CN116432548A - Fusion wind speed calculation method, device, equipment and medium based on transfer learning - Google Patents
Fusion wind speed calculation method, device, equipment and medium based on transfer learning Download PDFInfo
- Publication number
- CN116432548A CN116432548A CN202310248593.2A CN202310248593A CN116432548A CN 116432548 A CN116432548 A CN 116432548A CN 202310248593 A CN202310248593 A CN 202310248593A CN 116432548 A CN116432548 A CN 116432548A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- speed data
- wind
- simulated
- calculation
- 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
- 238000004364 calculation method Methods 0.000 title claims abstract description 110
- 230000004927 fusion Effects 0.000 title claims abstract description 100
- 238000013526 transfer learning Methods 0.000 title claims abstract description 85
- 238000003062 neural network model Methods 0.000 claims abstract description 68
- 238000000034 method Methods 0.000 claims abstract description 49
- 238000012821 model calculation Methods 0.000 claims abstract description 21
- 238000013508 migration Methods 0.000 claims description 17
- 230000005012 migration Effects 0.000 claims description 17
- 238000004458 analytical method Methods 0.000 claims description 15
- 238000012360 testing method Methods 0.000 claims description 14
- 230000008569 process Effects 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 239000012530 fluid Substances 0.000 claims description 9
- 238000003860 storage Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004088 simulation Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 5
- 238000009826 distribution Methods 0.000 description 5
- 238000011160 research Methods 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000002123 temporal effect Effects 0.000 description 2
- 238000012876 topography Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000802 evaporation-induced self-assembly Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
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
- G06F30/28—Design optimisation, verification or simulation using fluid dynamics, e.g. using Navier-Stokes equations or computational fluid dynamics [CFD]
-
- 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
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/096—Transfer learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/10—Numerical modelling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2113/00—Details relating to the application field
- G06F2113/08—Fluids
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/14—Force analysis or force optimisation, e.g. static or dynamic forces
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/10—Information and communication technologies [ICT] supporting adaptation to climate change, e.g. for weather forecasting or climate simulation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Mathematical Optimization (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Analysis (AREA)
- Fluid Mechanics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Algebra (AREA)
- Pure & Applied Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Indicating Or Recording The Presence, Absence, Or Direction Of Movement (AREA)
Abstract
The disclosure relates to a fusion wind speed calculation method, a fusion wind speed calculation device, fusion wind speed calculation equipment and fusion wind speed calculation media based on transfer learning. The fusion wind speed calculation method based on transfer learning comprises the following steps: determining a reference anemometer tower from among the plurality of anemometer towers according to the wind speed correlation; acquiring first real observed wind speed data and first simulated wind speed data of a reference anemometer tower, and acquiring second simulated wind speed data of a target point location; performing time sequence wind speed calculation on the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data to obtain first time sequence wind speed data of the target point position; and performing model calculation on the first time sequence wind speed data through the transfer learning neural network model to obtain first fusion time sequence wind speed data of the target point location. According to the embodiment of the disclosure, the wind speed calculation accuracy can be effectively improved by the method for carrying out fusion calculation on the multiple data.
Description
Technical Field
The disclosure relates to the technical field of wind speed data simulation, in particular to a fusion wind speed calculation method, a fusion wind speed calculation device, fusion wind speed calculation equipment and fusion wind speed calculation media based on transfer learning.
Background
The wind speed of each point of a wind farm, particularly the point of a wind turbine generator set is an important parameter for measuring the accuracy of wind resource assessment software.
In the related art, a computational fluid dynamics (Computational Fluid Dynamics, CFD) method is generally adopted to calculate the space steady-state flow field distribution under different incoming flow wind directions, and then the annual time sequence/frequency domain wind speed distribution of each point position of the wind power plant is calculated based on the reference wind tower time sequence/frequency domain wind data. In the process, due to the influences of factors such as terrain processing, turbulence models, boundary conditions, numerical solution and the like, wind speed errors of CFD numerical simulation are inevitably caused, so that the calculated wind speed accuracy is lower.
Disclosure of Invention
In order to solve the technical problems or at least partially solve the technical problems, the disclosure provides a fusion wind speed calculation method, a fusion wind speed calculation device, fusion wind speed calculation equipment and fusion wind speed calculation media based on transfer learning.
In a first aspect, the present disclosure provides a fusion wind speed calculation method based on transfer learning, including:
determining a reference anemometer tower from among the plurality of anemometer towers according to the wind speed correlation;
acquiring first real observed wind speed data and first simulated wind speed data of a reference anemometer tower, and acquiring second simulated wind speed data of a target point location;
Performing time sequence wind speed calculation on the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data to obtain first time sequence wind speed data of the target point position;
and performing model calculation on the first time sequence wind speed data through the transfer learning neural network model to obtain first fusion time sequence wind speed data of the target point location.
In a second aspect, the present disclosure provides a fusion wind speed computing device based on transfer learning, including:
the data determining module is used for determining a reference anemometer tower according to the wind speed correlation in the plurality of anemometer towers;
the first acquisition module is used for acquiring first real observed wind speed data and first simulated wind speed data of the reference anemometer tower and acquiring second simulated wind speed data of the target point location;
the first calculation module is used for carrying out time sequence wind speed calculation on the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data to obtain first time sequence wind speed data of the target point position;
and the second calculation module is used for carrying out model calculation on the first time sequence wind speed data through the transfer learning neural network model to obtain first fusion time sequence wind speed data of the target point position.
