A wind turbine generator operation control method, device, equipment and storage medium

Abstract

The application discloses a wind turbine operation control method, device and equipment and a storage medium, relates to the technical field of wind power generation, and comprises the following steps: acquiring historical wind speed data and historical wind direction data of all wind turbines and determining associated wind turbines of a target wind turbine; then generating wind speed prediction models corresponding to different preset wind direction sectors of the target wind turbine; determining the current predicted wind speed of the target wind turbine by using the wind speed prediction model corresponding to the current wind direction data of the target wind turbine and the current wind speed data of the associated wind turbines, and determining the current anemometer operation state based on the measured wind speed of a first anemometer and a second anemometer in the target wind turbine and the current predicted wind speed, and controlling the target wind turbine. In this way, the wind turbine anemometer state can be accurately identified, the corresponding control strategy can be executed, the shutdown caused by anemometer failure can be reduced, and the power generation capacity can be improved.

Description

Technical Field

[0001] This invention relates to the field of wind power generation technology, and in particular to a wind turbine operation control method, device, equipment and storage medium. Background Technology

[0002] Wind turbines operate in complex environments, facing severe weather conditions such as strong winds, sandstorms, and freezing temperatures, as well as extremely complex mechanical and electrical structures, which significantly challenge their normal and stable operation. When dealing with severe weather, the key control and scheduling indicator for wind turbines is wind speed, which influences start-up, shutdown, pitch control, and other control strategies. Wind speed is also a crucial data variable for calculating the power curve K-value and power generation of the wind turbine. In actual operation, anemometer malfunctions directly affect wind turbine operation, leading to missing or unusable data, or even turbine shutdown, resulting in lost power generation and negatively impacting the economic efficiency of wind turbines.

[0003] Currently, to address these issues, wind turbines are often equipped with multiple anemometers to facilitate timely switching to another anemometer in case of failure. This solution is effective for momentary anemometer malfunctions, such as when freezing causes data to remain constant. However, it is less effective for slow-moving anemometer failures, often requiring a considerable time to detect and switch anemometers, while the status of the backup anemometer remains unknown. Therefore, accurately identifying the anemometer status of wind turbines and detecting malfunctions in advance, ensuring that usable wind speed data is available for turbine control input even when anemometers are faulty, is crucial for the normal and stable operation of wind turbines.

[0004] In summary, accurately and timely identifying the status of wind turbine anemometers and obtaining accurate wind speed input to maintain the normal and stable operation of wind turbines is a technical research problem that wind power engineers need to solve. Summary of the Invention

[0005] In view of this, the purpose of this invention is to provide a wind turbine operation control method, device, equipment, and storage medium that can accurately identify the status of the wind turbine's anemometer and execute corresponding control strategies, reducing downtime caused by anemometer malfunctions while increasing power generation. The specific solution is as follows:

[0006] In a first aspect, this application discloses a wind turbine operation control method, including:

[0007] Data on nacelle wind speed and nacelle wind direction of all wind turbine units are collected to obtain corresponding historical wind speed data and historical wind direction data, and the associated wind turbine units are identified as having a correlation between their own historical wind speed data and the historical wind speed data of the target wind turbine unit in each preset wind direction sector.

[0008] Based on the historical wind speed data of the target wind turbine in each of the preset wind direction sectors and the historical wind speed data of the associated wind turbine, different wind speed prediction models for the target wind turbine corresponding to different preset wind direction sectors are generated.

[0009] The current predicted wind speed of the target wind turbine is determined by the wind speed prediction model corresponding to the current wind direction data of the target wind turbine and the current wind speed data of the associated wind turbine, and the measured wind speed of the first anemometer and the measured wind speed of the second anemometer in the target wind turbine are obtained.

[0010] The current operating status of the anemometers is determined based on the measured wind speeds of the first and second anemometers and the current predicted wind speed, and the wind turbines in the target wind turbine unit are controlled using the target wind speed determined based on the current operating status of the anemometers.

[0011] Optionally, the step of collecting data on the nacelle wind speed and nacelle wind direction of all wind turbine units to obtain corresponding historical wind speed data and historical wind direction data includes:

[0012] Data on nacelle wind speed and nacelle wind direction of all wind turbine units are collected within a preset time period, and the collected data is processed to obtain the corresponding historical wind speed data and historical wind direction data; the data processing includes missing value processing, time axis alignment processing, and invalid data removal processing.

[0013] Optionally, the associated wind turbines that determine a correlation between their own historical wind speed data and the historical wind speed data of the target wind turbine in each preset wind direction sector include:

[0014] The wind direction is divided into a preset number of wind direction sectors according to a preset division rule, and the historical wind direction data of the target wind turbine is divided into each wind direction sector;

[0015] Obtain the first historical wind speed data corresponding to the historical wind direction data of the target wind turbine in each wind direction sector, and obtain the second historical wind speed data corresponding to other wind turbines at the same time.

[0016] Based on the first historical wind speed data and the second historical wind speed data, the associated wind turbines corresponding to the target wind turbines in each wind direction sector are determined.

[0017] Optionally, determining the associated wind turbines corresponding to the target wind turbine in each of the wind direction sectors based on the first historical wind speed data and the second historical wind speed data includes:

[0018] Determine the similarity value between the first historical wind speed data and the second historical wind speed data;

[0019] The wind turbines with similarity values ​​greater than a first preset similarity threshold among the other wind turbines are identified as associated wind turbines of the target wind turbine, so as to obtain the associated wind turbines of the target wind turbine in each wind direction sector.

[0020] Optionally, determining the current anemometer operating status based on the measured wind speeds of the first and second anemometers and the current predicted wind speed includes:

[0021] The first similarity between the wind speed measured by the first anemometer and the wind speed measured by the second anemometer, the second similarity between the wind speed measured by the first anemometer and the current predicted wind speed, and the third similarity between the wind speed measured by the second anemometer and the current predicted wind speed are determined respectively.

[0022] The current operating status of the anemometer is determined based on the first similarity, the second similarity, and the third similarity.

[0023] Optionally, determining the current anemometer operating status based on the first similarity, the second similarity, and the third similarity includes:

[0024] If both the first similarity and the second similarity are greater than the second preset similarity threshold, then it is determined that both the first anemometer and the second anemometer are in normal operating condition.

[0025] If the first similarity is greater than the second preset similarity threshold, and the second similarity is not greater than the second preset similarity threshold, then it is determined that both the first anemometer and the second anemometer are in a fault state.

[0026] If the first similarity and the second similarity are both not greater than the second preset similarity threshold, and the third similarity is greater than the second preset similarity threshold, then it is determined that the first anemometer is in a fault state and the second anemometer is in a normal operating state.

[0027] If both the first similarity and the third similarity are not greater than the second preset similarity threshold, and the second similarity is greater than the second preset similarity threshold, then the first anemometer is determined to be in normal operating condition and the second anemometer is in fault condition.

[0028] Optionally, controlling the wind turbines in the target wind turbine unit using the target wind speed determined based on the current anemometer's operating state includes:

[0029] If both the first anemometer and the second anemometer are in normal operation, then either the wind speed measured by the first anemometer or the wind speed measured by the second anemometer is selected to control the wind turbine in the target wind turbine unit.

[0030] If the first anemometer is faulty and the second anemometer is operating normally, the wind speed measured by the second anemometer is selected to control the wind turbine in the target wind turbine unit.

[0031] If the second anemometer is in a faulty state and the first anemometer is in a normal operating state, then the wind speed measured by the first anemometer is selected to control the wind turbine in the target wind turbine unit.

[0032] If both the first and second anemometers are faulty, the wind turbines in the target wind turbine unit will be controlled using the current predicted wind speed.

[0033] Secondly, this application discloses a wind turbine operation control device, comprising:

[0034] The associated wind turbine unit determination module is used to collect data on the nacelle wind speed and nacelle wind direction of all wind turbine units to obtain the corresponding historical wind speed data and historical wind direction data, and to determine the associated wind turbine units that are associated with the historical wind speed data of their own units and the historical wind speed data of the target wind turbine unit in each preset wind direction sector.

[0035] The model generation module is used to generate different wind speed prediction models for the target wind turbine corresponding to different preset wind direction sectors based on the historical wind speed data of the target wind turbine in each preset wind direction sector and the historical wind speed data of the associated wind turbine.

[0036] The predicted wind speed generation module is used to determine the current predicted wind speed of the target wind turbine using the wind speed prediction model corresponding to the current wind direction data of the target wind turbine and the current wind speed data of the associated wind turbine, and to obtain the measured wind speed of the first anemometer and the measured wind speed of the second anemometer in the target wind turbine.

[0037] The wind turbine control module is used to determine the current operating status of the anemometers based on the measured wind speeds of the first and second anemometers and the current predicted wind speed, and to control the wind turbines in the target wind turbine unit using the target wind speed determined based on the current operating status of the anemometers.

[0038] Thirdly, this application discloses an electronic device, comprising:

[0039] Memory, used to store computer programs;

[0040] A processor is used to execute the computer program to implement the aforementioned wind turbine operation control method.

[0041] Fourthly, this application discloses a computer-readable storage medium for storing a computer program, which, when executed by a processor, implements the aforementioned wind turbine operation control method.

[0042] As can be seen, in this invention, firstly, data on the nacelle wind speed and nacelle wind direction of all wind turbine units are collected to obtain corresponding historical wind speed data and historical wind direction data, and associated wind turbine units are identified where their own historical wind speed data is correlated with the historical wind speed data of the target wind turbine unit in each preset wind direction sector; based on the historical wind speed data of the target wind turbine unit in each preset wind direction sector and the historical wind speed data of the associated wind turbine units, different wind speed prediction models for the target wind turbine unit corresponding to different preset wind direction sectors are generated; using the wind speed prediction model corresponding to the current wind direction data of the target wind turbine unit and the current wind speed data of the associated wind turbine units, the current predicted wind speed of the target wind turbine unit is determined, and the measured wind speed of the first anemometer and the measured wind speed of the second anemometer in the target wind turbine unit are obtained; based on the measured wind speed of the first anemometer and the second anemometer and the current predicted wind speed, the current anemometer operating state is determined, and the wind turbine in the target wind turbine unit is controlled using the target wind speed determined based on the current anemometer operating state. As can be seen, by establishing a wind speed prediction model for the target wind turbine in each preset wind direction sector, and then determining the wind speed that the anemometer in the target wind turbine should measure at the current moment based on the wind speed prediction model, the current predicted wind speed is obtained. Based on the actual wind speed measured by the first and second anemometers, and the current predicted wind speed, the operating status of the first and second anemometers is determined. This allows for the selection of the corresponding target wind speed to control the wind turbine in the target wind turbine based on the operating status of the anemometers. In this way, based on the current predicted wind speed and the actual wind speed measured by the first and second anemometers, the operating status of the anemometers in the target wind turbine can be accurately identified. Then, based on the operating status of the anemometers, the corresponding target wind speed can be selected to control the operation of the wind turbine in the target wind turbine. This ensures that the wind turbine can operate normally and stably even when anemometers malfunction, reducing downtime caused by anemometer failure and increasing the power generation of the wind farm. Attached Figure Description

[0043] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0044] Figure 1 This is a flowchart of a wind turbine operation control method disclosed in this application;

[0045] Figure 2 This application discloses a specific flowchart of a wind turbine operation control method.

