CN116757101B - Cabin wind speed correction method and system based on mechanism model and neural network - Google Patents
Cabin wind speed correction method and system based on mechanism model and neural network Download PDFInfo
- Publication number
- CN116757101B CN116757101B CN202311047504.4A CN202311047504A CN116757101B CN 116757101 B CN116757101 B CN 116757101B CN 202311047504 A CN202311047504 A CN 202311047504A CN 116757101 B CN116757101 B CN 116757101B
- Authority
- CN
- China
- Prior art keywords
- wind speed
- data
- frequency
- scada
- low
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 76
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 56
- 238000012937 correction Methods 0.000 title claims abstract description 48
- 230000007246 mechanism Effects 0.000 title claims abstract description 31
- 238000004364 calculation method Methods 0.000 claims abstract description 21
- 230000009466 transformation Effects 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 35
- 238000012549 training Methods 0.000 claims description 21
- 238000010408 sweeping Methods 0.000 claims description 18
- 230000004913 activation Effects 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims description 15
- 230000009191 jumping Effects 0.000 claims description 12
- 238000001514 detection method Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 238000011156 evaluation Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 125000004122 cyclic group Chemical group 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000006798 recombination Effects 0.000 description 1
- 238000005215 recombination Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
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
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- 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
-
- 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
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
Abstract
According to the cabin wind speed correction method and system based on the mechanism model and the neural network, wind speed data and power data measured in an SCADA system are selected, the SCADA wind speed is divided into wind speed data sets of different working conditions according to rated wind speed, and theoretical wind speed is obtained through calculation of an empirical formula; calculating high-low frequency residual errors of the real wind speed and the theoretical wind speed by wavelet transformation, establishing a relation between the SCADA wind speed and the high-low frequency residual errors by using a neural network, inputting SCADA wind speed data from an actual running wind power plant into the trained neural network, and obtaining corresponding high-low frequency residual errors; and (3) performing one-to-one correspondence on the SCADA wind speed data and the residual data, and performing linear addition to obtain a real wind speed correction value. The method and the system have the characteristics of high calculation speed, high precision and good generalization, and can be widely used for correcting the wind speed of wind driven generators of different types.
Description
Technical Field
The application relates to the field of data processing and data transmission, in particular to a cabin wind speed correction method and system based on a mechanism model and a neural network.
Background
Along with the development of wind power technology, accurate wind speed data need to be obtained when economic benefit evaluation, power generation amount evaluation, cluster arrangement and operation control are carried out on a wind field. Because the real wind speed is not easy to directly measure, the wind speed of the engine room recorded by a data acquisition and monitoring control system (Supervisory ControI And Data AcquiSition System, SCADA for short) is usually used as an important parameter for analysis during fan evaluation and calculation. However, due to the influence of factors such as blade rotation and airflow distortion caused by the nacelle, the wind speed value measured by the SCADA cannot always directly reflect the actual wind speed of the impeller, and the wind speed value must be corrected for use, and the correction of the wind speed is called a nacelle transfer function.
At present, the method for correcting the SCADA wind speed is mainly divided into a theoretical calculation correction method and a function fitting method. The theoretical calculation correction method is mainly based on an aerodynamic theory, and nacelle wind speed correction is realized through theoretical calculation by utilizing a plurality of parameters of a wind generating set and operation data recorded by SCADA, but the method has insufficient calculation accuracy and cannot cover different machine types due to the fact that the number of parameters is large and the internal mechanism is complex; the method is simple and easy to use, but depends on the wind measuring tower data seriously, the configuration place of the wind measuring tower is demanding and has high cost, and only one typical wind turbine generator is usually selected to be provided with the wind measuring tower for characteristic evaluation, so that the method cannot meet the requirements of all fans in the whole field, and therefore, the method has high application cost and limited application scene.
Disclosure of Invention
In order to overcome the defects of the prior art, the application provides a cabin wind speed correction method and system which use the technologies of neural network, theoretical characteristics, model evaluation and correction and the like and consider wind power operation conditions, and particularly provides a cabin wind speed correction method and system based on a mechanism model and the neural network. According to the application, the laser radar is arranged at the impeller to measure the real wind speed, and then the physical mechanism is combined with the data model, so that the wind speed correction method has the characteristics of high calculation speed and high precision, is good in generalization, and can be widely used for correcting the wind speeds of wind driven generators of different types.
In a first aspect, the application provides a nacelle wind speed correction method based on a mechanism model and a neural network, comprising the following steps:
selecting wind speed data and power data measured in an SCADA system, and dividing the wind speed data and the power data according to a preset rule to obtain a variable-pitch working condition data set and an unchangeable-pitch working condition data set;
wherein the dividing according to the preset rule comprises: judging whether the wind speed data is smaller than rated wind speed data or not, if yes, judging that the wind speed data is the wind speed under the condition of no pitch change; if not, judging that the wind speed data is the wind speed under the variable pitch working condition;
the resolution ratio of wind speed data and power data in the SCADA system is 1s level;
the variable-pitch working condition data set and the non-variable-pitch working condition data set are averagely converted into data with the resolution of 30s level to be used as a characteristic data set;
acquiring air density information and wind sweeping area information, and calculating the air density information, the wind sweeping area information, the wind speed data and the power data according to a preset empirical formula to obtain a theoretical wind speed under corresponding working conditions；
Wherein, the preset empirical formula is:
；
wherein the method comprises the steps ofIs power data, +.>Is wind speed data>Is air density information, ++>Is wind sweeping area information;
obtaining the true wind speedThe theoretical wind speed is then converted by wavelet>And the true wind speed +.>Respectively decomposing to obtain corresponding high-frequency data and low-frequency data, and obtaining corresponding high-frequency residual ∈>And low frequency residual->The high frequency residual error is->And said low frequency residual->As a target dataset, the wind speed data is a feature dataset;
wherein the true wind speed measured by the laser radarThen the real wind speed is converted by wavelet>And theoretical wind speed->Respectively decomposing to obtain corresponding high frequency data ∈>、/>And low frequency data->、/>Then ∈>And->Subtracting to obtain high-frequency residual error of real wind speed high-frequency data and theoretical wind speed high-frequency data>Will->And->Subtracting to obtain a low-frequency residual error of the real wind speed low-frequency data and the theoretical wind speed low-frequency data>Specifically, real wind speed data are obtained, then the real wind speed data are decomposed into high-frequency data and low-frequency data through wavelet transformation, corresponding time points are recorded, and then theoretical wind speed is decomposed into the high-frequency data and the low-frequency data according to the time points of the real wind speed;
taking the characteristic data set as input, taking the target data set as output, training by using a neural network, determining a time step by using an optimization method, and establishing a wind speed-residual prediction model according to working conditions and high-low frequency data;
inputting SCADA wind speed data of a certain time step into a trained wind speed-residual error prediction model to obtain high-frequency residual error prediction value data and low-frequency residual error prediction value data of a corresponding time step;
and linearly adding the SCADA wind speed data with the high-frequency residual error predicted value data and the low-frequency residual error predicted value data to obtain a final real wind speed correction value.
Optionally, wherein the actual wind speed in front of the fan hub is measured by a lidar；
Measuring nacelle wind speed by SCADA system。
Optionally, the step of using the characteristic data set as input and the target data set as output to train with a neural network, determining a time step with an optimization method, and establishing a wind speed-residual prediction model according to the working condition and the high-low frequency data includes:
training by using a neural network, and establishing wind speed-residual error prediction models under two working conditions, wherein the total number of the wind speed-residual error prediction models is four: the method comprises the steps that firstly, SCADA wind speed is used as input under a variable pitch working condition, and high-frequency residual errors are used as output high-frequency residual error prediction models; second, SCADA wind speed is used as input under the variable pitch working condition, and low-frequency residual is used as output low-frequency residual prediction model; thirdly, under the condition of no pitch change, the SCADA wind speed is taken as input, and the high-frequency residual is taken as an output high-frequency residual prediction model; and fourthly, taking the SCADA wind speed under the condition of no pitch variation as an input, and taking the low-frequency residual as an output low-frequency residual prediction model.
Optionally, in the process of establishing the wind speed-residual prediction model, a gamma detection technology is used for carrying out optimization solution on the training time step and the prediction time step, and a layer-by-layer random jump method is adopted for carrying out optimization combination solution on parameters of each layer.
Optionally, the layer-by-layer random jitter method includes the following steps:
1) Determining parameters of random jitter, jitter range and jitter step length:
determining parameters to be optimized as the number of LSTM units of the second layer, a dropout value and an activation function; the fourth layer of full connection layer unit number and activation function; setting the range and the jumping step length of each parameter; the activation function is selected randomly for sigmod function, tanh function and relu function, and the parameter value calculation formula is as follows:
；
calculating a value for the current wheel,/->Calculating a value for the previous round,/->Is the minimum value of the range>At the maximum value of the range,for jumping step length +.>For randomly selecting a function of integers within a given range, < >>；
2) In the first round, randomly initializing the unit number, dropout value, mapping dimension and activation function of the selected layer in a given range, dividing a certain amount of wind speed and residual error data set into a training set and a testing set for training test and calculating precision, obtaining the precision value of the corresponding parameter, and recording the parameter combination and result; then adding a random positive integer or a negative integer to the unit number and the dropout value of the selected layer to multiply the jumping step length to obtain a next group of parameter values, wherein the parameter values cannot exceed a given range, the activation function is also randomly selected, and five rounds of repeated execution are performed;
3) Calculating the precision of five groups of random parameters, selecting the parameter combination with the highest precision, then executing the parameters of the fourth layer according to the step 2), likewise calculating the precision of the five groups of parameters, then selecting the parameter combination with the highest precision, and finally obtaining the optimal parameter combination.
Optionally, after acquiring SCADA wind speed data and judging working conditions according to the SCADA wind speed data, inputting the SCADA wind speed data into a corresponding high-frequency residual error prediction model and a corresponding low-frequency residual error prediction model to obtain a high-frequency residual error of a corresponding time stepAnd low frequency residual/>Finally, cabin wind speed->Adding the high frequency residual of said corresponding time step +.>And low frequency residual->Obtaining corrected true wind speed +.>I.e.
。
In a second aspect, the present application provides a nacelle wind speed correction system based on a mechanism model and a neural network, for implementing a nacelle wind speed correction method based on the mechanism model and the neural network according to the first aspect, including:
the division module is used for selecting wind speed data and power data measured in the SCADA system, dividing the wind speed data and the power data according to a preset rule, and obtaining a variable-pitch working condition data set and an unchangeable-pitch working condition data set;
the calculation module is used for acquiring air density information and wind sweeping area information, and calculating the air density information, the wind sweeping area information, the wind speed data and the power data according to a preset empirical formula to obtain a theoretical wind speed under corresponding working conditions；
The decomposition module is used for obtaining the real wind speedThe theoretical wind speed is then converted by wavelet>And the true wind speed +.>Respectively decomposing to obtain corresponding high-frequency data and low-frequency data, and obtaining corresponding high-frequency residual ∈>And low frequency residual->The high frequency residual error is->And said low frequency residual->As a target dataset, the wind speed data is a feature dataset;
the building module is used for taking the characteristic data set as input, taking the target data set as output, training by using a neural network, determining a time step by using an optimization method, and building a wind speed-residual prediction model according to working conditions and high-low frequency data;
the input module is used for inputting SCADA wind speed data with a certain time step into the trained wind speed-residual error prediction model to obtain high-frequency residual error prediction value data and low-frequency residual error prediction value data corresponding to the time step;
and the output module is used for carrying out linear addition on the SCADA wind speed data, the high-frequency residual error predicted value data and the low-frequency residual error predicted value data to obtain a final real wind speed correction value.
According to the cabin wind speed correction method and system based on the mechanism model and the neural network, wind speed data and power data measured in an SCADA system are selected, the SCADA wind speed is divided into wind speed data sets of different working conditions according to rated wind speed, and theoretical wind speed is obtained through calculation of an empirical formula; calculating high-low frequency residual errors of the real wind speed and the theoretical wind speed by wavelet transformation, establishing a relation between the SCADA wind speed and the high-low frequency residual errors by using a neural network, inputting SCADA wind speed data from an actual running wind power plant into the trained neural network, and obtaining corresponding high-low frequency residual errors; and (3) performing one-to-one correspondence on the SCADA wind speed data and the residual data, and performing linear addition to obtain a real wind speed correction value. The wind speed correction method has the characteristics of high calculation speed and high precision, has good generalization, and can be widely used for correcting the wind speeds of wind driven generators of different types.
Drawings
FIG. 1 shows a flow diagram of steps of a nacelle wind speed correction method based on a mechanism model and a neural network of the present application;
FIG. 2 shows a schematic diagram of a nacelle wind speed correction method based on a mechanism model and a neural network according to the application;
FIG. 3 shows a block diagram of a neural network of the present application;
FIG. 4 shows a block schematic of a nacelle wind speed correction system based on a mechanism model and a neural network according to the application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
Referring to fig. 1 and 2, a flow chart and a framework chart of a nacelle wind speed correction method based on a mechanism model and a neural network according to the application are shown, and a nacelle wind speed correction method 100 based on the mechanism model and the neural network includes:
s102: selecting wind speed data and power data measured in an SCADA system, and dividing the wind speed data and the power data according to a preset rule to obtain a variable-pitch working condition data set and an unchangeable-pitch working condition data set;
the method comprises the steps of establishing an original data set, selecting wind speed and power data in an SCADA system, and dividing the wind speed and power data into a variable-pitch working condition wind speed data set and an unchangeable-pitch working condition wind speed data set according to whether the wind speed reaches a rated wind speed or not, wherein the specific steps are as follows:
when the wind speed data are divided into working conditions, the model of the fan is required to be determined firstly, then the corresponding rated wind speed value when the rated power is reached is determined, and then the rated wind speed is used as a judgment basis. Taking a 2MW direct-drive type fan in a certain wind field as an example, the rated power is 2000kw, and the rated wind speed is 12m/s.
Optionally, the actual wind speed in front of the fan hub is measured by a laser radar；
Measuring nacelle wind speed by SCADA system，
Further, the wind speed of the fan recorded by the SCADA systemJudging whether the wind speed data is smaller than rated wind speed data by taking rated wind speed as a boundary;
if yes, judging that the wind speed data is the wind speed under the condition of no pitch change;
if not, judging that the wind speed data is the wind speed under the variable pitch working condition.
Optionally, the resolution of wind speed data and power data in the SCADA system is 1s level; and averagely converting the variable-pitch working condition data set and the non-variable-pitch working condition data set into data with the resolution of 30s level as a characteristic data set.
S104: acquiring air density information and wind sweeping area information, and calculating the air density information, the wind sweeping area information, the wind speed data and the power data according to a preset empirical formula to obtain a theoretical wind speed under corresponding working conditions；
The step is used for processing the data set, inputting SCADA wind speed, power and environment and model parameters into an empirical formula to obtain a corresponding theoretical wind speed. Specifically, air density information and wind sweeping area information are obtained, the air density information, the wind sweeping area information, the wind speed data and the power data are calculated according to a preset empirical formula, and a corresponding theoretical wind speed ∈10 is obtained>；
Wherein, in calculating the theoretical wind speedThe empirical formula used is as follows:
；
wherein the method comprises the steps ofIs the generator output power,/-, is>Wind speed recorded by SCADA, < >>Is air density->Is the wind sweeping area.
The derivation process of the empirical formula is as follows:
according to aerodynamic theory, when the air mass is at a certain speedFlow-through region->When the power of the air movement is expressed as:
（1）
in the formula (1),is air density->Is the wind sweeping area.
Power coefficientIs generally defined as:
（2）
in the formula (2),is the mechanical power of the wind power generator.
According toEquation (2), the relationship between fan mechanical power and power coefficient can be written as:
（3）
wherein:，
for tip speed ratio->For the radius of the blade>Is the generator speed.
Considering that the mechanical power of the fan is difficult to directly measure, the actually measured power is the power of the generator in the SCADA system, and the above formula (3) can be rewritten as:
（4）
wherein,is the energy conversion rate.
According to aerodynamic theory, the air flow through a fan blade can be divided into three categories, one category representing the wind speed in front of the bladeThe method comprises the steps of carrying out a first treatment on the surface of the One class indicates wind speed when passing through the blade>The method comprises the steps of carrying out a first treatment on the surface of the One type represents wind speed behind the blade +.>. Since anemometers are usually mounted near the fan blades, SCADA wind speed can be considered +.>. According to aerodynamic theory, the air kinetic energy absorbed by the fan blade can be expressed as:
（5）
（6）
substituting formula (6) into formula (5) above:
（7）
neglecting the difference between the mechanical power of the fan and the generator power, and substituting formula (4) into formula (7) to obtain:
（8）
from formula (4) and formula (8):
（9）
the empirical formula of the final obtained true wind speed and SCADA wind speed is as follows:
（10）
wherein the method comprises the steps ofIs the generator output power,/-, is>Is the wind speed recorded by SCADA.
S106: obtaining the true wind speedThe theoretical wind speed is then converted by wavelet>And the true wind speed +.>Respectively decomposing to obtain corresponding high-frequency data and low-frequency data, and obtaining corresponding high-frequency residual ∈>And low frequency residuesDifference (S)>The high frequency residual error is->And said low frequency residual->As a target dataset, the wind speed data is a feature dataset;
in this step, the true wind speed measured by the lidarThen the real wind speed is converted by wavelet>And theoretical wind speed->Respectively decomposing to obtain corresponding high frequency data ∈>、/>And low frequency data->、/>Then ∈>And->Subtracting to obtain high-frequency residual error of real wind speed high-frequency data and theoretical wind speed high-frequency data>Will->And->Subtracting to obtain a low-frequency residual error of the real wind speed low-frequency data and the theoretical wind speed low-frequency data>。
Specifically, after obtaining real wind speed data, decomposing the real wind speed data into high-frequency data and low-frequency data through wavelet transformation, recording corresponding time points, and then decomposing theoretical wind speed into the high-frequency data and the low-frequency data according to the time points of the real wind speed, wherein a wavelet transformation formula is shown in a formula (11):
(11)
in the formula (11), the color of the sample is,representing the mother wavelet function, +.>Representing the scaling factor and the translation factor, respectively. />Two conditions must be met:
first:，/>；
second,:；
wherein the method comprises the steps ofIs->Is a fourier transform of (a). At this time signal +.>Is calculated by equation (12):
（12）
wherein,is wavelet coefficient +.>Is->Is a conjugate of (c).
To describe time seriesThe continuous wavelet transform is discretized. Let +.>At this time, the expression (11) becomes:
（13）
time seriesThe discrete wavelet coefficient calculation formula of (2) is:
（14）
thus, the inverse transform formula for reconstructing the original signal from the wavelet coefficients is:
（15）
s108: taking the characteristic data set as input, taking the target data set as output, training by using a neural network, determining a time step by using an optimization method, and establishing a wind speed-residual prediction model according to working conditions and high-low frequency data;
FIG. 3 shows a structure diagram of a neural network according to the present application, wherein the neural network is a Self-Attention mechanism-based long-short-term memory cyclic neural network (Self-Attention-LSTM), the neural network has a five-layer structure, a first layer is an input layer, a characteristic data set is input, a second layer is an LSTM layer, and data of the first layer is sequentially calculated according to the number of batches through LSTM neurons to obtain corresponding hidden states as input of the next layer; the third layer is a self-attention layer, the hidden state input by the second layer is subjected to mapping recombination by using a self-attention mechanism, and the dimension after Q, K, V mapping is 10; the fourth layer is a full connection layer (Dense); the fifth layer is an output layer, and the final calculated value of the model is output. The weight and bias parameters of the neural network are the relation model between wind speed and residual error, and the residual error value can be obtained by inputting wind speed into the neural network.
Optionally, in an embodiment, the step of using the characteristic data set as input, the target data set as output, training with a neural network, determining a time step with an optimization method, and building a wind speed-residual prediction model according to the working condition and the high-low frequency data includes:
training by using a neural network, and establishing wind speed-residual error prediction models under two working conditions, wherein the total number of the wind speed-residual error prediction models is four: the method comprises the steps that firstly, SCADA wind speed is used as input under a variable pitch working condition, and high-frequency residual errors are used as output high-frequency residual error prediction models; second, SCADA wind speed is used as input under the variable pitch working condition, and low-frequency residual is used as output low-frequency residual prediction model; thirdly, under the condition of no pitch change, the SCADA wind speed is taken as input, and the high-frequency residual is taken as an output high-frequency residual prediction model; and fourthly, taking the SCADA wind speed under the condition of no pitch variation as an input, and taking the low-frequency residual as an output low-frequency residual prediction model.
In the process of establishing the wind speed-residual error prediction model, a gamma detection technology is used for carrying out optimization solution on training time step and prediction time step, and a layer-by-layer random jump method is used for carrying out optimization combination solution on parameters of each layer.
Specifically, for different fans, the time step of input and output is determined by a gamma detection algorithm, and parameters of each layer are determined by using a layer-by-layer random jumping method, but the overall structure of the neural network is not changed.
The gamma detection estimates the minimum mean square error present in the nonlinear model directly from the observed data, in this way the parameters of the input data can be determined.
Let the sample data be in the form of，/>Indicate->Line inputs, each->Possibly comprising a plurality of features, with +.>Indicating what kind of feature->Indicate->And outputs. Assuming that the vector contains a useful factor affecting the output, the relationship with it can be expressed as:
（16）
is a smooth unknown regression function, +.>Representing noise random variables. Because any constant deviation can be included in the unknown function, it is desirable to +.>Variance->。
If two pointsAnd->（/>) In the input space, the distances are very close, so that their corresponding outputs +.>And->The distance in the output space should also be very close, if not, we consider this difference to be due to noise +.>Resulting in the following. />The function calculates the mean of the square values of the distances of approach for each point in the input space as shown in equation (17):
（17）
wherein,is->Is>Near points, i.e.)>Is closest to->Is>Point(s) of (E)>Is->Is>Near points, i.e.)>Is closest to->Is>Point(s) of (E)>Representing Euclidean distance, corresponding +.>The function is as follows:
（18）
gamma detection switchComputing gamma statistics by making linear regression lines at pointsThe calculation formula is as follows:
（19）
in formula (19), the vertical intercept (whenZero) describes that by ∈>The value of the gamma statistic represented. If->Very small, regression function->Exist, output value->To a great extent dependent on the input variable +.>There is a close correlation between input and output. If->Large, indicating that the input is independent of the output.
Since the value of the gamma statistic is affected by the magnitude of the sample value, the statistic is consideredThe results were normalized. Statistics->The definition is as follows:
（20）
in the formula (20) of the present application,representing output +.>Is a variance of (c). Approximately 0 +.>The value indicates output +.>Has high predictability, approximately 1 +.>The value indicates output +.>Is random, and input variable->Irrespective of the fact that the first and second parts are.
Gamma detection selects the relevant specification of the embedding dimension:taking the value of the corresponding gamma statistic for the embedding dimension M, the smaller the corresponding embedding dimension of the gamma statistic is, that is to say the statistic +.>The closer the value of 0, the more reasonable the corresponding embedding dimension. Therefore, gamma detection can be performed separately by increasing the embedding dimension, using statistics +.>And judging and selecting a proper embedding dimension.
In the process of determining parameters of each layer by using a layer-by-layer random jumping method, the layer-by-layer random jumping method comprises the following steps:
1) Determining parameters of random jitter, jitter range and jitter step length:
determining parameters to be optimized as the number of LSTM units of the second layer, a dropout value and an activation function; the fourth layer of full connection layer unit number and activation function; setting the range and the jumping step length of each parameter; the activation function is selected randomly for sigmod function, tanh function and relu function, and the parameter value calculation formula is as follows:
（21）
in the method, in the process of the application,calculating a value for the current wheel,/->Calculating a value for the previous round,/->Is the minimum value of the range>For the maximum value of the range>For jumping step length +.>For randomly selecting a function of integers within a given range, < >>；
2) In the first round, randomly initializing the unit number, dropout value, mapping dimension and activation function of the selected layer in a given range, dividing a certain amount of wind speed and residual error data set into a training set and a testing set for training test and calculating precision, obtaining the precision value of the corresponding parameter, and recording the parameter combination and result; then adding a random positive integer or a negative integer to the unit number and the dropout value of the selected layer to multiply the jumping step length to obtain a next group of parameter values, wherein the parameter values cannot exceed a given range, the activation function is also randomly selected, and five rounds of repeated execution are performed;
3) Calculating the precision of five groups of random parameters, selecting the parameter combination with the highest precision, then executing the parameters of the fourth layer according to the step 2), likewise calculating the precision of the five groups of parameters, then selecting the parameter combination with the highest precision, and finally obtaining the optimal parameter combination.
S110: inputting SCADA wind speed data of a certain time step into a trained wind speed-residual error prediction model to obtain high-frequency residual error prediction value data and low-frequency residual error prediction value data of a corresponding time step;
and extracting the SCADA second-level wind speed every 10 to 20 times of the resolution multiplied by the time step according to the input time step and the resolution during training. Dividing the SCADA wind speed into a variable pitch working condition speed dividing and a non-variable pitch working condition wind speed according to whether the SCADA wind speed reaches a rated wind speed or not, then averaging according to a set resolution, and inputting the variable pitch working condition wind speed after resolution reduction into a trained variable pitch working condition high-low frequency residual prediction model to obtain a variable pitch working condition wind speed high-frequency residual prediction value and a variable pitch working condition wind speed low-frequency residual prediction value; and inputting the wind speed of the un-pitch working condition after the resolution is reduced into a trained high-frequency and low-frequency residual prediction model of the un-pitch working condition to obtain a high-frequency residual prediction value and a low-frequency residual prediction value of the wind speed of the un-pitch working condition.
S112: and linearly adding the SCADA wind speed data with the high-frequency residual error predicted value data and the low-frequency residual error predicted value data to obtain a final real wind speed correction value.
Respectively obtaining the wind speed high-frequency residual error predicted value under the variable pitch working conditionAnd low frequency residual prediction value->After the high-frequency residual predicted value and the low-frequency residual predicted value of the wind speed under the non-pitch-changing working condition, the SCADA pitch-changing working condition wind speed, the high-frequency residual predicted value and the low-frequency residual predicted value of the wind speed under the pitch-changing working condition are linearly obtainedAdding to obtain a final true pitch wind speed correction value; and linearly adding the SCADA non-pitching working condition wind speed, the non-pitching working condition wind speed high-frequency residual predicted value and the non-pitching working condition wind speed low-frequency residual predicted value to obtain a final true non-pitching wind speed corrected value.
That is, the nacelle wind speedAdding the high frequency residual of said corresponding time step +.>And low frequency residual->Obtaining corrected true wind speed +.>I.e.
。 （22）
According to the cabin wind speed correction method based on the mechanism model and the neural network, wind speed data and power data measured in an SCADA system are selected, the SCADA wind speed is divided into wind speed data sets of different working conditions according to rated wind speed, and theoretical wind speed is obtained through calculation of an empirical formula; calculating high-low frequency residual errors of the real wind speed and the theoretical wind speed by wavelet transformation, establishing a relation between the SCADA wind speed and the high-low frequency residual errors by using a neural network, inputting SCADA wind speed data from an actual running wind power plant into the trained neural network, and obtaining corresponding high-low frequency residual errors; and (3) performing one-to-one correspondence on the SCADA wind speed data and the residual data, and performing linear addition to obtain a real wind speed correction value. The wind speed correction method has the characteristics of high calculation speed and high precision, has good generalization, and can be widely used for correcting the wind speeds of wind driven generators of different types.
FIG. 4 shows a block schematic of a nacelle wind speed correction system based on a mechanism model and a neural network according to the application. A cabin wind speed correction system 200 based on a mechanism model and a neural network, for implementing a cabin wind speed correction method based on a mechanism model and a neural network as described above, comprising:
the dividing module 210 is configured to select wind speed data and power data measured in the SCADA system, and divide the wind speed data and the power data according to a preset rule to obtain a variable-pitch working condition dataset and an unchangeable-pitch working condition dataset;
the calculation module 220 is configured to obtain air density information and wind sweeping area information, calculate the air density information, the wind sweeping area information, the wind speed data and the power data according to a preset empirical formula, and obtain a theoretical wind speed under a corresponding working condition；
A decomposition module 230 for obtaining the true wind speedThe theoretical wind speed is then converted by wavelet>And the true wind speed +.>Respectively decomposing to obtain corresponding high-frequency data and low-frequency data, and obtaining corresponding high-frequency residual ∈>And low frequency residual->The high frequency residual error is->And said low frequency residual->As a target dataset, the wind speed data is a feature dataset;
the building module 240 is configured to take the feature data set as input, the target data set as output, perform training using a neural network, determine a time step by using an optimization method, and build a wind speed-residual prediction model according to the working condition and the high-low frequency data;
the input module 250 is configured to input SCADA wind speed data with a certain time step into a trained wind speed-residual prediction model, so as to obtain high-frequency residual prediction value data and low-frequency residual prediction value data corresponding to the time step;
and the output module 260 is configured to linearly add the SCADA wind speed data with the high-frequency residual prediction value data and the low-frequency residual prediction value data to obtain a final true wind speed correction value.
It will be clearly understood by those skilled in the art that, for convenience and brevity of description, the specific working process of the electronic device of the present application may refer to the corresponding process in the foregoing embodiments, and the parts and advantages same as those of the foregoing embodiments will not be repeated herein.
According to the cabin wind speed correction system based on the mechanism model and the neural network, wind speed data and power data measured in an SCADA system are selected, the SCADA wind speed is divided into wind speed data sets of different working conditions according to rated wind speed, and theoretical wind speed is calculated through an empirical formula; calculating high-low frequency residual errors of the real wind speed and the theoretical wind speed by wavelet transformation, establishing a relation between the SCADA wind speed and the high-low frequency residual errors by using a neural network, inputting SCADA wind speed data from an actual running wind power plant into the trained neural network, and obtaining corresponding high-low frequency residual errors; and (3) performing one-to-one correspondence on the SCADA wind speed data and the residual data, and performing linear addition to obtain a real wind speed correction value. The wind speed correction method has the characteristics of high calculation speed and high precision, has good generalization, and can be widely used for correcting the wind speeds of wind driven generators of different types.
In the several embodiments provided in the present application, it should be understood that the disclosed methods and systems may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the modules is only one logical function division, and there may be other divisions in practice, such as: multiple modules or components may be combined, or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The modules described above as separate components may or may not be physically separate, and components shown as modules may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present application may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present application may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
While certain specific embodiments of the application have been described in detail by way of example, it will be appreciated by those skilled in the art that the above examples are for illustration only and are not intended to limit the scope of the application. Those skilled in the art will also appreciate that many modifications may be made to the embodiments without departing from the scope and spirit of the application. The scope of the application is defined by the appended claims.
Claims (7)
1. The cabin wind speed correction method based on the mechanism model and the neural network is characterized by comprising the following steps of:
selecting wind speed data and power data measured in an SCADA system, and dividing the wind speed data and the power data according to a preset rule to obtain a variable-pitch working condition data set and an unchanged-pitch working condition data set;
wherein the dividing according to the preset rule comprises: judging whether the wind speed data is smaller than rated wind speed data or not, if yes, judging that the wind speed data is the wind speed under the condition of no pitch change; if not, judging that the wind speed data is the wind speed under the variable pitch working condition;
the resolution ratio of wind speed data and power data in the SCADA system is 1s level;
the variable-pitch working condition data set and the non-variable-pitch working condition data set are averagely converted into data with the resolution of 30s level to be used as a characteristic data set;
acquiring air density information and wind sweeping area information, and calculating the air density information, the wind sweeping area information, the wind speed data and the power data according to a preset empirical formula to obtain a theoretical wind speed under corresponding working conditions；
Wherein, the preset empirical formula is:
；
wherein the method comprises the steps ofIs power data, +.>Is wind speed data>Is air density information, ++>Is wind sweeping area information;
obtaining the true wind speedThe theoretical wind speed is then converted by wavelet>And the true wind speed +.>Respectively decomposing to obtain corresponding high-frequency data and low-frequency data, and obtaining corresponding high-frequency residual ∈>And low frequency residual->The high frequency residual error is->And said low frequency residual->As a target dataset, the wind speed data is a feature dataset;
wherein, the real wind speed is measured by a laser radarThen the real wind speed is converted by wavelet>And theoretical wind speed->Respectively decomposing to obtain corresponding high frequency data ∈>、/>And low frequency data->、/>Then ∈>And->Subtracting to obtain high-frequency residual error of real wind speed high-frequency data and theoretical wind speed high-frequency data>Will->And->Subtracting to obtain a low-frequency residual error of the real wind speed low-frequency data and the theoretical wind speed low-frequency data>Specifically, real wind speed data are obtained, then the real wind speed data are decomposed into high-frequency data and low-frequency data through wavelet transformation, corresponding time points are recorded, and then theoretical wind speed is decomposed into the high-frequency data and the low-frequency data according to the time points of the real wind speed;
taking the characteristic data set as input, taking the target data set as output, training by using a neural network, determining a time step by using an optimization method, and establishing a wind speed-residual prediction model according to working conditions and high-low frequency data;
inputting SCADA wind speed data of a certain time step into a trained wind speed-residual error prediction model to obtain high-frequency residual error prediction value data and low-frequency residual error prediction value data of a corresponding time step;
and linearly adding the SCADA wind speed data with the high-frequency residual error predicted value data and the low-frequency residual error predicted value data to obtain a final real wind speed correction value.
2. The nacelle wind speed correction method based on a mechanism model and a neural network of claim 1, wherein,
real wind speed in front of fan hub is measured through laser radar；
Measuring nacelle wind speed by SCADA system。
3. A nacelle wind speed correction method based on a mechanism model and a neural network as recited in claim 1, wherein,
the characteristic data set is taken as input, the target data set is taken as output, the neural network is used for training, the time step length is determined by an optimization method, and the wind speed-residual prediction model is built according to working conditions and high-low frequency data and comprises the following steps:
training by using a neural network, and establishing wind speed-residual error prediction models under two working conditions, wherein the total number of the wind speed-residual error prediction models is four: the method comprises the steps that firstly, SCADA wind speed is used as input under a variable pitch working condition, and high-frequency residual errors are used as output high-frequency residual error prediction models; second, SCADA wind speed is used as input under the variable pitch working condition, and low-frequency residual is used as output low-frequency residual prediction model; thirdly, under the condition of no pitch change, the SCADA wind speed is taken as input, and the high-frequency residual is taken as an output high-frequency residual prediction model; and fourthly, taking the SCADA wind speed under the condition of no pitch variation as an input, and taking the low-frequency residual as an output low-frequency residual prediction model.
4. The cabin wind speed correction method based on the mechanism model and the neural network according to claim 1, wherein in the process of establishing a wind speed-residual error prediction model, a gamma detection technology is used for carrying out optimization solution on a training time step and a prediction time step, and a layer-by-layer random jump method is used for carrying out optimization combined solution on parameters of each layer.
5. The nacelle wind speed correction method based on a mechanism model and a neural network according to claim 4, wherein the layer-by-layer random jump method comprises the steps of:
1) Determining parameters of random jitter, jitter range and jitter step length:
determining parameters to be optimized as the number of LSTM units of the second layer, a dropout value and an activation function; the fourth layer of full connection layer unit number and activation function; setting the range and the jumping step length of each parameter; the activation function is selected randomly for sigmod function, tanh function and relu function, and the parameter value calculation formula is as follows:
；
calculating a value for the current wheel,/->Calculating a value for the previous round,/->Is the minimum value of the range>For the maximum value of the range>For jumping step length +.>For randomly selecting a function of integers within a given range, < >>；
2) In the first round, randomly initializing the unit number, dropout value, mapping dimension and activation function of the selected layer in a given range, dividing a certain amount of wind speed and residual error data set into a training set and a testing set for training test and calculating precision, obtaining the precision value of the corresponding parameter, and recording the parameter combination and result; then adding a random positive integer or a negative integer to the unit number and the dropout value of the selected layer to multiply the jumping step length to obtain a next group of parameter values, wherein the parameter values cannot exceed a given range, the activation function is also randomly selected, and five rounds of repeated execution are performed;
3) Calculating the precision of five groups of random parameters, selecting the parameter combination with the highest precision, then executing the parameters of the fourth layer according to the step 2), likewise calculating the precision of the five groups of parameters, then selecting the parameter combination with the highest precision, and finally obtaining the optimal parameter combination.
6. A nacelle wind speed correction method based on a mechanism model and a neural network according to claim 3,
acquiring SCADA wind speed data, judging working conditions according to the SCADA wind speed data, and inputting the SCADA wind speed data into a corresponding high-frequency residual error prediction model and a corresponding low-frequency residual error prediction model to obtain a high-frequency residual error of a corresponding time stepAnd low frequency residual->Finally, cabin wind speed->Adding the high frequency residual of said corresponding time step +.>And low frequency residual->Obtaining corrected true wind speed +.>I.e.
。
7. Cabin wind speed correction system based on a mechanism model and a neural network for implementing a cabin wind speed correction method based on a mechanism model and a neural network as claimed in any one of claims 1-6, comprising:
the division module is used for selecting wind speed data and power data measured in the SCADA system, dividing the wind speed data and the power data according to a preset rule, and obtaining a variable-pitch working condition data set and an unchangeable-pitch working condition data set;
the calculation module is used for acquiring air density information and wind sweeping area information to be obtainedThe air density information, the wind sweeping area information, the wind speed data and the power data are calculated according to a preset empirical formula to obtain a theoretical wind speed under corresponding working conditions；
The decomposition module is used for obtaining the real wind speedThe theoretical wind speed is then converted by wavelet>And the true wind speed +.>Respectively decomposing to obtain corresponding high-frequency data and low-frequency data, and obtaining corresponding high-frequency residual ∈>And low frequency residualThe high frequency residual error is->And said low frequency residual->As a target dataset, the wind speed data is a feature dataset;
the building module is used for taking the characteristic data set as input, taking the target data set as output, training by using a neural network, determining a time step by using an optimization method, and building a wind speed-residual prediction model according to working conditions and high-low frequency data;
the input module is used for inputting SCADA wind speed data with a certain time step into the trained wind speed-residual error prediction model to obtain high-frequency residual error prediction value data and low-frequency residual error prediction value data corresponding to the time step;
and the output module is used for carrying out linear addition on the SCADA wind speed data, the high-frequency residual error predicted value data and the low-frequency residual error predicted value data to obtain a final real wind speed correction value.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311047504.4A CN116757101B (en) | 2023-08-21 | 2023-08-21 | Cabin wind speed correction method and system based on mechanism model and neural network |
| NL2036572A NL2036572A (en) | 2023-08-21 | 2023-12-18 | Nacelle wind speed correction method and system based on mechanism model and neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311047504.4A CN116757101B (en) | 2023-08-21 | 2023-08-21 | Cabin wind speed correction method and system based on mechanism model and neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116757101A CN116757101A (en) | 2023-09-15 |
| CN116757101B true CN116757101B (en) | 2023-11-07 |
Family
ID=87959518
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311047504.4A Active CN116757101B (en) | 2023-08-21 | 2023-08-21 | Cabin wind speed correction method and system based on mechanism model and neural network |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN116757101B (en) |
| NL (1) | NL2036572A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102562469A (en) * | 2011-12-27 | 2012-07-11 | 华北电力大学 | Short-term wind driven generator output power predicting method based on correction algorithm |
| CN110414045A (en) * | 2019-06-18 | 2019-11-05 | 东华大学 | Short-term wind speed forecasting method based on VMD-GRU |
| CN113537582A (en) * | 2021-07-02 | 2021-10-22 | 东北电力大学 | Photovoltaic power ultra-short-term prediction method based on short-wave radiation correction |
| CN114091377A (en) * | 2022-01-21 | 2022-02-25 | 南京理工大学 | Method for calculating wake flow wind speed of dynamic double-Gaussian wind turbine based on space change |
| CN115374710A (en) * | 2022-09-19 | 2022-11-22 | 兰州理工大学 | Wind speed prediction method based on improved gull optimization algorithm and multi-core extreme learning machine |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2016093905A1 (en) * | 2014-08-29 | 2016-06-16 | Tzunum Aircraft Llc | System and methods for implementing regional air transit network using hybrid-electric aircraft |
| CN110261394B (en) * | 2019-06-24 | 2022-09-16 | 内蒙古工业大学 | Online real-time diagnosis system and method for damage of fan blade |
| CN110566406B (en) * | 2019-10-16 | 2020-08-04 | 上海海事大学 | Wind turbine generator set real-time variable pitch robust control system and method based on reinforcement learning |
-
2023
- 2023-08-21 CN CN202311047504.4A patent/CN116757101B/en active Active
- 2023-12-18 NL NL2036572A patent/NL2036572A/en unknown
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102562469A (en) * | 2011-12-27 | 2012-07-11 | 华北电力大学 | Short-term wind driven generator output power predicting method based on correction algorithm |
| CN110414045A (en) * | 2019-06-18 | 2019-11-05 | 东华大学 | Short-term wind speed forecasting method based on VMD-GRU |
| CN113537582A (en) * | 2021-07-02 | 2021-10-22 | 东北电力大学 | Photovoltaic power ultra-short-term prediction method based on short-wave radiation correction |
| CN114091377A (en) * | 2022-01-21 | 2022-02-25 | 南京理工大学 | Method for calculating wake flow wind speed of dynamic double-Gaussian wind turbine based on space change |
| CN115374710A (en) * | 2022-09-19 | 2022-11-22 | 兰州理工大学 | Wind speed prediction method based on improved gull optimization algorithm and multi-core extreme learning machine |
Non-Patent Citations (2)
| Title |
|---|
| Power Data Preprocessing Method of Mountain Wind Farm Based on POT-DBSCAN;Zhao Xiao等;《Energy Engineering》;第549-563页 * |
| 基于运行规律和TICC算法的风电SCADA高维时序数据聚类方法;肖钊;《机械工程学报》;第58卷(第23期);第196-206页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116757101A (en) | 2023-09-15 |
| NL2036572A (en) | 2024-03-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108334672B (en) | Maximum wind energy capturing method of variable-speed wind generating set based on effective wind speed estimation | |
| US10815972B2 (en) | System and method for assessing and validating wind turbine and wind farm performance | |
| CN112861429B (en) | Wind turbine engine room transfer function calculation method | |
| CN112329339B (en) | Short-term wind speed prediction method for wind power plant | |
| CN111091236A (en) | Multi-classification deep learning short-term wind power prediction method classified according to pitch angles | |
| CN107045574A (en) | The low wind speed section effective wind speed method of estimation of wind power generating set based on SVR | |
| CN110365053B (en) | Short-term wind power prediction method based on delay optimization strategy | |
| CN110761958B (en) | Blade stall diagnosis method and device of wind generating set | |
| CN116757101B (en) | Cabin wind speed correction method and system based on mechanism model and neural network | |
| CN116624343B (en) | Wind turbine generator tower abnormal vibration monitoring and health degree evaluation method and system | |
| CN115013258B (en) | Intelligent soft measurement method for wind speed in front of wind turbine generator | |
| CN115578084A (en) | Wind turbine generator set frequency converter fault early warning method based on deep convolution self-encoder | |
| CN116306236A (en) | Wind power plant dynamic equivalent modeling method and system based on GRU-LSTM-FC combined network | |
| CN116123029A (en) | Pitch angle control method and device, electronic equipment and wind turbine generator | |
| CN112669168B (en) | Short-term prediction method for wind power | |
| CN113048012B (en) | Wind turbine generator yaw angle identification method and device based on Gaussian mixture model | |
| CN114186407A (en) | Wind power plant wake velocity field calculation method and system with parameters capable of being adjusted in self-adaptive mode | |
| CN114320770A (en) | Effective wind speed measuring method and device for wind turbine generator | |
| CN114239920A (en) | Short-term wind power prediction method | |
| CN113807693A (en) | Wind turbine generator generating capacity optimization effect evaluation method based on airborne radar | |
| Cascianelli et al. | Experimental prediction intervals for monitoring wind turbines: An ensemble approach | |
| CN111178601A (en) | Wind turbine generator power prediction method based on meteorological data post-processing | |
| CN113343562B (en) | Fan power prediction method and system based on hybrid modeling strategy | |
| CN117390967B (en) | Offshore wind power short-term power prediction method, device, equipment and storage medium | |
| CN116933570B (en) | Method and device for evaluating power generation capacity in wind power plant redevelopment process |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |