of an intelligent wake prediction method for wake evolution characteristics of a wind farm;
FIG. 3 is a schematic illustration of wake wind speed profile variation in the horizontal direction;
fig. 4 is a schematic diagram of wake wind speed profile variation in the vertical direction.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the description of the present invention, it should be understood that the terms "open," "upper," "lower," "thickness," "top," "middle," "length," "inner," "peripheral," and the like indicate orientation or positional relationships, merely for convenience in describing the present invention and to simplify the description, and do not indicate or imply that the components or elements referred to must have a particular orientation, be constructed and operated in a particular orientation, and thus should not be construed as limiting the present invention.
Referring to fig. 1-4, the invention discloses an intelligent wake prediction method reflecting the evolution characteristics of a wind power plant wake, which comprises the following specific steps:
firstly, an engineering wake model reflecting the wake evolution characteristics of a wind farm is provided, a wind turbine wake area is divided into a near wake area and a far wake area according to the distance between a wake section and the wind turbine, wake wind speed distribution is increased along with the downstream distance, the evolution rule of a double-Gaussian to single-Gaussian model is spatially presented, and the related wake model is constructed as follows:
if the viscosity term and the pressure term in the momentum equation are ignored, the mass conservation and momentum conservation equations are applied to obtain the following wake equation:
ρ∫U W (U ∞ -U W )dA=T (1)
ρ represents the atmospheric density, U W Indicating wake velocity, U ∞ Representing the speed of the free incoming flow, A represents the wake cross-sectional area corresponding to any downstream distance, T represents the thrust of the wind turbine, and can be determined by the following formula:
C T represents the thrust coefficient, A 0 The effective area of the rotor surface of the wind turbine under the action of the thrust T is shown.
Self-similarity in the wake describes the normalized velocity deficit as:
where C (σ (x)) represents the amplitude function of the maximum normalized velocity deficit, and f (r (y, z), σ (x)) represents the gaussian shape function of the wake distribution. Dividing a wind turbine wake zone into a near wake zone and a far wake zone, wherein wake distribution of the near wake zone shows an asymmetric double-Gaussian rule, and wake distribution of the far wake zone shows a symmetric single-Gaussian rule. The far and near wake zone demarcation point may be determined by the following equation:
wherein x is d The demarcation points of the far wake flow and the near wake flow are represented, a=0.58, b=0.077, c is a proportionality coefficient, and the demarcation points are determined according to the actual wind field conditions; TI (TI) x,hub Is the turbulence intensity of the flow direction at the hub height.
The distance from the wake flow section to the wind turbine is expressed by x, and when x is less than x d When the near-wake region wake is in a double gaussian distribution, the gaussian shape function f (r (y, z), σ (x)) can be expressed as:
wherein r is 0 The radial distance between the wake wind speed minimum point and the hub center line, sigma represents the expansion function, and can be expressed as:
wherein ε 1 For initial wake radius, the thrust coefficient C can be determined according to the diameter D of the rotor T Calculating an initial wake radius ε 1 The specific formula is as follows:
substituting equation (3) (5) into equation (1) yields:
the following expression can be obtained by integration:
T=πρU ∞ 2 C(σ(x))(M-C(σ(x))N) (10)
wherein M, N is an error function, and the specific calculation formula is that
Substituting equation (2) into equation (7) can yield an amplitude function C (σ (x)) that can be expressed as:
when (when)And selecting the modular length of the complex root obtained by the equation to approximate the solution:
when x > x d When the wake of the far wake zone is in a single gaussian distribution, the gaussian shape function f (r (y, z), σ (x)) can be expressed as:
the self-similarity normalized velocity deficit in the single gaussian wake can be expressed as:
the velocity of the far wake can be expressed as:
substituting equations (2) and (16) into equation (1) yields the integral:
can be obtained by solving (17)
substituting formula (18) into formula (15)
(20)
Wherein z is h Representing the hub height.
Since we calculate the velocity field of the whole wind farm, the superposition of wake flows needs to be considered, and a wake flow superposition method is introduced:
where Deltau is the speed deficit caused by n upstream fans Deltau i Is the speed deficit caused by the ith upstream fan.
After the full-field wake model is constructed, wake expansion rates k and k of the far and near wake regions are calculated * As undetermined parameters, SCADA data of the wind power plant are selected, and firstly, the data of the SCADA data are filtered, and wind power plant incoming flows with wake influence and yaw angles and output power data of all units are screened out. And extracting wake characteristics of the data at each time point according to the data, and obtaining an optimal wake parameter data set.