In a third aspect, the present disclosure provides a fusion wind speed computing device based on transfer learning, including:
A processor;
a memory for storing executable instructions;
the processor is used for reading the executable instructions from the memory and executing the executable instructions to realize the fusion wind speed calculation method based on the transfer learning of the first aspect.
In a fourth aspect, the present disclosure provides a computer-readable storage medium storing a computer program, which when executed by a processor, causes the processor to implement the fusion wind speed calculation method based on transfer learning of the first aspect.
Compared with the prior art, the technical scheme provided by the embodiment of the disclosure has the following advantages:
according to the fusion wind speed calculation method, device, equipment and medium based on transfer learning, a reference wind measuring tower can be determined according to wind speed correlation in a plurality of wind measuring towers, then first real observed wind speed data and first simulated wind speed data of the reference wind measuring tower are obtained, second simulated wind speed data of a target point position are obtained, time-series wind speed calculation is carried out on the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data to obtain first time-series wind speed data of the target point position, finally model calculation is carried out on the first time-series wind speed data through a transfer learning neural network model to obtain first fusion time-series wind speed data of the target point position, and therefore fusion calculation can be carried out through the first real observed wind speed data, the first simulated wind speed data of the target point position and the second simulated wind speed data of the transfer learning neural network model to obtain first fusion time-series wind speed data of the target point position, and accordingly wind speed calculation accuracy is effectively improved through the method of fusion calculation of multiple data.
Drawings
The above and other features, advantages, and aspects of embodiments of the present disclosure will become more apparent by reference to the following detailed description when taken in conjunction with the accompanying drawings. The same or similar reference numbers will be used throughout the drawings to refer to the same or like elements. It should be understood that the figures are schematic and that elements and components are not necessarily drawn to scale.
FIG. 1 is a schematic flow chart of a fusion wind speed calculation method based on transfer learning according to an embodiment of the disclosure;
FIG. 2 is a thermal schematic diagram of a wind speed dependence provided by an embodiment of the present disclosure;
FIG. 3 is a schematic structural diagram of a fusion wind speed calculation device based on transfer learning according to an embodiment of the present disclosure;
fig. 4 is a schematic structural diagram of a fusion wind speed computing device based on transfer learning according to an embodiment of the present disclosure.
Detailed Description
Embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While certain embodiments of the present disclosure have been shown in the accompanying drawings, it is to be understood that the present disclosure may be embodied in various forms and should not be construed as limited to the embodiments set forth herein, but are provided to provide a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are for illustration purposes only and are not intended to limit the scope of the present disclosure.
It should be understood that the various steps recited in the method embodiments of the present disclosure may be performed in a different order and/or performed in parallel. Furthermore, method embodiments may include additional steps and/or omit performing the illustrated steps. The scope of the present disclosure is not limited in this respect.
The term "including" and variations thereof as used herein are intended to be open-ended, i.e., including, but not limited to. The term "based on" is based at least in part on. The term "one embodiment" means "at least one embodiment"; the term "another embodiment" means "at least one additional embodiment"; the term "some embodiments" means "at least some embodiments. Related definitions of other terms will be given in the description below.
It should be noted that the terms "first," "second," and the like in this disclosure are merely used to distinguish between different devices, modules, or units and are not used to define an order or interdependence of functions performed by the devices, modules, or units.
It should be noted that references to "one", "a plurality" and "a plurality" in this disclosure are intended to be illustrative rather than limiting, and those of ordinary skill in the art will appreciate that "one or more" is intended to be understood as "one or more" unless the context clearly indicates otherwise.
The names of messages or information interacted between the various devices in the embodiments of the present disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.
The wind speed of each point of a wind farm, particularly the point of a wind turbine generator set is an important parameter for measuring the accuracy of wind resource assessment software. In wind resource assessment software, a CFD method is generally adopted to calculate space steady-state flow field distribution under different incoming flow wind direction conditions, and then based on reference anemometer tower time sequence/frequency domain anemometer data, annual time sequence/frequency domain wind speed distribution of each point of a wind power plant is calculated. In the process, due to the influences of factors such as terrain processing, turbulence models, boundary conditions, numerical solution and the like, wind speed errors of CFD numerical simulation are inevitably caused, so that the calculated wind speed accuracy is lower. If more than one wind measuring tower exists in the wind power plant, wind measuring data of the wind power plant can be fused with CFD numerical simulation calculation wind speed and the like, and wind speed calculation accuracy of wind resource assessment software is effectively improved.
Aiming at the actual situations that the number of wind towers of a wind power plant to be developed and built is limited, and the point position wind speed distribution of each potential unit cannot be obtained through measurement, based on the actual observation wind speeds of a plurality of wind towers, the numerical simulation wind speeds of the CFD of the whole wind power plant and the mesoscale simulation data of the wind power plant, the intelligent algorithm is adopted to realize the fusion of wind speed data, the time sequence/frequency domain wind speeds of a plurality of points are extrapolated to the time sequence/frequency domain wind speeds of a plurality of target points in the wind power plant, the wind speed calculation precision of wind resource evaluation software is improved, basic data is provided for the follow-up calculation of the annual energy production of the target wind power plant points, and the like, and the microcosmic site selection work of the wind power plant is served.
Research is focused on high-precision mesoscale numerical modes and assimilation methods based on a large amount of local observation data in academia and industry at home and abroad. The Denmark university of science and technology provides a method for evaluating offshore wind resources by fusion of laser radar and mesoscale data, which proves that the multi-source data fusion can improve the evaluation accuracy.
At present, no research is performed on combining the actual observed wind speed of a wind measuring tower with the full-field CFD numerical simulation wind speed and the scale climate data in a wind power plant, and fusion research is performed on the wind speed data at the target point of the wind power plant to be developed and built. Aiming at the problems that the real observation data resources of the wind power plant to be developed and built are relatively deficient, the prior art cannot be qualified for high-precision resource evaluation and the like, and the wind speed data fusion research based on multi-source data for transfer learning is a front-edge hot spot in the current field.
In order to solve the above problems, embodiments of the present disclosure provide a fusion wind speed calculation method, apparatus, device, and medium based on transfer learning.
The fusion wind speed calculation method based on transfer learning provided by the embodiment of the present disclosure is first described with reference to fig. 1-2.
In the embodiment of the disclosure, the fusion wind speed calculation method based on transfer learning can be executed by electronic equipment. Among them, the electronic devices may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), in-vehicle terminals (e.g., in-vehicle navigation terminals), wearable devices, etc., and stationary terminals such as digital TVs, desktop computers, smart home devices, etc.
Fig. 1 shows a flowchart of a fusion wind speed calculation method based on transfer learning according to an embodiment of the present disclosure.
As shown in fig. 1, the fusion wind speed calculation method based on the transfer learning may include the following steps.
S110, determining a reference anemometer tower from the plurality of anemometer towers according to the wind speed correlation.
In the embodiment of the disclosure, the electronic device may determine the reference anemometer tower from among the plurality of anemometer towers through wind speed correlation.
Alternatively, the anemometer tower may be a device for measuring wind speed at a specific point.
Alternatively, the wind speed correlation may be a correlation for representing the wind speed between the respective anemometer towers.
Alternatively, the reference anemometer tower may be a anemometer tower that is a calculation reference for other anemometer towers.
Specifically, the electronic device may determine a wind speed correlation between the respective wind towers, thereby determining a reference wind tower from among the plurality of wind towers.
Optionally, S110 may specifically include: acquiring time sequence wind speed sequences of a plurality of wind towers at a first preset height, and calculating the wind speed correlation of the wind towers; and determining the anemometer tower with the maximum wind speed correlation as a reference anemometer tower.
In the embodiment of the disclosure, the electronic device may acquire time-series wind speed sequences of the plurality of anemometers at the first preset height, and calculate wind speed correlations of the plurality of anemometers.
Alternatively, the first preset height may be a preset height. For example, the first preset height may be a hub height of the wind turbine generator, such as 90m, 100m, etc., which is not limited herein.
Optionally, the time-series wind speed sequence may be a time-series wind speed data sequence of a plurality of anemometers within a preset time. Wherein the preset time may be 1 year or more. For example, the time series wind speed sequence may include all time series wind speed data obtained by a plurality of anemometers at data intervals of 10 minutes over 1 year.
Specifically, the electronic device may obtain time-series wind speed sequences corresponding to the plurality of wind towers within a preset time, and calculate a wind speed correlation between the wind towers according to the time-series wind speed sequences, where a method for calculating the wind speed correlation may be a known calculation method, which is not limited herein.
Further, after obtaining the wind speed correlations of the plurality of wind towers, the electronic device may determine the wind tower with the largest wind speed correlation as the reference wind tower.
In the embodiment of the disclosure, after the electronic device calculates the wind speed correlation between the wind towers, the wind tower with the maximum wind speed correlation with other wind towers may be determined, and the wind tower is used as a reference wind tower.
FIG. 2 illustrates a thermal schematic of a wind speed dependence provided by an embodiment of the present disclosure.
As shown in fig. 2, the wind speed correlation between 5 wind towers is included, the darker the color is the greater the wind speed correlation, the greater the digital mark is the greater the wind speed correlation, wherein the electronic device may determine one wind tower, such as wind tower # 2, with the maximum wind speed correlation with other wind towers, and use the wind tower # 2 as a reference wind tower.
Therefore, the reference wind measuring tower can be determined through the wind speed correlation, so that calculation is performed by taking the reference wind measuring tower as a reference in the subsequent calculation process, and the calculation accuracy can be improved.
S120, acquiring first real observed wind speed data and first simulated wind speed data of a reference anemometer tower, and acquiring second simulated wind speed data of a target point location.
In the embodiment of the disclosure, after determining the reference anemometer tower, the electronic device may acquire first real observed wind speed data and first simulated wind speed data of the reference anemometer tower, and acquire second simulated wind speed data of the target point location.
Alternatively, the first true observed wind speed data may be the wind speed that is actually measured at the reference anemometer tower.
Alternatively, the first simulated wind speed data may be a simulated wind speed at a reference anemometer tower calculated by a CFD method.
Alternatively, the target point location may be a point location where wind speed needs to be calculated.
Alternatively, the second simulated wind speed data may be a simulated wind speed at the target point location calculated by CFD method.
Specifically, the electronic device may obtain, after determining the reference anemometer tower, first real observed wind speed data and first simulated wind speed data of the reference anemometer tower, and second simulated wind speed data of the target point location.
S130, performing time sequence wind speed calculation on the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data to obtain first time sequence wind speed data of the target point position.
In the embodiment of the disclosure, after acquiring the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data, the electronic device may perform time-series wind speed calculation on the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data to obtain first time-series wind speed data of the target point location.
Optionally, S130 may specifically include: substituting the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data into a time sequence wind speed calculation formula to obtain first time sequence wind speed data of the target point position.
Alternatively, the time-series wind speed calculation may be calculated by a time-series wind speed calculation formula.