[0046] Figure 3 This is a schematic diagram of the structure of a wind turbine operation control device disclosed in this application;

[0047] Figure 4 This is a structural diagram of an electronic device disclosed in this application. Detailed Implementation

[0048] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0049] Currently, to address downtime caused by anemometer malfunctions, wind turbines are often equipped with multiple anemometers to facilitate timely switching to another anemometer in case of failure. However, this method still has limitations when anemometers fail slowly or simultaneously. This invention will specifically introduce a method that, by identifying the correlation patterns in wind speed distribution across different sectors and predicting the wind speed of the target wind turbine's anemometers, determines the current state of the wind turbine's anemometers and selects appropriate control strategies. This approach can reduce downtime due to anemometer malfunctions and increase wind farm power generation in various scenarios.

[0050] See Figure 1 As shown in the figure, this application discloses a wind turbine operation control method, including:

[0051] Step S11: Collect data on the nacelle wind speed and nacelle wind direction of all wind turbine units to obtain the corresponding historical wind speed data and historical wind direction data, and determine the associated wind turbine units whose historical wind speed data is correlated with the historical wind speed data of the target wind turbine unit in each preset wind direction sector.

[0052] In this embodiment, the data collection of nacelle wind speed and nacelle wind direction for all wind turbine units to obtain corresponding historical wind speed and historical wind direction data includes: collecting data on the nacelle wind speed and nacelle wind direction of all wind turbine units within a preset time period, and performing data standardization processing on the collected data to obtain corresponding historical wind speed and historical wind direction data; the data standardization processing includes missing value handling, time axis alignment processing, and invalid data removal processing. The nacelle wind speed and nacelle wind direction are data measured by anemometers installed in the wind turbine units. Since wind turbine units generally have more than one anemometer installed, during normal operation, the wind speed data measured by one anemometer is selected to control the wind turbines. Therefore, data collection of nacelle wind speed and nacelle wind direction for all wind turbine units in the wind farm is performed, with the nacelle wind speed being the nacelle wind speed used to control the wind turbines. Due to potential malfunctions in wind turbines or improper data acquisition methods, the collected data may contain invalid data, affecting subsequent model training. Therefore, data standardization processing is necessary to obtain the corresponding historical wind speed and direction data. This data standardization process includes missing value handling, timeline alignment, and invalid data removal. Then, associated wind turbines are identified that have a correlation with the historical wind speed data of the target wind turbine within each preset wind direction sector. Specifically, the wind direction sectors are first divided according to actual conditions. A full sector is 360°, which can be divided into 4, 8, 12, or 16 wind direction sectors depending on the actual situation. One sector is selected as the preset wind direction sector, and then the historical wind speed dataset of the target wind turbine within that preset wind direction sector is obtained, along with the historical wind speed datasets of other wind turbines simultaneously acquired. Then, the similarity δ between the historical wind speed dataset of the target wind turbine in the preset wind direction sector and the historical wind speed datasets of other wind turbines is calculated. The closer the similarity δ is to 1, the stronger the correlation between the two wind turbines. The calculation methods for determining the similarity include, but are not limited to, Pearson correlation coefficient, cosine distance, Euclidean distance, Mahalanobis distance, etc. When the similarity is greater than a first preset similarity threshold, the wind turbine can be identified as an associated wind turbine. This process sequentially identifies associated wind turbines whose historical wind speed data is correlated with the historical wind speed data of the target wind turbine in each preset wind direction sector. The similarity threshold can be set based on experience and actual conditions, but it needs to be higher than 0.9. It is important to emphasize that, to ensure the effectiveness of subsequent model training and prediction accuracy, the number of identified associated wind turbines should not be less than three.In this way, by standardizing the collected data on nacelle wind speed and direction of all wind turbine units, the accuracy of identifying associated wind turbine units can be improved, thereby increasing the accuracy of the subsequently generated wind speed prediction model.

[0053] Step S12: Based on the historical wind speed data of the target wind turbine in each of the preset wind direction sectors and the historical wind speed data of the associated wind turbine, generate different wind speed prediction models for the target wind turbine corresponding to different preset wind direction sectors.

[0054] In this embodiment, based on the historical wind speed data of the target wind turbine in each of the preset wind direction sectors and the historical wind speed data of the associated wind turbines, different wind speed prediction models for the target wind turbine corresponding to different preset wind direction sectors are generated. After determining the associated wind turbines of the target wind turbine in each of the preset wind direction sectors, the wind speed distribution variation law of the historical wind speed data of the target wind turbine in each of the preset wind direction sectors and the historical wind speed data of the associated wind turbines can be learned by a convolutional neural network. During training, the convolutional neural network includes an input layer, a convolutional layer, an activation function layer, a pooling layer, a fully connected layer, and an output layer, and the ReLU (Rectified Linear Unit) linear activation function is selected. Then, the performance of the model is evaluated by a loss function, and the model parameters are updated by an optimization algorithm. During optimization, the loss function can be selected as mean squared error or mean absolute error, and the optimization algorithm can be selected as stochastic gradient descent. This generates different wind speed prediction models for the target wind turbine corresponding to different preset wind direction sectors.

[0055] Step S13: Determine the current predicted wind speed of the target wind turbine using the wind speed prediction model corresponding to the current wind direction data of the target wind turbine and the current wind speed data of the associated wind turbine, and obtain the measured wind speed of the first anemometer and the measured wind speed of the second anemometer in the target wind turbine.

[0056] In this embodiment, after obtaining different wind speed prediction models corresponding to different preset wind direction sectors for the target wind turbine, the real-time wind speed of the target wind turbine can be predicted according to the wind speed prediction model to obtain the current predicted wind speed of the target wind turbine. The current wind direction data measured by the target wind turbine at the current moment is obtained, and then the corresponding wind speed prediction model is selected based on the wind direction data. Simultaneously, the current wind speed data of associated wind turbines within the wind direction sector corresponding to the current wind direction data of the target wind turbine is obtained. After inputting the current wind speed data of the associated wind turbines into the wind speed prediction model, the current predicted wind speed of the target wind turbine is obtained. The measured wind speeds of the first and second anemometers in the target wind turbine are also obtained. The measured wind speeds of the first and second anemometers are both wind speeds actually measured using the first and second anemometers.

[0057] Step S14: Determine the current operating status of the anemometer based on the measured wind speeds of the first and second anemometers and the current predicted wind speed, and control the wind turbines in the target wind turbine unit using the target wind speed determined based on the current operating status of the anemometer.

[0058] In this embodiment, determining the current anemometer operating state based on the measured wind speeds of the first and second anemometers and the current predicted wind speed includes: determining a first similarity between the measured wind speeds of the first and second anemometers, a second similarity between the measured wind speeds of the first and second anemometers, and a third similarity between the measured wind speeds of the second anemometer and the current predicted wind speed. The Pearson correlation coefficient can be used to determine the similarity between the wind speeds. The current anemometer operating state is then determined based on the first, second, and third similarities. The step of determining the current anemometer operating status based on the first similarity, the second similarity, and the third similarity includes: if both the first similarity and the second similarity are greater than a second preset similarity threshold, then both the first and second anemometers are determined to be in normal operating condition; if the first similarity is greater than the second preset similarity threshold and the second similarity is not greater than the second preset similarity threshold, then both the first and second anemometers are determined to be in fault condition; if both the first and second similarities are not greater than the second preset similarity threshold and the third similarity is greater than the second preset similarity threshold, then the first anemometer is determined to be in fault condition and the second anemometer is in normal operating condition; if both the first and third similarities are not greater than the second preset similarity threshold and the second similarity is greater than the second preset similarity threshold, then the first anemometer is determined to be in normal operating condition and the second anemometer is in fault condition. It should be noted that the second preset similarity threshold can be generated using the following formula:

[0059] ε=θ×ε'

[0060] Where ε' is the maximum similarity between the target anemometer fault dataset and the predicted wind speed, and θ is an empirical coefficient.

[0061] If any one of the first similarity, the second similarity, and the third similarity is less than the second preset similarity threshold, a corresponding alarm operation will be triggered to remind technicians to take appropriate action on the anemometer in a timely manner.

[0062] In this embodiment, controlling the wind turbines in the target wind turbine group using the target wind speed determined based on the current operating status of the anemometer includes: if both the first anemometer and the second anemometer are in normal operating condition, then either the measured wind speed of the first anemometer or the measured wind speed of the second anemometer is selected to control the wind turbines in the target wind turbine group; if the first anemometer is in a fault state and the second anemometer is in normal operating condition, then the measured wind speed of the second anemometer is selected to control the wind turbines in the target wind turbine group; if the second anemometer is in a fault state and the first anemometer is in normal operating condition, then the measured wind speed of the first anemometer is selected to control the wind turbines in the target wind turbine group; if both the first anemometer and the second anemometer are in a fault state, then the currently predicted wind speed is selected to control the wind turbines in the target wind turbine group. If both the first and second anemometers are operating normally, the target wind turbine can select either anemometer's wind speed control turbine for power generation. If the first anemometer is operating normally but the second anemometer malfunctions, the target wind turbine will select the wind speed control turbine's wind speed from the first anemometer and trigger an alarm to alert technicians to perform necessary maintenance on the second anemometer. If the second anemometer is operating normally but the first anemometer malfunctions, the target wind turbine will select the wind speed control turbine's wind speed from the second anemometer and trigger an alarm to alert technicians to perform necessary maintenance on the first anemometer. If both the first and second anemometers are malfunctioning, the target wind turbine will temporarily select the turbine controlled by the currently predicted wind speed to maintain its normal operation, triggering an alarm to alert technicians to perform necessary maintenance on both anemometers. This reduces downtime caused by anemometer malfunctions and can improve the wind turbine's power generation to some extent.

[0063] As can be seen, in this embodiment, firstly, data on the nacelle wind speed and nacelle wind direction of all wind turbine units are collected to obtain corresponding historical wind speed data and historical wind direction data, and associated wind turbine units are identified where their own historical wind speed data is correlated with the historical wind speed data of the target wind turbine unit in each preset wind direction sector; based on the historical wind speed data of the target wind turbine unit in each preset wind direction sector and the historical wind speed data of the associated wind turbine units, different wind speed prediction models for the target wind turbine unit corresponding to different preset wind direction sectors are generated; using the wind speed prediction model corresponding to the current wind direction data of the target wind turbine unit and the current wind speed data of the associated wind turbine units, the current predicted wind speed of the target wind turbine unit is determined, and the measured wind speed of the first anemometer and the measured wind speed of the second anemometer in the target wind turbine unit are obtained; based on the measured wind speed of the first anemometer and the second anemometer and the current predicted wind speed, the current anemometer operating state is determined, and the wind turbine in the target wind turbine unit is controlled using the target wind speed determined based on the current anemometer operating state. As can be seen, by establishing a wind speed prediction model for the target wind turbine in each preset wind direction sector, and then determining the wind speed that the anemometer in the target wind turbine should measure at the current moment based on the wind speed prediction model, the current predicted wind speed is obtained. Based on the actual wind speed measured by the first and second anemometers, and the current predicted wind speed, the operating status of the first and second anemometers is determined. This allows for the selection of the corresponding target wind speed to control the wind turbine in the target wind turbine based on the operating status of the anemometers. In this way, based on the current predicted wind speed and the actual wind speed measured by the first and second anemometers, the operating status of the anemometers in the target wind turbine can be accurately identified. Then, based on the operating status of the anemometers, the corresponding target wind speed can be selected to control the operation of the wind turbine in the target wind turbine. This ensures that the wind turbine can operate normally and stably even when anemometers malfunction, reducing downtime caused by anemometer failure and increasing the power generation of the wind farm.

[0064] The above embodiments specifically introduced a method for determining the current operating status of an anemometer based on the correlation law of wind speed distribution. This embodiment will specifically introduce a method for determining the associated wind turbines of the target wind turbine.

[0065] See Figure 2 As shown in the figure, this application discloses a specific method for confirming associated units, including:

[0066] Step S21: Divide the wind direction into a preset number of wind direction sectors according to the preset division rules, and divide the historical wind direction data of the target wind turbine into each wind direction sector.

[0067] In this embodiment, the wind direction is first divided into a preset number of wind direction sectors, centered on the target wind turbine, according to a preset division rule. Each sector is 360°, and the number of wind direction sectors can be 4, 8, 12, or 16. After dividing the wind direction sectors, the historical direction data of the target wind turbine is assigned to each of the respective wind direction sectors based on the wind direction.

[0068] Step S22: Obtain the first historical wind speed data corresponding to the historical wind direction data of the target wind turbine in each wind direction sector, and simultaneously obtain the second historical wind speed data corresponding to other wind turbines.

[0069] In this embodiment, after dividing the historical direction data of the target wind turbine into various wind direction sectors according to the wind direction, the first historical wind speed data corresponding to the historical direction data of the target wind turbine in each wind direction sector is obtained, and the second historical wind speed data corresponding to other wind turbines at the same time is obtained. For example, if there are five first historical wind speed data corresponding to the historical direction data of the target wind turbine in a certain wind direction sector, the time of these five historical wind speed data is determined, and then the historical wind speed data of other wind turbines at the same time are obtained.

[0070] Step S23: Determine the similarity value between the first historical wind speed data and the second historical wind speed data.

[0071] In this embodiment, the similarity value between the first historical wind speed data and the second historical wind speed data can be calculated using the Pearson correlation coefficient:

[0072] Assume the first historical wind speed data of the target wind turbine R1 is [x1, x2, ..., x n The second historical wind speed data for other wind turbine R2 units is [y1, y2, ..., y]. n If the similarity δ between the two is:

[0073]

[0074] in, Let Y represent the average of the first historical wind speed data, and Y represent the average of the second historical wind speed data. In addition, similarity can also be calculated using methods such as cosine distance, Euclidean distance, and Mahalanobis distance.

[0075] Step S24: Determine the wind turbines with similarity values ​​greater than the first preset similarity threshold among the other wind turbines as associated wind turbines of the target wind turbine, so as to obtain the associated wind turbines of the target wind turbine in each wind direction sector.

[0076] In this embodiment, after obtaining the similarity value, the similarity value is compared with the first preset similarity threshold. Wind turbines whose similarity threshold is greater than the first preset similarity threshold are identified as associated wind turbines of the target wind turbine, thus obtaining the associated wind turbines of the target wind turbine in each wind direction sector. It is important to emphasize that the first preset similarity threshold can be set based on experience and actual conditions, and the number of associated wind turbines should not be less than three. This way, the more associated turbines there are, the higher the prediction accuracy of the wind speed prediction model generated using the historical wind speed data of the associated turbines will be.

[0077] As can be seen, in this embodiment, the wind direction is first divided into a preset number of wind direction sectors according to a preset division rule, and the historical wind direction data of the target wind turbine is divided into each wind direction sector; the first historical wind speed data corresponding to the historical wind direction data of the target wind turbine in each wind direction sector is obtained, and the second historical wind speed data corresponding to other wind turbines at the same time is obtained; the similarity value between the first historical wind speed data and the second historical wind speed data is determined; the wind turbines among the other wind turbines whose similarity value is greater than a first preset similarity threshold are determined as the associated wind turbines of the target wind turbine, so as to obtain the associated wind turbines of the target wind turbine in each wind direction sector. That is, by using the first historical wind speed data and the second historical wind speed data, the associated wind turbines of the target wind turbine with strong correlation in wind speed distribution patterns under different wind direction sectors are determined. In this way, the wind speed of the target wind turbine can be predicted and judged based on the wind speed of the associated wind turbines.

[0078] refer to Figure 3 The present application also discloses a wind turbine operation control device, comprising:

[0079] The associated wind turbine unit determination module 11 is used to collect data on the nacelle wind speed and nacelle wind direction of all wind turbine units to obtain the corresponding historical wind speed data and historical wind direction data, and to determine the associated wind turbine units that are associated with the historical wind speed data of their own units and the historical wind speed data of the target wind turbine units in each preset wind direction sector.

[0080] Model generation module 12 is used to generate different wind speed prediction models for the target wind turbine corresponding to different preset wind direction sectors based on the historical wind speed data of the target wind turbine in each preset wind direction sector and the historical wind speed data of the associated wind turbine.

[0081] The predicted wind speed generation module 13 is used to determine the current predicted wind speed of the target wind turbine using the wind speed prediction model corresponding to the current wind direction data of the target wind turbine and the current wind speed data of the associated wind turbine, and to obtain the measured wind speed of the first anemometer and the measured wind speed of the second anemometer in the target wind turbine.

[0082] The wind turbine control module 14 is used to determine the current operating status of the anemometer based on the measured wind speed of the first anemometer and the second anemometer and the current predicted wind speed, and to control the wind turbine in the target wind turbine unit using the target wind speed determined based on the current operating status of the anemometer.

[0083] As can be seen, in this embodiment, firstly, data on the nacelle wind speed and nacelle wind direction of all wind turbine units are collected to obtain corresponding historical wind speed data and historical wind direction data, and associated wind turbine units are identified where their own historical wind speed data is correlated with the historical wind speed data of the target wind turbine unit in each preset wind direction sector; based on the historical wind speed data of the target wind turbine unit in each preset wind direction sector and the historical wind speed data of the associated wind turbine units, different wind speed prediction models for the target wind turbine unit corresponding to different preset wind direction sectors are generated; using the wind speed prediction model corresponding to the current wind direction data of the target wind turbine unit and the current wind speed data of the associated wind turbine units, the current predicted wind speed of the target wind turbine unit is determined, and the measured wind speed of the first anemometer and the measured wind speed of the second anemometer in the target wind turbine unit are obtained; based on the measured wind speed of the first anemometer and the second anemometer and the current predicted wind speed, the current anemometer operating state is determined, and the wind turbine in the target wind turbine unit is controlled using the target wind speed determined based on the current anemometer operating state. As can be seen, by establishing a wind speed prediction model for the target wind turbine in each preset wind direction sector, and then determining the wind speed that the anemometer in the target wind turbine should measure at the current moment based on the wind speed prediction model, the current predicted wind speed is obtained. Based on the actual wind speed measured by the first and second anemometers, and the current predicted wind speed, the operating status of the first and second anemometers is determined. This allows for the selection of the corresponding target wind speed to control the wind turbine in the target wind turbine based on the operating status of the anemometers. In this way, based on the current predicted wind speed and the actual wind speed measured by the first and second anemometers, the operating status of the anemometers in the target wind turbine can be accurately identified. Then, based on the operating status of the anemometers, the corresponding target wind speed can be selected to control the operation of the wind turbine in the target wind turbine. This ensures that the wind turbine can operate normally and stably even when anemometers malfunction, reducing downtime caused by anemometer failure and increasing the power generation of the wind farm.

[0084] In some specific embodiments, the associated unit determination module 11 may specifically include:

[0085] The data acquisition unit is used to collect data on the nacelle wind speed and nacelle wind direction of all wind turbine units within a preset time period, and to perform data standardization processing on the collected data to obtain the corresponding historical wind speed data and historical wind direction data; the data standardization processing includes missing value processing, time axis alignment processing, and invalid data removal processing.

[0086] In some specific embodiments, the associated unit determination module 11 may specifically include:

[0087] The wind direction sector division unit is used to divide the wind direction into a preset number of wind direction sectors according to a preset division rule, and to divide the historical wind direction data of the target wind turbine into each wind direction sector;

[0088] The wind speed acquisition unit is used to acquire the first historical wind speed data corresponding to the historical wind direction data of the target wind turbine in each wind direction sector, and to acquire the second historical wind speed data corresponding to other wind turbines at the same time.

[0089] The associated wind turbine unit determination submodule is used to determine the associated wind turbine units corresponding to the target wind turbine unit in each wind direction sector based on the first historical wind speed data and the second historical wind speed data.

[0090] In some specific embodiments, the associated unit determination submodule 11 may specifically include:

[0091] The first similarity determination unit is used to determine the similarity value between the first historical wind speed data and the second historical wind speed data;

[0092] The associated wind turbine unit is used to identify wind turbines with similarity values ​​greater than a first preset similarity threshold among the other wind turbines as associated wind turbines of the target wind turbine, so as to obtain the associated wind turbines of the target wind turbine in each wind direction sector.

[0093] In some specific embodiments, the wind turbine control module 14 may specifically include:

[0094] The similarity determination unit is used to determine the first similarity between the measured wind speed of the first anemometer and the measured wind speed of the second anemometer, the second similarity between the measured wind speed of the first anemometer and the current predicted wind speed, and the third similarity between the measured wind speed of the second anemometer and the current predicted wind speed.

[0095] The anemometer status confirmation submodule is used to determine the current operating status of the anemometer based on the first similarity, the second similarity, and the third similarity.

[0096] In some specific embodiments, the anemometer status confirmation submodule may specifically include:

[0097] The first state confirmation unit is used to determine that the first anemometer and the second anemometer are both in normal operating condition if both the first similarity and the second similarity are greater than the second preset similarity threshold.

[0098] The second state confirmation unit is used to determine that both the first anemometer and the second anemometer are in a fault state if the first similarity is greater than the second preset similarity threshold and the second similarity is not greater than the second preset similarity threshold.

[0099] The third state confirmation unit is used to determine that the first anemometer is in a fault state and the second anemometer is in a normal operating state if the first similarity and the second similarity are both not greater than the second preset similarity threshold and the third similarity is greater than the second preset similarity threshold.

[0100] The fourth state confirmation unit is used to determine that the first anemometer is in normal operation and the second anemometer is in fault state if the first similarity and the third similarity are both not greater than the second preset similarity threshold and the second similarity is greater than the second preset similarity threshold.

[0101] In some specific embodiments, the wind turbine control module 14 may specifically include:

[0102] The first control unit is configured to, if both the first anemometer and the second anemometer are in normal operating condition, select either the wind speed measured by the first anemometer or the wind speed measured by the second anemometer to control the wind turbine in the target wind turbine unit.

[0103] The second control unit is used to control the wind turbine in the target wind turbine group by selecting the wind speed measured by the second anemometer if the first anemometer is in a fault state and the second anemometer is in a normal operating state.

[0104] The third control unit is used to control the wind turbine in the target wind turbine group by selecting the measured wind speed of the first anemometer if the second anemometer is in a fault state and the first anemometer is in a normal operating state.

[0105] The fourth control unit is used to select the current predicted wind speed to control the wind turbine in the target wind turbine group if both the first anemometer and the second anemometer are in a fault state.

[0106] Furthermore, embodiments of this application also disclose an electronic device, Figure 4 This is a structural diagram of an electronic device 20 according to an exemplary embodiment. The content of the diagram should not be construed as limiting the scope of this application.

[0107] Figure 4 This is a schematic diagram of the structure of an electronic device 20 provided in an embodiment of this application. Specifically, the electronic device 20 may include: at least one processor 21, at least one memory 22, a power supply 23, a communication interface 24, an input / output interface 25, and a communication bus 26. The memory 22 stores a computer program, which is loaded and executed by the processor 21 to implement the relevant steps in the wind turbine operation control method disclosed in any of the foregoing embodiments. Alternatively, the electronic device 20 in this embodiment may specifically be an electronic computer.

[0108] In this embodiment, the power supply 23 is used to provide operating voltage for each hardware device on the electronic device 20; the communication interface 24 can create a data transmission channel between the electronic device 20 and external devices, and the communication protocol it follows can be any communication protocol applicable to the technical solution of this application, and is not specifically limited here; the input / output interface 25 is used to acquire external input data or output data to the outside world, and its specific interface type can be selected according to specific application needs, and is not specifically limited here.

[0109] In addition, the memory 22, as a carrier for resource storage, can be a read-only memory, random access memory, disk or optical disk, etc. The resources stored thereon can include operating system 221, computer program 222, etc., and the storage method can be temporary storage or permanent storage.

[0110] The operating system 221 is used to manage and control the various hardware devices on the electronic device 20 and the computer program 222, which may be Windows Server, Netware, Unix, Linux, etc. In addition to including a computer program capable of performing the wind turbine operation control method executed by the electronic device 20 as disclosed in any of the foregoing embodiments, the computer program 222 may further include computer programs capable of performing other specific tasks.

[0111] Furthermore, this application also discloses a computer-readable storage medium for storing a computer program; wherein, when the computer program is executed by a processor, it implements the aforementioned wind turbine operation control method. Specific steps of this method can be found in the corresponding content disclosed in the foregoing embodiments, and will not be repeated here.

[0112] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatus disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple; relevant parts can be referred to in the method section.

[0113] Those skilled in the art will further recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0114] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein can be implemented directly by hardware, a software module executed by a processor, or a combination of both. The software module can be located in random access memory (RAM), main memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, removable disk, CD-ROM, or any other form of storage medium known in the art.

[0115] Finally, it should be noted that in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0116] The technical solutions provided in this application have been described in detail above. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A wind turbine operation control method, characterized in that, include: Data is collected on the nacelle wind speed and nacelle wind direction of all wind turbine units to obtain corresponding historical wind speed and historical wind direction data. A correlated wind turbine unit is identified where its own historical wind speed data is correlated with the historical wind speed data of the target wind turbine unit within each preset wind direction sector. This correlation includes: dividing the wind direction into a preset number of wind direction sectors centered on the target wind turbine unit according to a preset division rule, and... The historical wind direction data of the target wind turbine is divided into wind direction sectors; first historical wind speed data corresponding to the historical wind direction data of the target wind turbine in each wind direction sector is obtained, and second historical wind speed data corresponding to other wind turbines at the same time are obtained; based on the first historical wind speed data and the second historical wind speed data, the associated wind turbines corresponding to the target wind turbine in each wind direction sector are determined; the wind speed direction of the first historical wind speed data and the historical wind direction data are the same; the time of the second historical wind speed data and the first historical wind speed data are the same. The step of determining the associated wind turbines of the target wind turbine in each wind direction sector based on the first historical wind speed data and the second historical wind speed data includes: determining the similarity value between the first historical wind speed data and the second historical wind speed data; identifying wind turbines among the other wind turbines whose similarity value is greater than a first preset similarity threshold as associated wind turbines of the target wind turbine, so as to obtain the associated wind turbines of the target wind turbine in each wind direction sector; wherein the number of associated wind turbines is greater than or equal to 3. Based on the historical wind speed data of the target wind turbine in each of the preset wind direction sectors and the historical wind speed data of the associated wind turbine, different wind speed prediction models for the target wind turbine corresponding to different preset wind direction sectors are generated; the wind speed prediction model is generated by a convolutional neural network model learning the wind speed distribution variation law of the historical wind speed data of the target wind turbine in each of the preset wind direction sectors and the historical wind speed data of the associated wind turbine. The current predicted wind speed of the target wind turbine is determined by the wind speed prediction model corresponding to the current wind direction data of the target wind turbine and the current wind speed data of the associated wind turbine, and the measured wind speed of the first anemometer and the measured wind speed of the second anemometer in the target wind turbine are obtained. The current operating status of the anemometers is determined based on the measured wind speeds of the first and second anemometers and the current predicted wind speed, and the wind turbines in the target wind turbine unit are controlled using the target wind speed determined based on the current operating status of the anemometers.

2. The wind turbine operation control method according to claim 1, characterized in that, The process of collecting data on nacelle wind speed and direction for all wind turbine units to obtain corresponding historical wind speed and direction data includes: Data on nacelle wind speed and nacelle wind direction of all wind turbine units are collected within a preset time period, and the collected data is processed to obtain the corresponding historical wind speed data and historical wind direction data; the data processing includes missing value processing, time axis alignment processing, and invalid data removal processing.

3. The wind turbine operation control method according to claim 1 or 2, characterized in that, The process of determining the current anemometer operating status based on the measured wind speeds of the first and second anemometers and the current predicted wind speed includes: The first similarity between the wind speed measured by the first anemometer and the wind speed measured by the second anemometer, the second similarity between the wind speed measured by the first anemometer and the current predicted wind speed, and the third similarity between the wind speed measured by the second anemometer and the current predicted wind speed are determined respectively. The current operating status of the anemometer is determined based on the first similarity, the second similarity, and the third similarity.

4. The wind turbine operation control method according to claim 3, characterized in that, Determining the current anemometer operating status based on the first similarity, the second similarity, and the third similarity includes: If both the first similarity and the second similarity are greater than the second preset similarity threshold, then it is determined that both the first anemometer and the second anemometer are in normal operating condition. If the first similarity is greater than the second preset similarity threshold, and the second similarity is not greater than the second preset similarity threshold, then it is determined that both the first anemometer and the second anemometer are in a fault state. If the first similarity and the second similarity are both not greater than the second preset similarity threshold, and the third similarity is greater than the second preset similarity threshold, then it is determined that the first anemometer is in a fault state and the second anemometer is in a normal operating state. If both the first similarity and the third similarity are not greater than the second preset similarity threshold, and the second similarity is greater than the second preset similarity threshold, then the first anemometer is determined to be in normal operating condition and the second anemometer is in fault condition.

5. The wind turbine operation control method according to claim 3, characterized in that, The control of the wind turbines in the target wind turbine unit using the target wind speed determined based on the current anemometer operating status includes: If both the first anemometer and the second anemometer are in normal operation, then either the wind speed measured by the first anemometer or the wind speed measured by the second anemometer is selected to control the wind turbine in the target wind turbine unit. If the first anemometer is faulty and the second anemometer is operating normally, the wind speed measured by the second anemometer is selected to control the wind turbine in the target wind turbine unit. If the second anemometer is in a faulty state and the first anemometer is in a normal operating state, then the wind speed measured by the first anemometer is selected to control the wind turbine in the target wind turbine unit. If both the first and second anemometers are faulty, the wind turbines in the target wind turbine unit will be controlled using the current predicted wind speed.

6. A wind turbine operation control device, characterized in that, include: The associated wind turbine unit determination module is used to collect data on the nacelle wind speed and nacelle wind direction of all wind turbine units to obtain the corresponding historical wind speed data and historical wind direction data, and to determine the associated wind turbine units that are associated with the historical wind speed data of their own units and the historical wind speed data of the target wind turbine unit in each preset wind direction sector. The step of determining the associated wind turbines that are correlated with the historical wind speed data of the target wind turbine in each preset wind direction sector includes: dividing the wind direction into a preset number of wind direction sectors according to a preset division rule, with the target wind turbine as the center, and assigning the historical wind direction data of the target wind turbine to each wind direction sector; obtaining the first historical wind speed data corresponding to the historical wind direction data of the target wind turbine in each wind direction sector, and obtaining the second historical wind speed data corresponding to other wind turbines at the same time; determining the associated wind turbines corresponding to the target wind turbine in each wind direction sector based on the first historical wind speed data and the second historical wind speed data; wherein the wind speed direction of the first historical wind speed data and the historical wind direction data are the same; and the time of the second historical wind speed data and the first historical wind speed data are the same. The step of determining the associated wind turbines of the target wind turbine in each wind direction sector based on the first historical wind speed data and the second historical wind speed data includes: determining the similarity value between the first historical wind speed data and the second historical wind speed data; identifying wind turbines among the other wind turbines whose similarity value is greater than a first preset similarity threshold as associated wind turbines of the target wind turbine, so as to obtain the associated wind turbines of the target wind turbine in each wind direction sector; wherein the number of associated wind turbines is greater than or equal to 3. The model generation module is used to generate different wind speed prediction models for the target wind turbine corresponding to different preset wind direction sectors based on the historical wind speed data of the target wind turbine in each preset wind direction sector and the historical wind speed data of the associated wind turbine; the wind speed prediction model is generated by a convolutional neural network model learning the wind speed distribution variation law of the historical wind speed data of the target wind turbine in each preset wind direction sector and the historical wind speed data of the associated wind turbine. The predicted wind speed generation module is used to determine the current predicted wind speed of the target wind turbine using the wind speed prediction model corresponding to the current wind direction data of the target wind turbine and the current wind speed data of the associated wind turbine, and to obtain the measured wind speed of the first anemometer and the measured wind speed of the second anemometer in the target wind turbine. The wind turbine control module is used to determine the current operating status of the anemometers based on the measured wind speeds of the first and second anemometers and the current predicted wind speed, and to control the wind turbines in the target wind turbine unit using the target wind speed determined based on the current operating status of the anemometers.

7. An electronic device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the wind turbine operation control method as described in any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that, Used to store a computer program, which, when executed by a processor, implements the wind turbine operation control method as described in any one of claims 1 to 5.

Images