Wind turbine generator control method and system based on wind power plant wind regime prediction

Abstract

The embodiment of the invention provides a wind turbine generator control method and system based on wind power plant wind regime prediction, and belongs to the technical field of wind power. The method comprises the following steps: collecting operation condition information of a target wind turbine generator, and preprocessing the operation condition information; taking the preprocessed operation condition information as a model input parameter, performing wind speed prediction based on a pre-trained wind speed prediction model in real time, and obtaining a time sequence wind speed prediction value; performing average turbulence intensity prediction within a predetermined time period based on the time sequence wind speed prediction value; and matching and executing a corresponding wind turbine generator control scheme based on the wind speed numerical interval where the time sequence wind speed predicted value is located and the turbulence intensity numerical interval where the average turbulence intensity is located. According to the scheme, through accurate wind speed and turbulence prediction, accurate wind power equipment self-adaptive adjustment strategy intervention is achieved, and the operation stability and economic benefits of a wind turbine generator are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of wind power, and in particular to a wind turbine control method based on wind farm wind condition prediction and a wind turbine control system based on wind farm wind condition prediction. Background Art

[0002] At present, with the increasing prominence of environmental and energy issues, the development of renewable energy has become one of the core tasks of global economic and technological development. As one of the main renewable energy sources in my country, wind energy has the advantages of being free, clean and pollution-free. While meeting energy needs, it also provides important guarantees for the development of the national economy. As the main way to utilize wind energy, wind power generation occupies an important position in my country's renewable energy field. However, despite the huge potential of wind power generation, existing wind farms still face many challenges in actual operation.

[0003] Among them, the most significant problem is that the wind speed in the environment where the wind farm is located is highly unstable and volatile. This volatility leads to the instability of power generation during wind power generation, which directly affects the power generation efficiency and the stability of the power grid. When facing such complex environmental conditions, existing wind measurement devices usually have problems with insufficient wind measurement accuracy and delayed response, especially in the measurement of turbulence intensity. There are large errors. This not only makes the wind speed prediction inaccurate, but also limits the operation optimization of wind turbines.

[0004] In the prior art, the scheme of adaptively adjusting wind turbines according to changes in wind speed and turbulence intensity can theoretically optimize the power generation curve and extend the service life of the equipment. However, since accurate predictions of wind speed and turbulence are difficult to achieve, the adaptive adjustment strategy cannot be accurately intervened. In the absence of accurate prediction data support, the control scheme of wind turbines is usually inefficient or overly conservative, and cannot fully tap the potential of the equipment. In addition, inaccurate predictions may also cause the protection mechanism of wind turbines to fail to start in time under extreme weather conditions, increasing the risk of equipment failure. To address this problem, it is necessary to propose an adaptive adjustment scheme for the operating status of wind turbines based on accurate wind condition predictions. Summary of the invention

[0005] The purpose of the embodiments of the present invention is to provide a wind turbine control method and system based on wind farm wind condition prediction, so as to at least solve the problem of insufficient accuracy of equipment adaptive adjustment caused by insufficient accuracy of wind farm wind condition prediction.

[0006] In order to achieve the above-mentioned objectives, the first aspect of the present invention provides a wind turbine control method based on wind farm wind condition prediction, the method comprising: collecting operating condition information of the target wind turbine and preprocessing the operating condition information; using the preprocessed operating condition information as a model input parameter, performing wind speed prediction in real time based on a pre-trained wind speed prediction model, and obtaining a time series wind speed prediction value; performing an average turbulence intensity prediction within a predetermined time period based on the time series wind speed prediction value; matching and executing a corresponding wind turbine control scheme based on the wind speed numerical interval in which the time series wind speed prediction value is located and the turbulence intensity numerical interval in which the average turbulence intensity is located.

[0007] Optionally, the operating condition information is preprocessed, including: performing outlier processing, missing value processing and normalization processing on the operating condition information in sequence to obtain an initial data set; performing sliding window processing on the initial data set to obtain operating condition time series data of a preset time length as data after the preprocessing is completed.

[0008] Optionally, sliding window processing is performed on the initial data set to obtain operating condition time series data of a preset time length, including: determining the window length of the sliding window based on the preset time length, randomly adjusting the sliding window step size, and obtaining a preset number of candidate operating condition time series data in a predetermined historical data length; identifying and comparing data features of each candidate operating condition time series data, and screening out candidate operating condition time series data with the best features based on an optimization matching rule as the obtained operating condition time series data; wherein the data features are smoothness and / or volatility.

[0009] Optionally, the pre-training rules of the wind speed prediction model include: collecting historical operating condition information of the target wind turbine set, and performing wind speed information at each moment and blade angle information and / or torque at the corresponding moment based on the historical operating condition information; calibrating the wind speed information at each moment based on the blade angle information and / or torque at the corresponding moment, and constructing a training set and a test set based on the calibration structure; performing model training in a pre-constructed network structure based on the training set to obtain an initial model; and verifying the initial model based on the test set, and using the verified model as a wind speed prediction model.

[0010] Optionally, the pre-constructed network structure is constructed based on a long short-term memory neural network; each layer of neurons in the long short-term memory neural network includes sequentially connected forget gates, input gates and output gates, and memory units.

[0011] Optionally, the forget gate, input gate and output gate are respectively expressed as:

[0012] f t =σ(ΣW xf x t +ΣW hf xt-1 +ΣW cf x t-1 +b f )

[0013] i t =σ(∑W xi x t +ΣW hi x t-1 +∑W ci x t-1 +b i )

[0014] o t =σ(ΣW xo x t +∑W ho x t-1 +∑W co x t-1 +b o )

[0015] Among them, f t 、i t , o t are the outputs of the forget gate, input gate, and output gate respectively; σ is the sigmoid activation function; W xf , W xi , W xo are the current input x t The weight matrix between the forget gate, input gate and output gate; x t is the input data of the current time step; W hf , W hi , W ho are the weight matrices between the hidden state of the previous time step and the forget gate, input gate, and output gate; W cf , W ci , W co It is divided into the memory unit state of the previous time step and the weight matrix between the forget gate, input gate and output gate; b f 、b i 、b o They are the bias terms of the forget gate, input gate and output gate respectively.

[0016] Optionally, the memory unit is used to perform memory unit state update at each time step, and the corresponding update rule is:

[0017] c t =f t c t-1 +i t tanh(∑W xc x t +∑W hc x t-c +bt )

[0018] Among them, c t is the memory cell state at the current time step; f t 、i t are the outputs of the forget gate and the input gate respectively; c t-1 is the memory unit state at the previous time step; tanh is the hyperbolic tangent function; W xc , W hc The current input x1 and the previous time step input x are t-1 The weight matrix between the memory cell state and b c is the bias term of the memory unit.

[0019] Optionally, the output gate is used to perform hidden state update at each time step, and the corresponding update rule is:

[0020] h t =o t tanh(c t )

[0021] Among them, h t is the hidden state of the current time step; o t is the output of the output gate; tanh is the hyperbolic tangent function; c t is the memory cell state at the current time step.

[0022] Optionally, performing an average turbulence intensity prediction within a predetermined time period based on the time-series wind speed prediction value includes: taking the time-series wind speed prediction value as an input parameter of a preset mapping function, performing an average turbulence intensity prediction within the corresponding predetermined time period, and obtaining an average turbulence intensity prediction value within the predetermined time period; wherein the mapping function is used to characterize the mapping relationship between the time-series wind speed prediction value and the average turbulence intensity prediction value within the corresponding time period.

[0023] Optionally, the method also includes: executing mapping function construction, including: collecting environmental status information of the target wind turbine within a fixed time length; wherein the environmental status information includes wind speed information, and any one or more of temperature information, air pressure information and humidity information; fitting turbulence information within a corresponding time length based on the environmental status information; fitting the mapping relationship between wind speed information and turbulence information based on the wind speed information within a fixed time length and the turbulence information within a corresponding time length.

[0024] Optionally, the mapping relationship fitting between the wind speed information and the turbulence information based on the wind speed information within a fixed time length and the turbulence information within a corresponding time length includes: calculating the wind speed mean within the corresponding time length based on the wind speed information within the fixed time length, and constructing a turbulence intensity fitting process reference variable based on the wind speed mean, expressed as:

[0025]

[0026] Among them, ReV is the reference variable of the turbulence intensity fitting process; T m is the average difference between the mean wind speed within the corresponding time length and the preset expected wind speed mean; T rated is the preset expected wind speed mean within the time length; β is the fitting process parameter; the mapping relationship between wind speed information and turbulence information is fitted based on the reference variable of the turbulence intensity fitting process, which is expressed as:

[0027] I real =K×ReV+b

[0028] Among them, I real is the turbulence information within the corresponding time length; K and b are fitting process variables.

[0029] Optionally, based on the wind speed numerical interval in which the time-series wind speed prediction value is located and the turbulence intensity numerical interval in which the average turbulence intensity is located, the corresponding wind turbine control scheme is matched and executed, including: if the time-series wind speed prediction value is in the first wind speed numerical interval, and the turbulence intensity is in the first turbulence intensity numerical interval, it is determined to be a first matching relationship, then the wind turbine control scheme matched and executed is a pitch action pre-adjustment scheme; if the time-series wind speed prediction value is in the second wind speed numerical interval, and the turbulence intensity is in the first turbulence intensity numerical interval, it is determined to be a second matching relationship, then the wind turbine control scheme matched and executed is a power limiting adjustment scheme; if the time-series wind speed prediction value is in the second wind speed numerical interval, and the turbulence intensity is in the second turbulence intensity numerical interval, it is determined to be a third matching relationship, then the wind turbine control scheme matched and executed is a power increase adjustment scheme; wherein, the first wind speed numerical interval is smaller than the second wind speed numerical interval, and the first turbulence intensity numerical interval is larger than the second turbulence intensity numerical interval; otherwise, if it does not belong to any of the first matching relationship, the second matching relationship and the third matching relationship, the wind turbine control is not executed.

[0030] The second aspect of the present invention provides a wind turbine control system based on wind farm wind condition prediction, the system comprising: an acquisition unit, used to acquire operating condition information of a target wind turbine; a preprocessing unit, used to preprocess the operating condition information; a wind speed prediction unit, used to use the preprocessed operating condition information as a model input parameter, perform wind speed prediction in real time based on a pre-trained wind speed prediction model, and obtain a time series wind speed prediction value; a turbulence mapping unit, used to perform an average turbulence intensity prediction within a predetermined time period based on the time series wind speed prediction value; a control unit, used to match and execute a corresponding wind turbine control scheme based on the wind speed numerical interval in which the time series wind speed prediction value is located and the turbulence intensity numerical interval in which the average turbulence intensity is located.

[0031] On the other hand, the present invention provides a computer-readable storage medium having instructions stored thereon, which, when executed on a computer, enables the computer to execute the above-mentioned wind turbine control method based on wind farm wind condition prediction.

[0032] Through the above technical scheme, the present invention collects and preprocesses the operating condition information of the target wind turbine to ensure the accuracy and consistency of the input data. Then, the pre-trained wind speed prediction model is used to obtain the time-series wind speed prediction value in real time to ensure that the wind speed prediction can respond to environmental changes in a timely manner. Based on this, the average turbulence intensity within a predetermined time period is further predicted, thereby providing a dual reference basis for wind speed and turbulence. Next, the most suitable wind turbine control scheme is matched according to the numerical range of the time-series wind speed and turbulence intensity. This strategy can not only optimize the power generation efficiency of the wind turbine and ensure precise control under different wind conditions, but also extend the service life of the equipment and avoid the risk of equipment failure caused by extreme weather or wind speed fluctuations. In general, the scheme improves the operating stability and economic benefits of wind turbines through accurate wind speed and turbulence predictions.

[0033] Other features and advantages of the embodiments of the present invention will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0035] Figure 1 It is a flowchart of the steps of a wind turbine control method based on wind farm wind condition prediction provided by an embodiment of the present invention;

[0036] Figure 2 It is an internal module structure diagram of an LSTM network provided by one embodiment of the present invention;

[0037] Figure 3 is a timing diagram of actual wind speed provided by one embodiment of the present invention;

[0038] Figure 4 is a predicted wind speed time series diagram provided by one embodiment of the present invention;

[0039] Figure 5 It is a system structure diagram of a wind turbine control system based on wind farm wind condition prediction provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0040] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0041] Figure 1 FIG. 1 is a flow chart of a method for controlling a wind turbine generator system based on wind farm wind condition prediction provided by an embodiment of the present invention. Figure 1 As shown, an embodiment of the present invention provides a wind turbine control method based on wind farm wind condition prediction, the method comprising:

[0042] Step S10: collecting operating condition information of the target wind turbine generator set and preprocessing the operating condition information.

[0043] Specifically, the operating condition information is real-time blade angle information and / or real-time torque of the wind turbine.

[0044] In the embodiment of the present invention, although the traditional anemometer can provide wind speed data, due to the rapidity and complexity of wind speed changes, its measurement results often have lags and cannot reflect the current wind condition changes in a timely manner, thereby affecting the real-time regulation of the wind turbine. By directly selecting the measurable variables of the unit that are highly correlated with wind speed and turbulence intensity, especially the pitch angle and torque values, the scheme can more quickly obtain operating status information related to wind speed and turbulence. Pitch angle and torque, as key parameters of the operating status of the wind turbine, can indirectly reflect changes in wind speed and turbulence without direct measurement by an anemometer. This prediction method based on the unit's own operating information can significantly reduce the feedback lag of wind speed measurement and improve the real-time and accuracy of wind speed prediction.

[0045] Based on the scheme of the present invention, the scheme of the present invention avoids the delayed feedback problem caused by traditional anemometers and significantly improves the response speed of wind turbines. Through the real-time collection and analysis of pitch angle and torque values, the system can make a more rapid prediction of wind speed and turbulence intensity, and then more accurately adjust the operating state of the wind turbine. This can not only improve the power generation efficiency of wind farms, but also effectively extend the service life of wind turbines and reduce the loss and failure risk of equipment caused by delayed response.

[0046] Furthermore, the operating condition information is preprocessed, including: performing outlier processing, missing value processing and normalization processing on the operating condition information in sequence to obtain an initial data set; performing sliding window processing on the initial data set to obtain operating condition time series data of a preset time length as data after the preprocessing is completed.

[0047] In an embodiment of the present invention, the preprocessing process includes outlier processing, missing value processing and normalization processing of the operating condition information. The main purpose of this step is to eliminate noise data, repair potential errors caused by missing data, and unify the values ​​of different dimensions to the same scale through normalization to facilitate subsequent model processing. Outlier processing can remove extreme data points caused by equipment failure or other accidental factors to ensure the reliability of model input data; missing value processing uses interpolation or filling technology to compensate for discontinuities in the data collection process; normalization processing reduces the adverse effects of data of different magnitudes on model training by mapping the data to a unified range (such as 0 to 1).

[0048] Furthermore, after the preprocessing is completed, the solution further performs sliding window processing on the initial data set. Sliding window technology is a method commonly used in time series data processing, which can ensure that continuous time series data of a fixed time length can be obtained each time. By setting the window length and step size, the sliding window can capture the dynamic change trend of the wind turbine in a specific time period, thereby better reflecting the time series characteristics of wind speed and turbulence. Time series data of a preset time length can provide stable input for subsequent models, thereby improving the accuracy of prediction.

[0049] Specifically, sliding window processing is performed on the initial data set to obtain operating condition time series data of a preset time length, including: determining the window length of the sliding window based on the preset time length, randomly adjusting the sliding window step size, and obtaining a preset number of candidate operating condition time series data in a predetermined historical data length; identifying and comparing data features of each candidate operating condition time series data, and screening out candidate operating condition time series data with the best features based on an optimization matching rule as the obtained operating condition time series data; wherein the data features are smoothness and / or volatility.

[0050] In the embodiment of the present invention, the time series data of the most recent window length is directly used as the collected data. This passive collection method is simple and has low implementation cost, and is suitable for scenarios with high real-time requirements. However, since it is based on the most recent time series data, no further optimization selection is performed, and it may not be possible to ensure that the collected data has the best characteristics, such as the smoothness or volatility of the data may be poor, thereby affecting the training effect of the subsequent model.

[0051] Based on this, the scheme of the present invention can ensure that the collected data better meets the needs of subsequent models by actively selecting time series data with better features. Specifically, the active collection scheme first sets the window length of the sliding window, and allows the step size of the sliding window to be randomly adjusted, so as to generate multiple candidate operating condition time series data in the recent period of time. These candidate time series data cover the operating characteristics of different time periods, and therefore can more comprehensively reflect the historical operating status of the wind turbine. Next, the system identifies and compares the features of these candidate data, mainly examining the smoothness and volatility of the data. These two data features can reflect the stability and consistency of the time series data, and are key indicators for optimizing the accuracy of subsequent model training. Finally, based on the optimization matching rule, the system screens out the candidate time series data with the best features as the final input data for model training.

[0052] Based on the solution of the present invention, through the active collection scheme, the feature-rich data that best meets the model requirements can be screened out from a large number of candidate time series data, thereby greatly improving the accuracy and stability of model training. Compared with passive collection, active collection not only ensures the smoothness and consistency of time series data, but also reduces the noise interference caused by excessive data volatility. This optimization method ensures that the model can obtain high-quality training data, thereby providing more accurate results in wind speed and turbulence intensity predictions, helping wind turbines to achieve more stable operation and more efficient power generation performance. In addition, through random adjustment of the step size of the sliding window and comparison of multiple candidate data features, the generalization ability of the model can also be enhanced, enabling it to better adapt to different wind conditions and complex working conditions.

[0053] Step S20: using the preprocessed operating condition information as a model input parameter, performing wind speed prediction in real time based on the pre-trained wind speed prediction model, and obtaining a time series wind speed prediction value.

[0054] Specifically, before executing the prediction, it is necessary to perform corresponding wind speed prediction model training, collect historical operating condition information of the target wind turbine, and perform wind speed information at each moment and blade angle information and / or torque at the corresponding moment based on the historical operating condition information; calibrate the wind speed information at each moment based on the blade angle information and / or torque at the corresponding moment, and construct a training set and a test set based on the calibration structure; perform model training in a pre-constructed network structure based on the training set to obtain an initial model; verify the initial model based on the test set, and use the verified model as a wind speed prediction model.

[0055] In an embodiment of the present invention, the scheme requires the collection of historical operating condition information of the target wind turbine, which includes the blade angle information and / or torque information of the wind turbine at different times, and these operating condition data reflect the actual operating status of the wind turbine. By associating the historical operating condition information with the wind speed information at the corresponding time, the system can provide accurate input data for the subsequent wind speed prediction model. In particular, the blade angle and torque, these two parameters have a direct correlation with the wind speed, and their changes can reflect the changing trend of the wind speed to a certain extent. After collecting the data, the system will calibrate these data. The calibration process is to correspond the blade angle information and / or torque information at each moment to the wind speed data one by one, and establish a mapping relationship between the two. This process is equivalent to providing a mapping reference between the input and output for the model, so that the model can understand the correlation between the operating parameters of the wind turbine and the wind speed change. After the calibration is completed, the system will construct a training set and a test set based on the calibration structure. The training set is used for model training, providing a large amount of historical data to help the model learn the complex relationship between wind speed and operating conditions; the test set is used for subsequent model verification to ensure that the model not only performs well on the training set, but also has strong generalization capabilities on unknown data.

[0056] Furthermore, the model is trained in the pre-built network structure. By using the training set, the model can gradually optimize its parameters, learn the nonlinear relationship between the blade angle information, torque information and wind speed, and finally obtain an initial wind speed prediction model. Finally, the initial model is verified based on the test set. If the performance of the model on the test set meets the expected standards, that is, the predicted wind speed is highly consistent with the actual wind speed, the model is considered to have passed the verification and is put into use as a formal wind speed prediction model.

[0057] Based on the solution of the present invention, the wind speed prediction model can accurately learn the changing law of wind speed based on the historical operating information of the wind turbine, especially key variables such as blade angle and torque. The calibration process ensures the correlation between data input and output, and the construction of training sets and test sets ensures that the training and verification process of the model is scientific and complete. Through the training and verification of the model, the wind speed prediction model finally obtained not only has high accuracy, but also can maintain good generalization ability when facing different wind conditions. The core advantage of this solution is that it can improve the accuracy of wind speed prediction, help wind turbines make timely and accurate adjustments under complex and changeable wind conditions, thereby improving power generation efficiency and extending equipment life. In addition, the process of model training and verification ensures the reliability and stability of the wind speed prediction model in practical applications, and further optimizes the operation effect of wind turbines.

[0058] Furthermore, the pre-constructed network structure is constructed based on a long short-term memory neural network; each layer of neurons in the long short-term memory neural network includes sequentially connected forget gates, input gates and output gates, as well as memory units.

[0059] In an embodiment of the present invention, the pre-built network structure uses a long short-term memory neural network (LSTM), which is a deep learning model designed specifically for processing long time series data. Traditional recurrent neural networks (RNNs) often encounter problems with gradient vanishing or gradient exploding when processing long sequences, especially in the training process of long time series data, the network cannot effectively retain the information input earlier, resulting in poor model prediction results. In order to solve this problem, the present invention uses an LSTM network, the core advantage of which is that it can handle long-term dependencies well and effectively deal with the problem of gradient vanishing.

[0060] Figure 2 The internal module structure diagram of the LSTM network is shown in the figure. As shown in the figure, the internal structure of the LSTM consists of three important gating units: the forget gate (f t ), input gate (i t ) and output gate (o t ). They retain or forget past information by controlling the input and adjusting the state of the memory unit, ensuring that the model can effectively handle long-range dependency issues in the processing of long sequence data. The specific process is expressed as:

[0061] 1) Forget gate (f t ): Control the memory state h of the previous moment t-1 The cross symbol in the figure represents the element-level multiplication operation. t and h t-1 , indicating that the gating unit retains or forgets part of the past memory information.

[0062] 2) Input gate (i t ): Determine the current input x t And the previous output y t-1 After processing, whether to update to the memory unit. The input gate uses the tanh function to perform nonlinear transformation on the input, and then decides how to update to the memory unit through the gating unit.

[0063] 3) Output gate (o t ): The output gate determines the output at the current time t, combining the current memory state and the data processed by the tanh function to generate the current hidden state h t and output y t .

[0064] Furthermore, the LSTM network adds a unit control mechanism on the basis of RNN to ensure that the error can be transmitted over a longer time step to avoid the gradual loss of information over time. Each LSTM unit contains three key parts: the forget gate, the input gate, and the output gate. These "gates" control the retention, update, and output of information respectively. Specifically, the forget gate determines whether the previous memory should be discarded at the current moment, the input gate is responsible for writing new information into the memory unit, and the output gate controls the output of the current information to the next layer of neurons.

[0065] Furthermore, the memory unit of LSTM can retain important historical information between multiple time steps through these gating mechanisms. Unlike traditional RNN, each layer of neurons in the LSTM network not only processes the input at the current moment, but also effectively saves and propagates the key information in the previous time step, so that the dependencies of long time series can be maintained. This design enables the LSTM model to handle the long-term dependency problem in the wind speed prediction task well, because wind speed data has obvious time series characteristics, and the future operation status of wind turbines depends largely on the trend of historical wind speed changes.