The characteristic extraction steps of the wake model are as follows:
(1) Preparing the layout condition of a wind power plant, and simultaneously preparing basic parameters of the wind power plant, including rotor diameter, hub height, thrust coefficient curve, power curve and the like;
(2) Preparing wind speed, wind direction and output power data of each unit;
(3) Establishing a relation between the wake expansion rate and the calculated generated energy by combining the data set in the second step;
(4) Establishing an optimization model, calling the power quantity recorded by SCADA data, comparing the power quantity with the power calculated by the wake model, and evaluating by adopting Root Mean Square Error (RMSE);
(5) Optimizing the problems by using a genetic algorithm to obtain an optimal wake expansion rate;
(6) The above steps are performed for each recording instant of SCADA data to establish a wake feature set.
Further, the layout conditions of the wind farm include parameters such as: the number, spacing and arrangement of wind motors.
And training a machine learning model by taking wind power plant incoming flow data as input and wake flow parameter data as output, establishing a relation between incoming flow information and wake flow characteristics, and constructing a self-adaptive wind power plant engineering wake flow model. And inputting current incoming flow information for test data outside the training set, predicting to obtain wake flow parameters through a trained machine learning model, and combining the wake flow parameters with the established analytic wake flow model to execute wake flow related calculation in the wind power plant.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (10)
1. A wind farm wake prediction method, the method comprising the steps of:
s1: dividing a wake flow area of the wind turbine into a near wake flow area and a far wake flow area according to the distance between the wake flow section and the wind turbine;
s2: respectively constructing wake models of a near wake area and a far wake area of the wind turbine;
s3: introducing a wake superposition method to construct a full-field wake model structure;
s4, the wake expansion rates k and k of the far wake region and the near wake region are reduced * As undetermined parameters, SCADA data of a wind power plant are selected, wake characteristic extraction is carried out on the data of each time point, and an optimal wake expansion rate data set is obtained;
s5, training a machine learning model by taking wind farm incoming flow data as input and wake flow parameter data as output, and establishing a relation between incoming flow information and wake flow characteristics to construct a self-adaptive wind farm engineering wake flow model;
s6, predicting wake parameters through a trained machine learning model according to the input information of the wake, combining the wake parameters with the established analysis wake model, and executing wake-related calculation in the wind power plant.
2. The wind farm wake prediction method according to claim 1, wherein the near wake zone wake distribution exhibits a double gaussian law, the far wake zone wake distribution exhibits a single gaussian law, and the far and near wake zone demarcation point is determined by the following equation:
wherein a=0.58, b=0.077, c is a proportionality coefficient, and is determined according to the condition of the practical application wind field; TI (TI) x,hub The flow direction turbulence intensity at the height of the hub is D is the diameter of the rotating wheel and C T Is a thrust coefficient;
when x is less than x d When the wake flow of the near wake flow area is distributed in double gauss.
3. A wind farm wake prediction method according to claim 1, wherein the near wake zone wake is in a double gaussian distribution, and the gaussian shape function f (r (y, z), σ (x)) can be expressed as:
wherein r is 0 Represents the radial distance between the minimum value point of wake wind speed and the central line of the hub, sigma represents the expansion function, z h The hub height is represented by y, the radial distance from the hub center position in the horizontal direction of the space point is represented by y, the ground is represented by z, and the height difference between the space point and the ground in the vertical direction is represented by y.
4. A method of wind farm wake prediction according to claim 1, wherein the far wake zone wake is a single gaussian distribution, and the gaussian shape function f (r (y, z), σ (x)) is expressed as:
where r represents the distance from any position in the wake cross section to the wake centerline and σ represents the spread function.
5. A wind farm wake prediction method according to claim 1, wherein the feature extraction step of the wake model comprises the steps of
S4.1, determining the layout condition of a wind power plant and basic parameters of a wind motor;
s4.2: determining wind speed, wind direction and output power data of each unit, and determining wake expansion rates k and k of a far wake region and a near wake region * Setting the variable parameters;
s4.3: establishing a relation between the wake expansion rate and the calculated generated energy by combining the data set in the step 2;
s4.4: comparing the actual output power of the wind power plant with the power calculated by the wake model, and evaluating whether the wake expansion rate meets the requirement;
s4.5: optimizing the problems by using a genetic algorithm to obtain an optimal wake expansion rate;
s4.6: the above steps are performed for each recording instant of SCADA data to establish a wake feature set.
6. The method of claim 5, wherein the wind turbine basic parameters include rotor diameter, hub height, thrust coefficient profile and power profile.
7. A wind farm wake prediction method according to claim 5, wherein the wake expansion ratio parameter is determined by comparing the amount of power recorded by the retrieved SCADA data with the power calculated by the wake model, and evaluating the wake expansion ratio parameter using a root mean square error RMSE.