Alternatively, the time-series wind speed calculation formula may be:
wherein, the point position of the reference anemometer tower is A, the target point position is B, V A Can be the first real observed wind speed data used for representing the reference anemometer tower, namely the point position A, V CFDA Can be the first simulated wind speed data for representing the reference anemometer tower, namely point position A, V CFDB Can be the second simulated wind speed data for representing the target point position, namely the point position B, V CFD May be first timing wind speed data representing a target point location, point location B.
Alternatively, the first chronograph wind speed data may be preliminary chronograph wind speed data at a target point location.
Specifically, the electronic device may perform time-series wind speed calculation on the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data through a time-series wind speed calculation formula, so as to obtain first time-series wind speed data of the target point location, and obtain the preliminary time-series wind speed data.
For example, the electronic device may calculate the first real observed wind speed data V of the point a where the reference anemometer tower is located through a time-series wind speed calculation formula A First simulated wind speed data V CFDA And second simulated wind speed data V of target point location B CFDB Performing time sequence wind speed calculation to obtain first time sequence wind speed data V of target point positions CFD 。
And S140, performing model calculation on the first time sequence wind speed data through a transfer learning neural network model to obtain first fusion time sequence wind speed data of the target point position.
In the embodiment of the disclosure, after obtaining the first time-series wind speed data, the electronic device may perform model calculation on the first time-series wind speed data through the transfer learning neural network model to obtain first fused time-series wind speed data of the target point location.
Alternatively, the transfer learning neural network model may be a pre-trained model.
Alternatively, the model calculation may be a calculation of the first timing wind speed data by a transfer learning neural network model.
Alternatively, the first chronograph wind speed data may be final chronograph wind speed data at the target point location.
Specifically, the electronic device may perform model calculation on the first time-series wind speed data through the transfer learning neural network model, that is, further fuse and correct the preliminary time-series wind speed data, so as to obtain first fused time-series wind speed data of the target point location, that is, obtain final time-series wind speed data.
Optionally, S140 may specifically include: inputting the first time sequence wind speed data into a transfer learning neural network model, so that the transfer learning neural network model carries out model calculation on the first time sequence wind speed data, and first fusion time sequence wind speed data of the target point position is obtained.
In the embodiment of the disclosure, after obtaining the first time-sequence wind speed data, the electronic device may input the first time-sequence wind speed data into the transfer learning neural network model, and the transfer learning neural network model may receive and perform model calculation on the first time-sequence wind speed data, so as to obtain first fused time-sequence wind speed data, and output the first fused time-sequence wind speed data, and the electronic device may obtain the first fused time-sequence wind speed data of the target point location.
Therefore, in the embodiment of the disclosure, the reference wind measuring tower can be determined according to the wind speed correlation in the wind measuring towers, then the first real observation wind speed data and the first simulation wind speed data of the reference wind measuring tower are obtained, the second simulation wind speed data of the target point location is obtained, then the time sequence wind speed calculation is carried out on the first real observation wind speed data, the first simulation wind speed data and the second simulation wind speed data to obtain the first time sequence wind speed data of the target point location, finally the model calculation is carried out on the first time sequence wind speed data through the migration learning neural network model to obtain the first fusion time sequence wind speed data of the target point location, and therefore the fusion calculation can be carried out through the first real observation wind speed data, the first simulation wind speed data and the second simulation wind speed data of the target point location of the reference wind measuring tower and the migration learning neural network model to obtain the first fusion time sequence wind speed data of the target point location, so that the wind speed calculation accuracy is effectively improved through the method of fusion calculation of data.
Optionally, before S120, the fusion wind speed calculation method based on the transfer learning may further include: the method comprises the steps of obtaining a simulated wind speed data table of each point position through a computational fluid dynamics method, wherein the simulated wind speed data table comprises time sequence wind direction label characteristics, the time sequence wind direction label characteristics are mesoscale wind direction data at a second preset height, and the simulated wind speed data table comprises first simulated wind speed data and second simulated wind speed data.
In the embodiment of the disclosure, the electronic equipment can acquire the simulated wind speed data table of each point location through a computational fluid dynamics method.
Alternatively, computational fluid dynamics (Computational Fluid Dynamics, CFD) methods may be used to calculate model wind speed data for various points.
Alternatively, the simulated wind speed data table may comprise wind speed data at a first preset altitude at different wind directions at each point. Wherein the simulated wind speed data table may include a time-series wind direction tag feature.
Alternatively, the time series wind vane features may be mesoscale wind direction data at the second preset height for each point.
Alternatively, the second preset height may be a predefined height. For example, the second preset height may be 1500m, 1600m, etc., which is not limited herein.
Alternatively, the mesoscale wind direction data may be data characterising wind direction at a second preset height. For example, the mesoscale wind direction data may be data characterizing a wind direction of southeast wind, northeast wind, etc. at the second predetermined altitude, without limitation.
Specifically, the electronic device may obtain wind speed data at a first preset height under different wind directions at each point location by using a Computational Fluid Dynamics (CFD) method, so as to obtain a simulated wind speed data table.
For example, the electronic device may calculate, by using a CFD method, numerical simulation of a wind farm flow field in 16 wind direction sectors, and obtain model wind speed data at a first preset height of each point location (including a target point location) in the wind farm in 16 wind direction sectors under a neutral condition, to form a simulated wind speed data table, where each wind tower may correspond to one point location.
Optionally, due to the influence of factors such as topography and topography, the wind directions of various points in the wind farm are different, and the wind direction of a certain anemometer tower cannot be used as an inlet wind direction boundary condition of the wind farm flow field CFD simulation, so that mesoscale wind direction data at a second preset height, such as 1500m, needs to be acquired as time sequence wind direction label characteristics in the simulated wind speed data table.
Optionally, the simulated wind speed data table may include first simulated wind speed data of the point where the reference anemometer tower is located and second simulated wind speed data of the target point.
Therefore, in the embodiment of the disclosure, the simulated wind speed data table can be obtained through the CFD method, so that corresponding data is provided for subsequent calculation, and the wind speed calculation accuracy is effectively improved.
Optionally, before S140, the fusion wind speed calculation method based on the transfer learning may further include: according to the first real observed wind speed data and the first simulated wind speed data of the reference wind measuring tower and the second real observed wind speed data and the third simulated wind speed data of the fusion wind measuring tower, model training is carried out on the neural network model to be trained to obtain a trained neural network model, and the fusion wind measuring tower is a wind measuring tower except the reference wind measuring tower in a plurality of wind measuring towers;
and performing transfer learning processing on the trained neural network model to obtain a transfer learning neural network model.
In the embodiment of the disclosure, the electronic device may perform model training on the neural network model to be trained according to the first real observed wind speed data and the first simulated wind speed data of the reference wind measuring tower and the second real observed wind speed data and the third simulated wind speed data of the fusion wind measuring tower, so as to obtain a trained neural network model.
Alternatively, the fused anemometer tower may be a anemometer tower other than the reference anemometer tower among the plurality of anemometer towers.
For example, after the electronic device determines that the wind tower # 2 is the reference wind tower, it can determine that #1, #3, #4, and #5 are the fusion wind towers.
Alternatively, the second true observed wind speed data may be the wind speed that is actually measured at the fused anemometer tower.
Alternatively, the third simulated wind speed data may be a simulated wind speed at the fused anemometer tower calculated by a CFD method.
Specifically, the electronic device may obtain the first real observed wind speed data of the reference anemometer tower and the second real observed wind speed data of the fusion anemometer tower by measuring, then obtain the first simulated wind speed data of the simulated wind speed data table and the third simulated wind speed data of the fusion anemometer tower in the simulated wind speed data table, and perform model training on the neural network model to be trained through the data, so as to obtain a trained neural network model, and obtain parameters in the trained neural network model.
Further, after the electronic device obtains the trained neural network model, the electronic device can perform transfer learning processing on the trained neural network model to obtain a transfer learning neural network model.
Alternatively, the migration learning process may assist in new model training for migrating trained model parameters to a new model.
Specifically, after the electronic device obtains the trained neural network model, parameters in the trained neural network model can be migrated to a new model to perform model training, so as to obtain a migration learning neural network model.
For example, the electronic device may perform the migration learning process on the reference anemometer tower and the neural network model trained by the fusion anemometer tower, so as to obtain a migration learning neural network model corresponding to the target point location. The electronic device uses an artificial neural network (Artificial Neural Network, ANN) as a kernel network model for transfer learning, and applies a Back Propagation (BP) algorithm to train the model to establish a reliable transfer learning neural network model.
Therefore, in the embodiment of the disclosure, the electronic equipment can obtain a relatively accurate migration learning neural network model through migration learning processing, so that the accuracy of calculating the wind speed subsequently is improved.
Optionally, after performing the migration learning process on the trained neural network model to obtain a migration learning neural network model, the fusion wind speed calculation method based on migration learning may further include: and carrying out error analysis and calculation on the transfer learning neural network model through the second time sequence wind speed data and the second fusion time sequence wind speed data of the test wind measuring tower to obtain an error result, wherein the error analysis and calculation is used for calculating root mean square error of the second time sequence wind speed data and the second fusion time sequence wind speed data and third real observation wind speed data of the test wind measuring tower.
In the embodiment of the disclosure, the electronic device may perform error analysis calculation on the transfer learning neural network model by testing the second time-series wind speed data and the second fusion time-series wind speed data of the wind measuring tower, so as to obtain an error result.
Alternatively, the test anemometer tower may be any one of a plurality of fused anemometer towers.
For example, there are 5 wind towers, and after the electronic device determines that wind tower # 2 is the reference wind tower, it may determine that #1, #3, #4, #5 may be the fusion wind tower, and then it may determine that wind tower # 1 is the test wind tower.
Alternatively, the second time-series wind speed data may be preliminary time-series wind speed data at the test wind tower. The second time-series wind speed data may be obtained by performing time-series wind speed calculation according to a time-series wind speed calculation formula, and detailed description thereof is omitted herein.
Alternatively, the second fused temporal wind speed data may be final temporal wind speed data at the test anemometer tower. The second fused time-series wind speed data may be obtained by performing model calculation through a transfer learning neural network model, and the detailed description is omitted herein.
Optionally, the error analysis is calculated as calculating a root mean square error of the second time series wind speed data and the second fused time series wind speed data with the third true observed wind speed data of the test wind tower.
Alternatively, the third true observed wind speed data may be the wind speed that is actually measured at the test anemometer tower.
Alternatively, the root mean square error may be the square root of the ratio of the square sum of the deviations of the second time-series wind speed data and the second fused time-series wind speed data from the third real observed wind speed data, respectively, to the number of observations n.
Alternatively, the error analysis calculation may be calculated by an error analysis calculation formula.
Alternatively, the error analysis calculation formula may be:
wherein i=1, 2,3,. The. N is the length of the selected time series (resolution 10 min), V model Can represent second time-series wind speed data or second fusion time-series wind speed data, V obs The third true observed wind speed data may be represented.
Specifically, the electronic device may perform error analysis and calculation on the second time-series wind speed data and the third real observed wind speed data, and the second fused time-series wind speed data and the third real observed wind speed data according to an error analysis and calculation formula, so as to obtain a corresponding error result, that is, obtain a corresponding root mean square error.
For example, there are 5 wind towers, the wind tower # 2 is a reference wind tower, the wind tower # 1 is a test wind tower, the wind towers #3, #4 and #5 can be combined, the electronic device can perform error analysis and calculation on the test wind tower # 1 through an error analysis and calculation formula to obtain a corresponding root mean square error, for example, the root mean square error of the second time sequence wind speed data and the third real observed wind speed data is 1.03m/s, and the root mean square error of the second combined time sequence wind speed data and the third real observed wind speed data is 0.81m/s, so that the root mean square error of the second combined time sequence wind speed data calculated by the migration learning neural network model is smaller than that of the second time sequence wind speed data, that is, the second combined time sequence wind speed data is more accurate.
Therefore, in the embodiment of the disclosure, the wind speed calculation accuracy can be effectively improved by the method of fusion calculation of the data.
The embodiment of the disclosure also provides a fusion wind speed calculation device based on transfer learning, and the fusion wind speed calculation device is described below with reference to fig. 3.
In an embodiment of the disclosure, the fusion wind speed computing device based on transfer learning may be an electronic device. Among other things, the electronic devices may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDA, PAD, PMP, in-vehicle terminals (e.g., in-vehicle navigation terminals), wearable devices, and the like, and stationary terminals such as digital TVs, desktop computers, smart home devices, and the like.
Fig. 3 illustrates a schematic structural diagram of a fusion wind speed computing device based on transfer learning according to an embodiment of the present disclosure.
As shown in fig. 3, the fusion wind speed computing device 300 based on the transfer learning may include a data determination module 310, a first acquisition module 320, a first computing module 330, and a second computing module 340.
The data determination module 310 may be configured to determine a baseline anemometer tower from the wind speed correlations among a plurality of anemometer towers.
The first obtaining module 320 may be configured to obtain first real observed wind speed data and first simulated wind speed data of the reference anemometer tower, and obtain second simulated wind speed data of the target point location.
The first calculation module 330 may be configured to perform time-series wind speed calculation on the first real observed wind speed data, the first simulated wind speed data, and the second simulated wind speed data, so as to obtain first time-series wind speed data of the target point location.
The second calculation module 340 may be configured to perform model calculation on the first time-series wind speed data through a transfer learning neural network model, so as to obtain first fused time-series wind speed data of the target point location.
In the embodiment of the disclosure, a reference wind tower can be determined according to the wind speed correlation in a plurality of wind towers, then first real observed wind speed data and first simulated wind speed data of the reference wind tower are obtained, second simulated wind speed data of a target point location are obtained, then time-sequence wind speed calculation is carried out on the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data to obtain first time-sequence wind speed data of the target point location, finally model calculation is carried out on the first time-sequence wind speed data through a migration learning neural network model to obtain first fused time-sequence wind speed data of the target point location, and therefore fusion calculation can be carried out through the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data of the target point location of the reference wind tower and the migration learning neural network model to obtain first fused time-sequence wind speed data of the target point location, and therefore the wind speed calculation accuracy is effectively improved through a method of fusion calculation of data.
In some embodiments of the present disclosure, the data determination module 310 may specifically include a data acquisition unit and a data determination unit.
The data acquisition unit may be configured to acquire a time-series wind speed sequence of the plurality of wind towers at a first preset altitude, and calculate a wind speed correlation of the plurality of wind towers.
The data determining unit may be configured to determine a wind tower with the highest wind speed correlation as a reference wind tower.
In some embodiments of the present disclosure, the fusion wind speed computing device 300 based on transfer learning may further include a second acquisition module.
The second obtaining module may be configured to obtain, by using a computational fluid dynamics method, a simulated wind speed data table of each point location before obtaining first real observed wind speed data and first simulated wind speed data of the reference anemometer tower and second simulated wind speed data of the target point location, where the simulated wind speed data table includes a time-series wind direction tag feature, and the time-series wind direction tag feature is mesoscale wind direction data at a second preset height, and the simulated wind speed data table includes the first simulated wind speed data and the second simulated wind speed data.
In some embodiments of the present disclosure, the first computing module 330 may specifically include a first computing unit.
The first calculation unit may be configured to substitute the first real observed wind speed data, the first simulated wind speed data, and the second simulated wind speed data into a time-series wind speed calculation formula to obtain first time-series wind speed data of the target point location.
In some embodiments of the present disclosure, the fusion wind speed computing device 300 based on transfer learning may further include a model training module and a model processing module.
The model training module can be used for carrying out model training on the neural network model to be trained according to the first real observation wind speed data and the first simulation wind speed data of the reference wind measuring tower and the second real observation wind speed data and the third simulation wind speed data of the fusion wind measuring tower before carrying out model calculation on the time sequence wind speed data through the transfer learning neural network model to obtain first fusion time sequence wind speed data of the target point position, and carrying out model training on the neural network model to be trained to obtain a trained neural network model, wherein the fusion wind measuring tower is a wind measuring tower except the reference wind measuring tower in the multiple wind measuring towers.
The model processing module can be used for performing transfer learning processing on the trained neural network model to obtain a transfer learning neural network model.
In some embodiments of the present disclosure, the fusion wind speed computing device 300 based on transfer learning may further include a third computing module.
The third calculation module may be configured to perform an error analysis calculation on the transfer learning neural network model by testing the second time-series wind speed data and the second fusion time-series wind speed data of the wind tower after performing the transfer learning process on the trained neural network model to obtain the transfer learning neural network model, so as to obtain an error result, where the error analysis calculation is to calculate root mean square errors of the second time-series wind speed data and the second fusion time-series wind speed data and third real observed wind speed data of the wind tower.
In some embodiments of the present disclosure, the second computing module 340 may specifically include a second computing unit.
The second calculation unit may be configured to input the first time-series wind speed data into the transfer learning neural network model, so that the transfer learning neural network model performs model calculation on the first time-series wind speed data to obtain first fused time-series wind speed data of the target point location.
It should be noted that, the fusion wind speed computing device 300 based on the transfer learning shown in fig. 3 may perform the steps in the method embodiments shown in fig. 1 to 2, and implement the processes and effects in the method embodiments shown in fig. 1 to 2, which are not described herein.
The disclosed embodiments also provide an electronic device that may include a processor and a memory that may be used to store executable instructions. The processor may be configured to read the executable instructions from the memory and execute the executable instructions to implement the fusion wind speed calculation method based on the migration learning in the foregoing embodiment.
Fig. 4 shows a schematic structural diagram of a fusion wind speed computing device based on transfer learning according to an embodiment of the present disclosure.
In some embodiments of the present disclosure, the fusion wind speed computing device based on transfer learning shown in fig. 4 may be an electronic device that a user wants to perform wind speed computing operations. Among them, the electronic device may include, but is not limited to, a mobile terminal such as a notebook computer, a PDA (personal digital assistant), a PAD (tablet computer), etc., and a fixed terminal such as a digital TV, a desktop computer, etc.
As shown in fig. 4, the fusion wind speed computing device based on transfer learning may include a processor 401 and a memory 402 storing computer program instructions.
In particular, the processor 401 described above may include a Central Processing Unit (CPU), or an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), or may be configured to implement one or more integrated circuits of embodiments of the present application.
The processor 401 reads and executes the computer program instructions stored in the memory 402 to perform the steps of the fusion wind speed calculation method based on the transfer learning provided in the embodiment of the present disclosure.
In one example, the fusion wind speed computing device based on transfer learning may further include a transceiver 403 and a bus 404. As shown in fig. 4, the processor 401, the memory 402, and the transceiver 403 are connected by a bus 404 and perform communication with each other.
The embodiments of the present disclosure also provide a computer-readable storage medium, which may store a computer program, where the computer program when executed by a processor causes the processor to implement the fusion wind speed calculation method based on the migration learning provided by the embodiments of the present disclosure.
The storage medium described above may, for example, comprise a memory 402 of computer program instructions executable by the processor 401 of the fusion wind speed computing device based on transfer learning to perform the fusion wind speed computing method based on transfer learning provided by the embodiments of the present disclosure. Alternatively, the storage medium may be a non-transitory computer readable storage medium, for example, a ROM, a random access memory (Random Access Memory, RAM), a Compact Disc ROM (CD-ROM), a magnetic tape, a floppy disk, an optical data storage device, and the like.
It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The foregoing is merely a specific embodiment of the disclosure to enable one skilled in the art to understand or practice the disclosure. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the disclosure. Thus, the present disclosure is not intended to be limited to the embodiments shown and described herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (10)
1. The fusion wind speed calculation method based on transfer learning is characterized by comprising the following steps of:
determining a reference anemometer tower from among the plurality of anemometer towers according to the wind speed correlation;
acquiring first real observed wind speed data and first simulated wind speed data of the reference anemometer tower, and acquiring second simulated wind speed data of a target point location;
performing time sequence wind speed calculation on the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data to obtain first time sequence wind speed data of the target point position;
and performing model calculation on the first time sequence wind speed data through a transfer learning neural network model to obtain first fusion time sequence wind speed data of the target point location.
2. The method of claim 1, wherein determining a reference anemometer tower from a wind speed correlation among a plurality of anemometer towers comprises:
acquiring time sequence wind speed sequences of the plurality of anemometer towers at a first preset height, and calculating the wind speed correlation of the plurality of anemometer towers;
and determining the anemometer tower with the maximum wind speed correlation as the reference anemometer tower.
3. The method of claim 1, wherein prior to the acquiring the first true observed wind speed data and the first simulated wind speed data of the reference anemometer tower and the second simulated wind speed data of the target point location, the method further comprises:
the method comprises the steps of obtaining a simulated wind speed data table of each point position through a computational fluid dynamics method, wherein the simulated wind speed data table comprises time sequence wind direction label characteristics, the time sequence wind direction label characteristics are mesoscale wind direction data at a second preset height, and the simulated wind speed data table comprises first simulated wind speed data and second simulated wind speed data.
4. The method according to claim 1, wherein performing a time-series wind speed calculation on the first real observed wind speed data, the first simulated wind speed data, and the second simulated wind speed data to obtain first time-series wind speed data of the target point location comprises:
Substituting the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data into a time sequence wind speed calculation formula to obtain first time sequence wind speed data of the target point position.
5. The method of claim 1, wherein prior to the model calculation of the time-series wind speed data by the transfer learning neural network model to obtain the first fused time-series wind speed data of the target point location, the method further comprises:
according to the first real observed wind speed data and the first simulated wind speed data of the reference wind measuring tower, and the second real observed wind speed data and the third simulated wind speed data of a fusion wind measuring tower, model training is carried out on a neural network model to be trained to obtain a trained neural network model, wherein the fusion wind measuring tower is a wind measuring tower except the reference wind measuring tower in the plurality of wind measuring towers;
and performing transfer learning processing on the trained neural network model to obtain the transfer learning neural network model.
6. The method of claim 5, wherein after said performing a transfer learning process on said trained neural network model to obtain said transfer learning neural network model, said method further comprises:
And carrying out error analysis and calculation on the migration learning neural network model through second time sequence wind speed data and second fusion time sequence wind speed data of the test wind measuring tower to obtain an error result, wherein the error analysis and calculation is used for calculating root mean square error of the second time sequence wind speed data and the second fusion time sequence wind speed data and third real observation wind speed data of the test wind measuring tower.
7. The method according to claim 1, wherein the performing model calculation on the first time-series wind speed data by using the transfer learning neural network model to obtain first fused time-series wind speed data of the target point location includes:
and inputting the first time sequence wind speed data into the transfer learning neural network model so that the transfer learning neural network model carries out model calculation on the first time sequence wind speed data to obtain the first fusion time sequence wind speed data of the target point location.
8. A fusion wind speed computing device based on transfer learning, comprising:
the data determining module is used for determining a reference anemometer tower according to the wind speed correlation in the plurality of anemometer towers;
the first acquisition module is used for acquiring first real observed wind speed data and first simulated wind speed data of the reference anemometer tower and acquiring second simulated wind speed data of a target point location;
The first calculation module is used for carrying out time sequence wind speed calculation on the first real observed wind speed data, the first simulated wind speed data and the second simulated wind speed data to obtain first time sequence wind speed data of the target point position;
and the second calculation module is used for carrying out model calculation on the first time sequence wind speed data through a transfer learning neural network model to obtain first fused time sequence wind speed data of the target point location.
9. A fusion wind speed computing device based on transfer learning, comprising:
a processor;
a memory for storing executable instructions;
wherein the processor is configured to read the executable instructions from the memory and execute the executable instructions to implement the fusion wind speed calculation method based on transfer learning of any one of the preceding claims 1-7.
10. A computer readable storage medium, characterized in that the storage medium stores a computer program, which when executed by a processor causes the processor to implement the fusion wind speed calculation method based on transfer learning as claimed in any one of the preceding claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310248593.2A CN116432548A (en) | 2023-03-09 | 2023-03-09 | Fusion wind speed calculation method, device, equipment and medium based on transfer learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310248593.2A CN116432548A (en) | 2023-03-09 | 2023-03-09 | Fusion wind speed calculation method, device, equipment and medium based on transfer learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116432548A true CN116432548A (en) | 2023-07-14 |
Family
ID=87091678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310248593.2A Pending CN116432548A (en) | 2023-03-09 | 2023-03-09 | Fusion wind speed calculation method, device, equipment and medium based on transfer learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116432548A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117993136A (en) * | 2024-03-14 | 2024-05-07 | 深圳市千百炼科技有限公司 | Offshore wind power multi-model automatic arrangement and cable topological structure optimization method |
-
2023
- 2023-03-09 CN CN202310248593.2A patent/CN116432548A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117993136A (en) * | 2024-03-14 | 2024-05-07 | 深圳市千百炼科技有限公司 | Offshore wind power multi-model automatic arrangement and cable topological structure optimization method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP7344389B2 (en) | Cooperative positioning methods, devices, equipment and storage media | |
| Lackner et al. | Uncertainty analysis in MCP-based wind resource assessment and energy production estimation | |
| CN109779848B (en) | Method and device for obtaining full-field wind speed correction function and wind power plant | |
| Schindler et al. | Copula-based estimation of directional wind energy yield: A case study from Germany | |
| CN116432548A (en) | Fusion wind speed calculation method, device, equipment and medium based on transfer learning | |
| CN109307795B (en) | Waveform point detection method and device | |
| CN107730097B (en) | Bus load prediction method and device and computing equipment | |
| CN103885867B (en) | Online evaluation method of performance of analog circuit | |
| CN107330233B (en) | Method and device for analyzing design wind speed of power transmission tower | |
| CN111090907B (en) | Flight test transition judgment method | |
| CN110765640A (en) | Method, system and equipment for calculating effective wind speed of rotor | |
| CN115758717A (en) | Method and device for estimating simulated brightness temperature deviation, electronic equipment and storage medium | |
| CN112685977B (en) | Wind power plant wind resource unsteady value simulation method and device | |
| CN114841077A (en) | Wind power prediction method, device and medium | |
| CN108196087B (en) | Data processing apparatus | |
| CN109100103B (en) | Fan 1p signal identification method, device, terminal and computer readable storage medium based on continuous monitoring | |
| CN112700134A (en) | Method, system and equipment for wind measuring tower representativeness analysis | |
| CN117175585B (en) | Wind power prediction method, device, equipment and storage medium | |
| CN113775482B (en) | Maximum wind speed determination method and device for wind turbine generator and electronic equipment | |
| CN105893696B (en) | A kind of multistage reliability evaluation method that more products are gradually put into | |
| CN104516858A (en) | Phase diagram matrix method for nonlinear dynamic behavior analysis | |
| CN117970514B (en) | Global ocean gravity field model fusion system and method based on water depth | |
| CN116595381B (en) | Reservoir layered water temperature simulation method and system | |
| CN117349573B (en) | Wind power plant wind speed prediction method, electronic equipment and storage medium | |
| CN118148857B (en) | Fan monitoring method and device based on wind measuring tower turbulence transfer and terminal equipment |
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 |