[0066] Based on the scheme of the present invention, by introducing the LSTM neural network, the present invention can effectively solve the gradient vanishing problem of RNN in long sequence training, and ensure that the model has good prediction accuracy when processing long time series. The design of the LSTM network enables the error to be transmitted within a longer time step, ensuring that important information will not be lost in the layer-by-layer propagation of the network. Therefore, the wind speed model can make full use of historical wind speed data to make more accurate predictions. In addition, the gating mechanism in LSTM allows the model to finely control the input information, so that the model can retain valuable long-term information and forget useless information in time, further improving the training efficiency and prediction effect of the model. Through this scheme, wind turbines can achieve more stable and accurate wind speed predictions, thereby optimizing power generation efficiency and equipment operation status.

[0067] Specifically, the forget gate, input gate and output gate are respectively expressed as:

[0068] f t =σ(∑W xf x t +∑W hf x t-1 +∑W cf x t-1 +b f )

[0069] i t =σ(∑W xi x t +∑W hi x t-1+ΣW ci x t-1 +b i )

[0070] o t =σ(∑W xo x t +∑W ho x t-1 +∑W co x t-1 +b o )

[0071] Among them, f t 、i t , o t are the outputs of the forget gate, input gate, and output gate respectively; σ is the sigmoid activation function; W xf , W xi , W xo are the current input x t The weight matrix between the forget gate, input gate and output gate; x t is the input data of the current time step; W hf , W hi , W ho are the weight matrices between the hidden state of the previous time step and the forget gate, input gate, and output gate; W cf , W ci , W co It is divided into the memory unit state of the previous time step and the weight matrix between the forget gate, input gate and output gate; b f 、b i 、b o They are the bias terms of the forget gate, input gate and output gate respectively.

[0072] Specifically, the memory unit is used to execute the memory unit state update at each time step, and the corresponding update rule is:

[0073] c t =f t c t-1 +i t tanh(∑W xc x t +ΣW hc x t-1 +b c )

[0074] Among them, c t is the memory cell state at the current time step; f t 、i t are the outputs of the forget gate and the input gate respectively; c t-1 is the memory unit state at the previous time step; tanh is the hyperbolic tangent function; Wxc , W hc are the current input x t and the previous time step input x t-1 The weight matrix between the memory cell state and b c is the bias term of the memory unit.

[0075] Specifically, the output gate is used to perform hidden state update at each time step, and the corresponding update rule is:

[0076] h t =o t tanh(c t )

[0077] Among them, h t is the hidden state of the current time step; o t is the output of the output gate; tanh is the hyperbolic tangent function; c t is the memory cell state at the current time step.

[0078] Step S30: performing average turbulence intensity prediction within a predetermined time period based on the time series wind speed prediction value.

[0079] Specifically, the time-series wind speed prediction value is used as an input parameter of a preset mapping function, and the average turbulence intensity prediction within the corresponding predetermined time period is performed to obtain the average turbulence intensity prediction value within the predetermined time period; wherein the mapping function is used to characterize the mapping relationship between the time-series wind speed prediction value and the average turbulence intensity prediction value within the corresponding time period.

[0080] In an embodiment of the present invention, the predicted time-series wind speed is used as the input of a preset mapping function, and the mapping relationship between wind speed and turbulence intensity is realized through this function. The function of the mapping function is to convert the wind speed change characteristics over a period of time into a turbulence intensity prediction value, so that the turbulence intensity can be derived based on the wind speed data without directly measuring the turbulence. This method can effectively use wind speed prediction data to generate a more comprehensive environmental condition assessment. The construction of the mapping function is based on the complex physical relationship between wind speed and turbulence intensity. Through the fitting of historical data and the optimization of the model, the mapping function can accurately predict the average turbulence intensity over a period of time under different wind speed fluctuation conditions. The application of this mapping relationship enables the wind turbine to reasonably evaluate the upcoming turbulence intensity based on the current wind speed forecast, thereby making optimized operation adjustments.

[0081] Specifically, the method also includes: executing mapping function construction, including: collecting environmental status information of the target wind turbine within a fixed time length; wherein the environmental status information includes wind speed information, and any one or more of temperature information, air pressure information and humidity information; fitting turbulence information within a corresponding time length based on the environmental status information; fitting the mapping relationship between wind speed information and turbulence information based on the wind speed information within a fixed time length and the turbulence information within a corresponding time length.

[0082] In an embodiment of the present invention, environmental status information of the target wind turbine is collected within a fixed time length. This information includes not only the core wind speed information, but also various factors such as temperature, air pressure, and humidity. By introducing these environmental factors, the actual operating environment of the wind turbine can be more comprehensively reflected, avoiding the problem of inaccurate prediction that may be caused by relying solely on wind speed information. Factors such as temperature, air pressure, and humidity have a significant impact on wind speed and turbulence intensity. By integrating these environmental information, it is helpful to capture the relationship between wind speed and turbulence intensity more accurately.

[0083] Specifically, based on the collected environmental state information, turbulence information fitting within the corresponding time length is performed. This process involves combining wind speed information with other environmental state data to generate turbulence information within a period of time through model fitting. The fitting process can establish a suitable model to predict turbulence intensity based on the analysis of historical data. The fitted turbulence information can provide a more reliable reference for the operation and regulation of wind turbines.

[0084] In a possible implementation, assume that the following information is collected in a wind farm:

[0085] Time period: 600 seconds.

[0086] Wind speed information: During this period, the average wind speed was 7.5m / s and the standard deviation was 2.1m / s.

[0087] Temperature information: During this period, the temperature remained around 15°C with little variation.

[0088] Air pressure information: The air pressure is 1012hPa, with slight fluctuations.

[0089] Humidity information: Humidity is 60%, relatively stable.

[0090] Based on these data, the specific process of fitting the turbulence intensity is as follows:

[0091] 1) Data preprocessing: Standardize the collected wind speed, temperature, air pressure, and humidity information, for example, normalize the wind speed to the range of 0-1 to ensure that the scale of each variable is consistent.

[0092] 2) Model selection: Select a linear regression model as the fitting model, or select a deep learning model such as LSTM for complex time series fitting according to task requirements. Assuming a linear regression model is selected, the model input variables are wind speed, temperature, air pressure, and humidity, and the output is turbulence intensity.

[0093] 3) Model training: Use historical wind speed and environmental status data to train a linear regression model to understand the impact of wind speed and environmental conditions on turbulence intensity.

[0094] 4) Turbulence fitting: The wind speed information (7.5m / s, standard deviation 2.1m / s), temperature information (15℃), air pressure information (1012hPa) and humidity information (60%) collected within 600 seconds are input into the model to fit the turbulence intensity within this time period. For example, the model predicts that the turbulence intensity is 0.25, which means that the turbulence is relatively weak during this period.

[0095] Output result: The fitted turbulence intensity of 0.25 is passed to the control system of the wind turbine. The wind turbine can adjust its operating strategy based on the turbulence prediction value, such as adjusting the blade angle to cope with turbulence changes.

[0096] Furthermore, after obtaining wind speed information and turbulence information, the system further fits the mapping relationship between wind speed information and turbulence information to establish an accurate mapping model between the two. This mapping model can predict the turbulence intensity in real time according to the change of wind speed, forming a relationship between wind speed and turbulence. This process is based on training and optimization of the data collected in the early stage to ensure that the mapping relationship can be accurately applied under different wind conditions. Through wind speed and turbulence data within a fixed time length, the mapping model can effectively learn the complex nonlinear relationship between the two, thereby providing high-precision turbulence prediction.

[0097] Specifically, the mapping relationship fitting between the wind speed information and the turbulence information based on the wind speed information within a fixed time length and the turbulence information within the corresponding time length includes: calculating the wind speed mean within the corresponding time length based on the wind speed information within the fixed time length, and constructing a turbulence intensity fitting process reference variable based on the wind speed mean, which is expressed as:

[0098]

[0099] Among them, ReV is the reference variable of the turbulence intensity fitting process; T m is the average difference between the mean wind speed within the corresponding time length and the preset expected wind speed mean; T rated is the preset expected wind speed mean within the time length; β is the fitting process parameter; the mapping relationship between wind speed information and turbulence information is fitted based on the reference variable of the turbulence intensity fitting process, which is expressed as:

[0100] I real =K×ReV+b

[0101] Among them, I real is the turbulence information within the corresponding time length; K and b are fitting process variables.

[0102] Step S40: matching and executing a corresponding wind turbine control scheme based on the wind speed numerical interval in which the time series wind speed prediction value is located and the turbulence intensity numerical interval in which the average turbulence intensity is located.

[0103] Specifically, if the time-series wind speed prediction value is in the first wind speed numerical interval, and the turbulence intensity is in the first turbulence intensity numerical interval, it is determined to be a first matching relationship, and the wind turbine control scheme matched and executed is a pitch action pre-adjustment scheme; if the time-series wind speed prediction value is in the second wind speed numerical interval, and the turbulence intensity is in the first turbulence intensity numerical interval, it is determined to be a second matching relationship, and the wind turbine control scheme matched and executed is a power limiting adjustment scheme; if the time-series wind speed prediction value is in the second wind speed numerical interval, and the turbulence intensity is in the second turbulence intensity numerical interval, it is determined to be a third matching relationship, and the wind turbine control scheme matched and executed is a power increase adjustment scheme; wherein, the first wind speed numerical interval is smaller than the second wind speed numerical interval, and the first turbulence intensity numerical interval is larger than the second turbulence intensity numerical interval; otherwise, if it does not belong to any of the first matching relationship, the second matching relationship and the third matching relationship, the wind turbine control is not executed.

[0104] In an embodiment of the present invention, the scheme of the present invention dynamically adjusts the control strategy of the wind turbine set through the matching relationship between the wind speed prediction value and the turbulence intensity to cope with the operating status of the wind turbine set under different wind conditions. The scheme is mainly divided into four types of wind conditions, each of which is classified according to the average wind speed and turbulence intensity value, and different control strategies are executed according to different matching situations, such as variable pitch pre-adjustment, power limit adjustment or power increase operation. Specifically including:

[0105] 1) The first matching relationship (rated wind speed and high turbulence wind conditions):

[0106] Conditions: When the average wind speed is between 8-12m / s (the first wind speed numerical range) and the turbulence intensity is between 0.12-0.2 (the first turbulence intensity numerical range).

[0107] Control strategy: It is determined to be a high turbulence wind condition at rated wind speed. At this time, the wind turbine may face large wind speed fluctuations. Therefore, in order to reduce the impact of turbulence on the unit, the controller will execute the pitch action pre-adjustment plan, that is, by adjusting the pitch angle in advance to cope with possible wind speed changes, thereby reducing the impact on the wind turbine and optimizing the operation stability.

[0108] 2) The second matching relationship (high wind speed and high turbulence):

[0109] Conditions: When the average wind speed is between 12-20m / s (the second wind speed numerical range) and the turbulence intensity is between 0.1-0.2 (the first turbulence intensity numerical range).

[0110] Control strategy: It is determined to be a high wind speed and high turbulence wind condition. At this time, the wind turbine is in a high wind speed and strong turbulence environment, and the wind turbine may face a large load pressure. In order to protect the equipment, the controller will execute the power limit adjustment plan, by appropriately increasing the pitch action and limiting the power generation, reducing the load of the equipment, and avoiding equipment loss caused by high wind speed and high turbulence.

[0111] 3) The third matching relationship (high wind speed and low turbulence wind conditions):

[0112] Conditions: When the average wind speed is between 12-20m / s (the second wind speed numerical range) and the turbulence intensity is between 0-0.08 (the second turbulence intensity numerical range).

[0113] Control strategy: It is determined to be a high wind speed and low turbulence wind condition. In this case, although the wind speed is high, the turbulence intensity is low and the environment is relatively stable. The wind turbine can fully utilize the high wind speed to generate electricity. At this time, the controller will execute the power increase adjustment plan, that is, increase the power output and improve the power generation efficiency under the premise of ensuring the safety of the equipment.

[0114] 4) Other wind conditions (does not match any of the conditions):

[0115] Condition: If the current wind speed and turbulence intensity do not satisfy the above three matching relationships, the system will judge it as other wind conditions.

[0116] Control strategy: At this time, the controller will not perform additional operations, maintain the current operating state, avoid unnecessary adjustments, and reduce unnecessary energy consumption and control delays.

[0117] Based on the scheme of the present invention, the scheme of the present invention can flexibly respond to different wind conditions according to different combinations of wind speed and turbulence intensity. Especially under extreme conditions such as high turbulence and high wind speed, the early execution of variable pitch and power limiting control can effectively avoid equipment overload and wind turbine loss, and protect the safe operation of the equipment. At the same time, when the wind conditions are relatively stable and the turbulence is low, the system can increase the power in a timely manner, make full use of wind energy, and improve power generation efficiency. The core of the entire control scheme is to closely combine the operating status of the wind turbine with the changes in environmental parameters such as wind speed and turbulence, so that the wind turbine can achieve intelligent adjustment, maintain efficient operation under complex wind conditions, and significantly improve the life and operation reliability of the equipment. Through this dynamic matching and adjustment scheme, the wind farm can maintain the optimal operating state under different wind conditions and improve the overall energy utilization rate.

[0118] In a possible embodiment, the wind speed is predicted based on the wind turbine control method based on wind farm wind condition prediction proposed in the solution of the present invention, and compared with the measured wind speed. Figure 3 is the measured wind speed time series diagram, Figure 4 This is a time series diagram of predicted wind speed. The horizontal axis represents time in seconds (s), and the vertical axis represents wind speed in meters per second (m / s). The measured wind speed curve shows the fluctuation of wind speed in the actual environment, while the LSTM predicted wind speed curve reflects the model's prediction of future wind speed after neural network training. Figure 3 and Figure 4 The prediction accuracy of the LSTM model is demonstrated, which helps verify its effectiveness in practical applications. As can be seen from the figure, although there is a certain fluctuation in the measured wind speed, the LSTM model can accurately predict the change trend of the wind speed, and the time series change trends of the two are highly consistent. Through comparative analysis, the advantages of the LSTM model in wind condition prediction are further confirmed, especially in dealing with the instability and volatility of wind speed.

[0119] Figure 5 FIG. 1 is a system structure diagram of a wind turbine control system based on wind farm wind condition prediction provided by an embodiment of the present invention. Figure 5 As shown, an embodiment of the present invention provides a wind turbine control system based on wind farm wind condition prediction, the system comprising: a collection unit, used to collect operating condition information of a target wind turbine, and preprocess the operating condition information; a wind speed prediction unit, used to use the preprocessed operating condition information as a model input parameter, and perform wind speed prediction in real time based on a pre-trained wind speed prediction model to obtain a time series wind speed prediction value; a turbulence mapping unit, used to perform an average turbulence intensity prediction within a predetermined time period based on the time series wind speed prediction value; a control unit, used to match and execute a corresponding wind turbine control scheme based on a wind speed numerical interval in which the time series wind speed prediction value is located and a turbulence intensity numerical interval in which the average turbulence intensity is located.

[0120] The embodiment of the present invention further provides a computer-readable storage medium, on which instructions are stored, which, when executed on a computer, enable the computer to execute the above-mentioned wind turbine control method based on wind farm wind condition prediction.

[0121] Those skilled in the art will understand that all or part of the steps in the method for implementing the above-mentioned embodiments can be completed by instructing the relevant hardware through a program, and the program is stored in a storage medium, including several instructions for making a single-chip microcomputer, a chip or a processor (processor) perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program codes.

[0122] The optional embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above embodiments. Within the technical concept of the embodiments of the present invention, the technical scheme of the embodiments of the present invention can be subjected to a variety of simple modifications, and these simple modifications all belong to the protection scope of the embodiments of the present invention. It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0123] In addition, various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed in the embodiments of the present invention.

Claims

1. A wind turbine control method based on wind farm wind condition prediction, characterized in that: The method comprises: Collecting operating condition information of the target wind turbine generator set and preprocessing the operating condition information; The pre-processed operating condition information is used as the model input parameter, and the wind speed prediction is performed in real time based on the pre-trained wind speed prediction model to obtain the time series wind speed prediction value; Performing average turbulence intensity prediction within a predetermined time period based on the time series wind speed prediction value; Based on the wind speed numerical interval in which the time-series wind speed prediction value is located and the turbulence intensity numerical interval in which the average turbulence intensity is located, the corresponding wind turbine control scheme is matched and executed.

2. The method according to claim 1, characterized in that: Preprocessing the operating condition information includes: Performing outlier processing, missing value processing and normalization processing on the operating condition information in sequence to obtain an initial data set; Sliding window processing is performed on the initial data set to obtain operating condition time series data of a preset time length as data after preprocessing.

3. The method according to claim 2, characterized in that Performing sliding window processing on the initial data set to obtain operating condition time series data of a preset time length includes: Determine the window length of the sliding window based on a preset time length, randomly adjust the sliding window step length, and obtain a preset number of candidate operating condition time series data in a predetermined historical data length; Identify and compare the data features of each candidate operating condition time series data, and select the candidate operating condition time series data with the best features based on the optimization matching rule as the obtained operating condition time series data; wherein, Data are characterized by smoothness and / or volatility.

4. The method according to claim 1, characterized in that Pre-training of wind speed prediction model The rules include: Collecting historical operating condition information of the target wind turbine generator set, and performing wind speed information at each moment and blade angle information and / or torque at the corresponding moment based on the historical operating condition information; Calibrate the wind speed information at each moment based on the blade angle information and / or torque at the corresponding moment, and construct a training set and a test set based on the calibration structure; Performing model training in a pre-built network structure based on the training set to obtain an initial model; The initial model is verified based on the test set, and the model that passes the verification is used as the wind speed prediction model.

5. The method according to claim 4, characterized in that The pre-built network structure is built based on a long short-term memory neural network; Each layer of neurons in the long short-term memory neural network includes a forget gate, an input gate, an output gate, and a memory unit that are connected in sequence.

6. The method according to claim 5, characterized in that The forget gate, input gate and output gate are respectively expressed as: f t =σ(∑W xf x t +∑W hf x t-1 +∑W cf x t-1 +b f ) I t =σ(∑W xi x t +∑W hi x t-1 +∑W ci x t-1 +b i ) oh t =σ(ΣW xo x t +ΣW ho x t-1 +ΣW co x t-1 +b o ) Among them, f t 、i t , o t They are the outputs of the forget gate, input gate, and output gate respectively; σ is the sigmoid activation function; W xf , W xi , W xo are the current input x t The weight matrix between the forget gate, input gate and output gate; x t is the input data of the current time step; W hf , W hi , W ho are the hidden state and forget gate, input gate and output gate of the previous time step respectively. The weight matrix between ; W cf , W ci , W co It is divided into the memory cell state of the previous time step and the weight matrix between the forget gate, input gate and output gate; b f 、b i 、b o They are the bias terms of the forget gate, input gate and output gate respectively.

7. The method according to claim 5, characterized in that The memory unit is used to perform the memory unit state update at each time step, and the corresponding update rule is: c t =f t c t-1 +i t tanh(∑W xc x t +∑W hc x t-1 +b c ); Among them, c t is the memory cell state at the current time step; f t 、i t They are the outputs of the forget gate and the input gate respectively; c t-1 is the memory cell state at the previous time step; tanh is the hyperbolic tangent function; W xc , W hc are the current input x t and the previous time step input x t-1 The weight matrix between the memory cell state and b c is the bias term of the memory unit.

8. The method according to claim 5, characterized in that The output gate is used to perform hidden state updates at each time step, and the corresponding update rule is: h t =o t fishy t ); Among them, h t is the hidden state of the current time step; o t is the output of the output gate; tanh is the hyperbolic tangent function; c t is the memory cell state at the current time step.

9. The method according to claim 1, characterized in that: The average turbulence intensity prediction within a predetermined time period is performed based on the time series wind speed prediction value, including: The time series wind speed prediction value is used as the input parameter of the preset mapping function, and the average turbulence intensity prediction within the corresponding predetermined time period is performed to obtain the average turbulence intensity prediction value within the predetermined time period; wherein, The mapping function is used to characterize the mapping relationship between the time series wind speed prediction value and the average turbulence intensity prediction value in the corresponding time period.

10. The method according to claim 9, characterized in that The method further comprises: Execute mapping function construction, including: Collect the environmental status information of the target wind turbine within a fixed time length; The environmental status information includes wind speed information, and any one or more of temperature information, air pressure information, and humidity information; Fitting turbulence information within a corresponding time length based on the environmental state information; The mapping relationship between the wind speed information and the turbulence information is fitted based on the wind speed information within a fixed time length and the turbulence information within a corresponding time length.

11. The method according to claim 10, characterized in that The mapping relationship fitting between the wind speed information and the turbulence information based on the wind speed information within a fixed time length and the turbulence information within a corresponding time length includes: Based on the wind speed information within a fixed time length, the mean wind speed within the corresponding time length is calculated, and based on the wind speed mean, a reference variable of the turbulence intensity fitting process is constructed, which is expressed as: Among them, ReV is the reference variable of the turbulence intensity fitting process; T m is the average difference between the mean wind speed within the corresponding time length and the preset expected wind speed mean; T rated is the preset expected wind speed mean within the time length; β is the fitting process parameter; The mapping relationship between wind speed information and turbulence information is fitted based on the reference variables of the turbulence intensity fitting process, which is expressed as: I real =K×ReV+b; Among them, I real is the turbulence information within the corresponding time length; K and b are fitting process variables.

12. The method according to claim 1, characterized in that Based on the wind speed numerical interval where the time series wind speed prediction value is located and the turbulence intensity numerical interval where the average turbulence intensity is located, the corresponding wind turbine control scheme is matched and executed, including: If the time series wind speed prediction value is within the first wind speed numerical interval, and the turbulence intensity is within the first turbulence intensity numerical interval, it is determined to be a first matching relationship, and the wind turbine control scheme matched and executed is the pitch action pre-adjustment scheme; If the time series wind speed prediction value is within the second wind speed numerical interval, and the turbulence intensity is within the first turbulence intensity numerical interval, it is determined to be a second matching relationship, and the wind turbine control scheme matched and executed is the power limit adjustment scheme; If the time series wind speed prediction value is in the second wind speed numerical interval, and the turbulence intensity is in the second turbulence intensity numerical interval, it is determined to be a third matching relationship, and the wind turbine control scheme matched and executed is the power increase adjustment scheme; wherein, The first wind speed numerical interval is smaller than the second wind speed numerical interval, and the first turbulence intensity numerical interval is larger than the second turbulence intensity numerical interval; On the contrary, if it does not belong to any one of the first matching relationship, the second matching relationship and the third matching relationship, the wind turbine group control is not executed.

13. A wind turbine control system based on wind farm wind condition prediction, characterized in that: The system comprises: A collection unit, used for collecting operating condition information of a target wind turbine; A preprocessing unit, used for preprocessing the operating condition information; A wind speed prediction unit is used to use the pre-processed operating condition information as a model input parameter, perform wind speed prediction based on a pre-trained wind speed prediction model in real time, and obtain a time series wind speed prediction value; A turbulence mapping unit, used to perform average turbulence intensity prediction within a predetermined time period based on the time series wind speed prediction value; The control unit is used to match and execute the corresponding wind turbine control scheme based on the wind speed numerical interval in which the time series wind speed prediction value is located and the turbulence intensity numerical interval in which the average turbulence intensity is located.

Images