8. A wind farm wake prediction system, the system comprising:
wake dividing module: the wind turbine wake flow area is divided into a near wake flow area and a far wake flow area according to the distance between the wake flow section and the wind turbine;
wake model construction module: the wake models are used for respectively constructing a near wake area and a far wake area of the wind turbine;
full-field wake model construction module: the method is used for introducing a wake superposition method to construct a full-field wake model;
the wake expansion rate calculation module is used for calculating wake expansion rates k and k of the far wake region and the near wake region * As undetermined parameters, SCADA data of a wind power plant are selected, wake characteristic extraction is carried out on the data of each time point, and an optimal wake parameter data set is obtained;
the machine learning module is used for taking wind power plant incoming flow data as input and wake flow parameter data as output, training a machine learning model, establishing a relation between incoming flow information and wake flow characteristics and constructing a self-adaptive wind power plant engineering wake flow model;
and the calculation output module predicts wake parameters through a trained machine learning model according to the input information of the wake, combines the wake parameters with the established analysis wake model and executes wake-related calculation in the wind power plant.
9. A wind farm wake prediction device, characterized in that the device is adapted to perform a wind farm wake prediction method according to one of the claims 1-8.
10. A storage medium, characterized in that the storage medium stores a wind farm wake prediction method according to one of claims 1-8.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310236517.XA CN116227357A (en) | 2023-03-13 | 2023-03-13 | Wind power plant wake prediction method, model and system thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310236517.XA CN116227357A (en) | 2023-03-13 | 2023-03-13 | Wind power plant wake prediction method, model and system thereof |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116227357A true CN116227357A (en) | 2023-06-06 |
Family
ID=86569320
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310236517.XA Pending CN116227357A (en) | 2023-03-13 | 2023-03-13 | Wind power plant wake prediction method, model and system thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116227357A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116596165A (en) * | 2023-07-17 | 2023-08-15 | 国网山东省电力公司汶上县供电公司 | Wind power generation power prediction method and system |
CN117454721A (en) * | 2023-12-21 | 2024-01-26 | 浙江远算科技有限公司 | Wind power plant wake superposition effect evaluation method and medium based on digital simulation experiment |
-
2023
- 2023-03-13 CN CN202310236517.XA patent/CN116227357A/en active Pending
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116596165A (en) * | 2023-07-17 | 2023-08-15 | 国网山东省电力公司汶上县供电公司 | Wind power generation power prediction method and system |
CN116596165B (en) * | 2023-07-17 | 2023-10-13 | 国网山东省电力公司汶上县供电公司 | Wind power generation power prediction method and system |
CN117454721A (en) * | 2023-12-21 | 2024-01-26 | 浙江远算科技有限公司 | Wind power plant wake superposition effect evaluation method and medium based on digital simulation experiment |
CN117454721B (en) * | 2023-12-21 | 2024-03-22 | 浙江远算科技有限公司 | Wind power plant wake superposition effect evaluation method and medium based on digital simulation experiment |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116227357A (en) | Wind power plant wake prediction method, model and system thereof | |
Annoni et al. | Evaluating wake models for wind farm control | |
CN112818590A (en) | Method for evaluating power generation capacity of wind power plant and establishing micro-site selection model | |
EP3791060B1 (en) | Wind turbine control method | |
CN107194097B (en) | Analysis method based on wind power plant aerodynamic simulation and wind speed and direction data | |
CN110543649B (en) | Fan arrangement method and device based on rapid evaluation fluid model and wake flow model | |
CN101684774A (en) | Wind power generation system and wind measuring method of wind power generator | |
JP2020502424A (en) | Wind turbine power station level load management control strategy | |
CN109460629A (en) | A kind of cooling fan performance optimization method based on approximate model method | |
CN114169614B (en) | Wind power plant optimal scheduling method and system based on wind turbine wake model optimization | |
CN113205210B (en) | Wind power plant wind speed and power prediction method, system and equipment for complex terrain and storage medium | |
Nai-Zhi et al. | A data-driven analytical model for wind turbine wakes using machine learning method | |
CN115618540A (en) | Wind generating set optimal layout method based on three-level dynamic variation rate | |
CN105843777B (en) | A kind of hydrodynamic force coefficient method for solving based on genetic algorithm multivariable concurrent operation | |
CN108256712B (en) | Control method and device for wind power plant group | |
EP3741991B1 (en) | Method for dynamic real-time optimization of the performance of a wind park and wind park | |
CN116628894A (en) | Hydrofoil design optimization method and hydrofoil design optimization framework based on deep learning | |
CN105956318B (en) | Based on the wind power plant group of planes division methods for improving division H-K clustering method | |
CN105389614B (en) | A kind of implementation method of neutral net self refresh process | |
van der Hoek et al. | Maximizing wind farm power output with the helix approach: Experimental validation and wake analysis using tomographic particle image velocimetry | |
Wang et al. | Construction of offline predictive controller for wind farm based on CNN–GRNN | |
CN109611268A (en) | A kind of bilobed wheel horizontal-shaft wind turbine design optimization method | |
EP3536949B1 (en) | Wind farm, and operation method, control device, and operation control program for wind farm | |
CN113567164A (en) | Systematic evaluation and prediction method for technical improvement demand of wind power plant | |
Jamieson | Multi rotor solution for large scale offshore wind power |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination |