Wind turbine generator blade angle control method and device, storage medium and electronic equipment
By using a deep learning model to predict the wind speed change trend and dynamically adjust the blade angle, the problem of response lag of the wind turbine unit when the wind speed changes is solved, the adaptability and safety of the unit are improved, and the power generation efficiency of the wind farm is improved.
Patent Information
- Application Number
- CN202411543884.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-31
- Publication Date
- 2025-01-24
AI Technical Summary
The existing wind turbines have a time lag when the wind speed changes, and they cannot quickly adapt to the sudden change in wind speed, resulting in safety hazards such as overspeeding and aggravated vibrations, affecting the safe and stable operation of the unit.
By acquiring the real-time operating data and wind energy data of wind turbines, preprocessing it combined with environmental meteorological data, and inputting it into the pre-trained deep learning model, the wind speed change trend is predicted, and the blade angle is dynamically adjusted according to the prediction results.
The response speed and adaptability of wind turbines were significantly improved, and the safety issues such as speeding and vibration of the unit during wind speed mutations were avoided, and the power field efficiency was improved, and the unit of the unit was safe and stable.
Smart Images
Figure CN119353155A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the technical field of wind turbine control, and in particular to a method, device, storage medium and electronic device for controlling a blade angle of a wind turbine. Background Art
[0002] In a wind turbine, the blade angle determines the efficiency of wind energy conversion. When the wind speed changes, the blade angle needs to be adjusted dynamically to ensure maximum output efficiency.
[0003] In the related technology, wind turbines usually transmit wind speed signals to main controllers such as PLC and single-chip microcomputer after receiving them from anemometers. After data analysis, they give instructions for adjusting the blade angle, thereby achieving the optimal power output of the current unit. However, there is an obvious time lag in this adjustment process, and it is unable to quickly adapt to sudden changes in wind speed. In addition, feedback control strategies based on current wind speed and rotation speed are usually adopted, which lack adaptability to complex and changeable wind conditions. When the wind speed suddenly increases, the blade angle cannot be adjusted in time, which can easily lead to safety hazards such as overspeed and increased vibration of the unit, seriously affecting the safe and stable operation of the unit. Summary of the invention
[0004] The purpose of the present disclosure is to provide a method, device, storage medium and electronic device for controlling the blade angle of a wind turbine generator set to solve the problems in the related art.
[0005] In order to achieve the above objectives, in a first aspect, the present disclosure provides a method for controlling a blade angle of a wind turbine, the method comprising: Acquire real-time operation data and real-time wind energy data of each wind turbine in the target area, as well as environmental meteorological data of the target area; Preprocessing the real-time wind energy data and the environmental meteorological data to obtain target data; Inputting the target data into a pre-trained deep learning model to obtain a wind speed prediction result corresponding to each wind turbine in the target area; According to the wind speed prediction result and the real-time operation data, the blade angle of each wind turbine is controlled to reach a corresponding target angle.
[0006] Optionally, the preprocessing of the real-time wind energy data and the environmental meteorological data to obtain target data includes: Obtaining smoothed data according to the real-time wind energy data, the environmental meteorological data and a preset filtering algorithm; Perform feature recognition on the smoothed data to obtain the target data.
[0007] Optionally, the training of the deep learning model includes: Acquire a model training sample, wherein the model training sample includes sample data and a data label corresponding to the sample data; Divide the model training samples into a training set, a validation set and a test set, wherein the training set is used for learning model parameters, the validation set is used for model selection and tuning, and the test set is used to evaluate the performance of the final model; The deep learning model is trained according to the training set, the validation set and the test set to obtain a trained deep learning model.
[0008] Optionally, the data tag includes an actual wind speed value corresponding to a time series of the sample data.
[0009] Optionally, inputting the target data into a pre-trained deep learning model to obtain a wind speed prediction result corresponding to each wind turbine in the target area includes: Inputting the target data into a pre-trained deep learning model to obtain a wind speed prediction value corresponding to each wind turbine set in a time period to be predicted; The wind speed prediction result is obtained according to the wind speed prediction value.
[0010] Optionally, controlling the blade angle of each wind turbine set to reach a corresponding target angle according to the wind speed prediction result and the real-time operation data includes: The wind speed prediction result is compared with a preset wind speed range, and according to the real-time operation data and a preset fuzzy control algorithm, the blade angle of each wind turbine is controlled to reach a corresponding target angle.
[0011] In a second aspect, the present disclosure provides a wind turbine blade angle control device, the device comprising: An acquisition module, used to acquire real-time operation data and real-time wind energy data of each wind turbine in the target area, as well as environmental meteorological data of the target area; A preprocessing module, used for preprocessing the real-time wind energy data and the environmental meteorological data to obtain target data; A prediction module, used to input the target data into a pre-trained deep learning model to obtain a wind speed prediction result corresponding to each wind turbine in the target area; The control module is used to control the blade angle of each wind turbine set to reach a corresponding target angle according to the wind speed prediction result and the real-time operation data.
[0012] Optionally, the preprocessing module is used to: Obtaining smoothed data according to the real-time wind energy data, the environmental meteorological data and a preset filtering algorithm; Perform feature recognition on the smoothed data to obtain the target data.
[0013] In a third aspect, the present disclosure provides a non-temporary computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any one of the methods described in the first aspect.
[0014] In a fourth aspect, the present disclosure provides an electronic device, including: a memory having a computer program stored thereon; A processor is used to execute the computer program in the memory to implement the steps of any one of the methods in the first aspect.
[0015] Through the above technical solution, the real-time operation data and real-time wind energy data of each wind turbine in the target area, as well as the environmental meteorological data of the target area, are obtained, the real-time wind energy data and environmental meteorological data are preprocessed to obtain the target data, and the target data is input into the pre-trained deep learning model to obtain the wind speed prediction results corresponding to each wind turbine in the target area. According to the wind speed prediction results and real-time operation data, the blade angle of each wind turbine is controlled to reach the corresponding target angle. Among them, by constructing a deep learning model, the wind speed change trend can be predicted in advance, and the blade angle of each wind turbine can be dynamically adjusted according to the wind speed prediction results and real-time operation data, thereby greatly improving the response speed and adaptability, and effectively avoiding safety problems such as overspeed and vibration of the unit when the wind speed suddenly changes, thereby effectively improving the power generation efficiency of the wind farm and ensuring the safe and stable operation of the unit.
[0016] Other features and advantages of the present disclosure will be described in detail in the following detailed description. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] The accompanying drawings are used to provide a further understanding of the present disclosure and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present disclosure but do not constitute a limitation of the present disclosure. In the accompanying drawings: Figure 1 The figure is a flow chart of a method for controlling a blade angle of a wind turbine according to an exemplary embodiment of the present disclosure.
[0018] Figure 2 The present invention is a block diagram of a wind turbine blade angle control device according to an exemplary embodiment of the present invention.
[0019] Figure 3 It is a block diagram of an electronic device according to an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION
[0020] The specific implementation of the present disclosure is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the present disclosure, and is not used to limit the present disclosure.
[0021] As mentioned in the background technology, in the related technology, wind turbines usually transmit wind speed signals to main controllers such as PLC and single-chip microcomputer after the anemometer receives them. After data analysis, the command of blade angle adjustment is given to achieve the optimal power output of the current unit. However, there is an obvious time lag in the process of this adjustment method, and it is unable to quickly adapt to sudden changes in wind speed. In addition, the feedback control strategy based on the current wind speed and rotation speed is usually adopted, which lacks adaptability to complex and changeable wind conditions. When the wind speed suddenly increases, the blade angle cannot be adjusted in time, which easily leads to safety hazards such as overspeed and increased vibration of the unit, seriously affecting the safe and stable operation of the unit.
[0022] Specifically, in the above-mentioned adjustment method, the measurement of wind speed, the transmission and processing of data, and the execution of instructions all require time, resulting in a significant lag in the response of the entire system. When the wind speed changes dramatically, especially when encountering gusty or windy weather, this lag is particularly significant, and it is impossible to quickly adapt to the change in wind speed. And although adjusting the blade angle according to the current wind speed and unit speed can achieve power optimization and unit protection to a certain extent, it is not flexible and adaptable enough when facing complex and changeable wind conditions. Especially when the wind speed changes suddenly, a single control strategy often finds it difficult to quickly find the optimal blade angle, and the blade may not be adjusted to the appropriate angle in time to limit the captured wind energy, resulting in unsafe conditions such as unit overspeed, increased vibration, and overpower. These conditions will not only damage the transmission system of the unit, but may also cause more serious failures, such as damage to mechanical components, shutdowns, and even accidents, seriously affecting the safe operation and life of the unit.
[0023] In view of this, the embodiments of the present disclosure provide a method, device, storage medium and electronic device for controlling the blade angle of a wind turbine set, which can effectively improve the power generation efficiency of the wind farm and ensure the safe and stable operation of the set.
[0024] Figure 1 is a flow chart of a method for controlling a blade angle of a wind turbine according to an exemplary embodiment of the present disclosure. Figure 1 As shown, the method may include the following steps: Step S101, acquiring real-time operation data and real-time wind energy data of each wind turbine in a target area, and environmental meteorological data of the target area.
[0025] It should be understood that the Internet of Things technology can be used to connect wind turbines, anemometers, weather stations and other equipment in the target area to a unified cloud platform to achieve real-time data collection, transmission and sharing. The cloud platform should have high availability, scalability and security. The operating data and environmental meteorological data of these devices can include: operating parameters such as the speed, power output, and vibration status of each wind turbine, real-time wind energy data such as wind speed, wind direction, temperature, and humidity, and environmental meteorological data such as air pressure, rainfall, and cloud cover. In addition, the processed data can be stored in the database of the cloud platform, and an efficient data indexing and query mechanism can be established to facilitate subsequent data analysis and model training.
[0026] For example, appropriate communication protocols, such as MQTT (Message Queue Telemetry Transport) and CoAP (Constrained Application Protocol), can be used to establish a stable and reliable IoT communication network to ensure the efficiency and security of data transmission.
[0027] Step S102, pre-processing the real-time wind energy data and environmental meteorological data to obtain target data.
[0028] Step S103: input the target data into a pre-trained deep learning model to obtain the wind speed prediction result corresponding to each wind turbine in the target area.
[0029] Step S104, controlling the blade angle of each wind turbine to reach a corresponding target angle according to the wind speed prediction result and the real-time operation data.
[0030] It should be understood that when the wind speed is low, in order to maximize the capture of wind energy, the blades can usually be maintained at a smaller pitch angle (close to 0°) so that the blades can more effectively capture wind energy and convert it into mechanical energy. When the wind speed reaches the rated wind speed of the wind turbine, the system can adjust the pitch angle in real time according to the change in wind speed to ensure that the wind turbine avoids overload and excessive mechanical stress while maintaining maximum output power. When the wind speed exceeds the rated wind speed, in order to limit the output power of the wind turbine and protect the unit from damage, the system can increase the pitch angle so that the blades deviate from the optimal windward angle, thereby reducing the captured wind energy. This adjustment method helps to achieve air braking and ensure the safe operation of the unit.
[0031] Through the above method, the real-time operation data and real-time wind energy data of each wind turbine in the target area, as well as the environmental meteorological data of the target area, are obtained, the real-time wind energy data and environmental meteorological data are preprocessed to obtain the target data, and the target data is input into the pre-trained deep learning model to obtain the wind speed prediction results corresponding to each wind turbine in the target area. According to the wind speed prediction results and real-time operation data, the blade angle of each wind turbine is controlled to reach the corresponding target angle. Among them, by constructing a deep learning model, the wind speed change trend can be predicted in advance, and the blade angle of each wind turbine can be dynamically adjusted according to the wind speed prediction results and real-time operation data, thereby greatly improving the response speed and adaptability, and effectively avoiding safety problems such as overspeed and vibration of the unit when the wind speed suddenly changes, thereby effectively improving the power generation efficiency of the wind farm and ensuring the safe and stable operation of the unit.
[0032] In a possible implementation, preprocessing the real-time wind energy data and environmental meteorological data to obtain target data may include: Obtain smoothed data based on real-time wind energy data, environmental meteorological data, and a preset filtering algorithm; Perform feature recognition on the smoothed data to obtain the target data.
[0033] It should be understood that the raw data collected in real time will contain some noise and sudden outliers, which will have an adverse effect on the subsequent prediction model. Therefore, it is necessary to use digital filtering algorithms, such as moving average filtering, Gaussian filtering, etc., to smooth the raw data, remove noise and outliers, and obtain a relatively smooth data sequence. This ensures that subsequent feature recognition and model training are based on more stable and reliable data input.
[0034] It should also be understood that in addition to the original parameters such as wind speed and temperature, some more representative features need to be extracted as input to the deep learning model. For example, statistics such as the average, variance, and peak value within a certain time window can be calculated, or the spectral characteristics of wind speed and wind direction can be extracted. These features can often better reflect the influence of environmental conditions on the operation of wind turbines, which is conducive to model learning and making more accurate predictions.
[0035] Through the above method, real-time wind energy data and environmental meteorological data are effectively preprocessed, which helps the subsequent deep learning model to maintain a high prediction performance in complex environments, thereby improving the accuracy of wind speed prediction.
[0036] In one possible implementation, the training of the deep learning model may include: Obtain model training samples, where the model training samples include sample data and data labels corresponding to the sample data.
[0037] The data tags may include actual wind speed values corresponding to the time series of the sample data.
[0038] It should be understood that by integrating the historical operating data of a single unit and related meteorological information, and associating these characteristic data with the actual wind speed value label, a representative training sample can be constructed, laying a good foundation for model training. These data labels can provide accurate supervision signals for the model, enabling it to learn the law of wind speed changes, thereby improving the accuracy of predictions.
[0039] The model training samples are divided into training set, validation set and test set. The training set is used to learn model parameters, the validation set is used for model selection and tuning, and the test set is used to evaluate the performance of the final model.
[0040] The deep learning model is trained according to the training set, validation set and test set to obtain a trained deep learning model.
[0041] It should be understood that the deep learning model used for wind speed prediction can consider multi-dimensional inputs such as real-time wind energy information of wind turbines in the region, historical wind speed data, weather forecast data, topographic information, etc., and annotate historical data and divide them into training sets, validation sets, and test sets for model training and evaluation. The model is trained using the training set data, and the prediction accuracy and generalization ability of the model are improved by adjusting model parameters and optimizing algorithms. The model is evaluated using validation sets and test sets, and the model is tuned according to the evaluation results. At the same time, a self-learning mechanism is introduced to enable the model to continuously learn and optimize from new operating data to adapt to changing wind conditions and unit status.
[0042] It should be understood that the deep learning algorithm is a method of training computers to learn and recognize patterns by imitating the structure and operation of the human brain neural network. It is based on a multi-level neural network and continuously optimizes network parameters through the back propagation algorithm to achieve efficient processing and prediction of complex data. In addition, the deep learning model is suitable for processing time series data and can capture long-term dependencies in time series.
[0043] For example, regarding the structural design of the deep learning model, the Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN) can be used in combination, and multi-dimensional input can be considered. Among them, the input layer can include: time series data input: including time series data such as historical wind speed, wind direction, and power output; static feature input: including features that do not change over time such as topographic information and wind turbine location; meteorological forecast data input: including future short-term temperature, humidity, and air pressure forecasts. The time series feature extraction module (LSTM layer) can be used to capture short-term time series features and long-term time series dependencies. The spatial feature extraction module (CNN layer) can include: convolutional layers and pooling layers for processing spatial information such as topography and wind turbine location. The meteorological feature processing module can include: a fully connected layer for processing meteorological forecast data. And feature fusion layer, fully connected layer, and output layer for further processing the fused features and giving the final wind speed prediction result.
[0044] It should also be understood that the model structure design can comprehensively consider the temporal characteristics, spatial characteristics and meteorological forecast data, and can effectively process multi-dimensional inputs to achieve the effect of improving the accuracy of wind speed prediction. And according to the actual application scenario and data characteristics, the model structure and parameters can be further adjusted to obtain the best performance.
[0045] Through the above methods, the model trained with historical data can be fully utilized to better capture the complex relationship between wind turbines and the environment, and provide more accurate wind speed prediction results. In practical applications, new data can be continuously collected, and retrained and optimized regularly to adapt to dynamic changes in the environment.
[0046] In a possible implementation, inputting the target data into a pre-trained deep learning model to obtain a wind speed prediction result corresponding to each wind turbine in the target area may include: Input the target data into the pre-trained deep learning model to obtain the wind speed prediction value for each wind turbine in the prediction time period; According to the wind speed prediction value, the wind speed prediction result is obtained.
[0047] It should be understood that the output of the model is a series of wind speed prediction values corresponding to each wind turbine, which represents the wind speed change trend within the prediction period. By integrating these prediction values, the wind speed prediction results of each unit in the target area can be formed. These prediction results can provide a decision basis for subsequent blade angle control.
[0048] In this way, the model can process the latest environmental data in real time and quickly give corresponding wind speed forecasts to meet the needs of real-time control of wind turbines.
[0049] In a possible implementation, controlling the blade angle of each wind turbine to reach a corresponding target angle according to the wind speed prediction result and the real-time operation data may include: The wind speed prediction result is compared with the preset wind speed range, and the blade angle of each wind turbine is controlled to reach the corresponding target angle based on the real-time operation data and the preset fuzzy control algorithm.
[0050] It should be understood that an adaptive mechanism can be introduced according to actual conditions to continuously monitor the control effect and dynamically adjust the prediction model and fuzzy rule parameters according to the actual operating data, so that the control strategy can be adaptively adjusted according to changes in the mutual influence between random groups.
[0051] It should also be understood that the relative distance factor between wind turbines can be incorporated into the preset fuzzy control algorithm for processing. The specific process can be as follows: 1) Divide the distance between units into fuzzy sets: According to the actual layout of the wind farm, the relative distance between units is divided into fuzzy sets such as "near", "middle" and "far", which can qualitatively describe the spatial position relationship between different units.
[0052] 2) Introducing the distance between units into the fuzzy rules: When formulating the fuzzy control rules for blade angle adjustment, in addition to considering factors such as wind speed prediction and unit operating status, the relative distance between units can also be included as one of the input variables of the rule.
[0053] 3) Reflect the influence of distance in fuzzy reasoning: When reasoning according to fuzzy rules, the fuzzy value of the distance between units will affect the determination of the blade angle adjustment amount. For units that are close to each other, the adjustment range can be appropriately reduced because wind speed changes propagate faster. For units that are far apart, the adjustment range needs to be appropriately increased to cope with the delayed propagation of wind speed changes.
[0054] 4) Dynamic adjustment of fuzzy rules: As the actual operating conditions change, the weight of the distance between units in the fuzzy rules can be dynamically adjusted. For example, when it is found that the distance factor has a greater impact on the control effect, its status in the rules can be appropriately improved. Through adaptive adjustment, the fuzzy control strategy can better adapt to the actual conditions of different wind farms.
[0055] For example, the wind speed range can be set according to actual conditions as a reference for adjusting the blade angle.
[0056] It is worth noting that the fuzzy control algorithm has the ability of adaptive adjustment and can dynamically optimize parameters according to the actual operating conditions. This adaptability helps to improve the robustness of the algorithm and adapt to complex and changing environments. By coordinating the blade angle adjustment of each unit, the power generation of the entire wind farm can be maximized, while also ensuring the safe and stable operation of each unit. It can be verified in a simulation environment to evaluate its effect on improving the overall power generation efficiency and stability of the wind farm, and the verified relevant control strategies can be deployed to the actual wind farm, and dynamically adjusted and optimized according to the actual operating conditions.
[0057] Through the above method, based on accurate wind speed prediction and optimized blade angle control, it can be ensured that each unit works in the best condition, so as to obtain more wind power conversion power to improve the overall power generation and economic benefits of the entire wind farm.
[0058] In summary, the wind turbine blade angle control method has the following advantages: 1) Significantly improve response speed: By collecting data from multiple wind turbines, anemometers and meteorological stations in the target area in real time and using the cloud platform for big data analysis, the wind speed change trend can be predicted in advance, so that the blade angle adjustment command can be issued before the wind speed actually changes, effectively reducing the lag time of system response and improving the dynamic response capability of the unit.
[0059] 2) Optimize control strategy and enhance adaptability: Abandon the traditional single control strategy and introduce advanced control algorithms based on big data analysis and prediction. These algorithms can comprehensively consider multiple factors, such as wind speed, wind direction, topography and mutual influence between units, to achieve more flexible and intelligent blade angle adjustment, so as to better adapt to complex and changeable wind conditions and improve the operating efficiency and stability of the unit.
[0060] 3) Enhanced safety performance: By predicting wind speed changes in advance and adjusting the blade angle in a timely manner, it can effectively avoid unsafe conditions such as overspeed, vibration, overpower, etc. caused by untimely adjustment when the wind speed changes suddenly, reduce the mechanical stress of the unit, extend the life of the unit, and significantly improve the unit's safe operation capabilities under extreme weather conditions.
[0061] 4) Explore optimization potential and improve overall efficiency: Make full use of big data and artificial intelligence technology to deeply explore the potential value of wind turbine operation data, and further optimize the power output efficiency and energy utilization rate of the unit through customized blade angle adjustment and regional collaborative control strategy. At the same time, it realizes the collaborative optimization between multiple wind turbines, improving the operating efficiency and economy of the entire wind farm.
[0062] 5) Intelligence and self-optimization: It has the ability of self-learning and continuous optimization, and can continuously learn from new operating data and optimize prediction models and control strategies to adapt to changing wind conditions and unit status, ensuring safe and stable operation of the unit.
[0063] Figure 2 A wind turbine blade angle control device 200 is shown according to an exemplary embodiment of the present disclosure. Figure 2 As shown, the wind turbine blade angle control device 200 may include: An acquisition module 201 is used to acquire real-time operation data and real-time wind energy data of each wind turbine in the target area, as well as environmental meteorological data of the target area; A preprocessing module 202 is used to preprocess the real-time wind energy data and environmental meteorological data to obtain target data; Prediction module 203, used to input target data into a pre-trained deep learning model to obtain wind speed prediction results corresponding to each wind turbine in the target area; The control module 204 is used to control the blade angle of each wind turbine to reach a corresponding target angle according to the wind speed prediction result and the real-time operation data.
[0064] Through the above device, the real-time operation data and real-time wind energy data of each wind turbine in the target area, as well as the environmental meteorological data of the target area, are obtained, the real-time wind energy data and environmental meteorological data are preprocessed to obtain the target data, and the target data is input into the pre-trained deep learning model to obtain the wind speed prediction results corresponding to each wind turbine in the target area. According to the wind speed prediction results and real-time operation data, the blade angle of each wind turbine is controlled to reach the corresponding target angle. Among them, by constructing a deep learning model, the wind speed change trend can be predicted in advance, and the blade angle of each wind turbine can be dynamically adjusted according to the wind speed prediction results and real-time operation data, thereby greatly improving the response speed and adaptability, and effectively avoiding safety problems such as overspeed and vibration of the unit when the wind speed suddenly changes, thereby effectively improving the power generation efficiency of the wind farm and ensuring the safe and stable operation of the unit.
[0065] Optionally, the preprocessing module 202 is used to: Obtain smoothed data based on real-time wind energy data, environmental meteorological data, and a preset filtering algorithm; Perform feature recognition on the smoothed data to obtain the target data.
[0066] Optionally, the training of the deep learning model includes the following modules: A model training sample acquisition module is used to acquire model training samples, where the model training samples include sample data and data labels corresponding to the sample data; The model training sample division module is used to divide the model training samples into training set, validation set and test set. The training set is used to learn model parameters, the validation set is used for model selection and tuning, and the test set is used to evaluate the performance of the final model. The deep learning model training module is used to train the deep learning model according to the training set, validation set and test set to obtain a trained deep learning model.
[0067] Optionally, the data labels in the model training sample acquisition module include actual wind speed values corresponding to the time series of the sample data.
[0068] Optionally, the prediction module 203 is used to: Input the target data into the pre-trained deep learning model to obtain the wind speed prediction value for each wind turbine in the prediction time period; According to the wind speed prediction value, the wind speed prediction result is obtained.
[0069] Optionally, the control module 204 is used to: The wind speed prediction result is compared with the preset wind speed range, and the blade angle of each wind turbine is controlled to reach the corresponding target angle based on the real-time operation data and the preset fuzzy control algorithm.
[0070] Regarding the device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0071] Figure 3 FIG. 1 is a block diagram of an electronic device 300 according to an exemplary embodiment of the present disclosure. Figure 3 As shown, the electronic device 300 may include: a processor 301 , a memory 302 . The electronic device 300 may also include one or more of a multimedia component 303 , an input / output (I / O) interface 304 , and a communication component 305 .
[0072] The processor 301 is used to control the overall operation of the electronic device 300 to complete all or part of the steps in the above-mentioned wind turbine blade angle control method. The memory 302 is used to store various types of data to support the operation of the electronic device 300, and these data may include, for example, instructions for any application or method used to operate on the electronic device 300, and data related to the application. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 303 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 302 or sent through the communication component 305. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 304 provides an interface between the processor 301 and other interface modules, and the other interface modules may be keyboards, mice, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 305 is used for wired or wireless communication between the electronic device 300 and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, etc., or a combination of one or more of them, is not limited here. Therefore, the corresponding communication component 305 may include: Wi-Fi module, Bluetooth module, NFC module, etc.
[0073] In an exemplary embodiment, the electronic device 300 can be implemented by one or more application specific integrated circuits (ASIC), digital signal processors (DSP), digital signal processing devices (DSPD), programmable logic devices (PLD), field programmable gate arrays (FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned wind turbine blade angle control method.
[0074] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned wind turbine blade angle control method are implemented. For example, the computer-readable storage medium can be the above-mentioned memory 302 including program instructions, and the above-mentioned program instructions can be executed by the processor 301 of the electronic device 300 to complete the above-mentioned wind turbine blade angle control method.
[0075] The preferred embodiments of the present disclosure are described in detail above in conjunction with the accompanying drawings; however, the present disclosure is not limited to the specific details in the above embodiments. Within the technical concept of the present disclosure, a variety of simple modifications can be made to the technical solution of the present disclosure, and these simple modifications all fall within the protection scope of the present disclosure.
[0076] 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 present disclosure will not further describe various possible combinations.
[0077] In addition, various embodiments of the present disclosure may be arbitrarily combined, and as long as they do not violate the concept of the present disclosure, they should also be regarded as the contents disclosed by the present disclosure.
Claims
1. A method for controlling the blade angle of a wind turbine, characterized in that: The method comprises: Acquire real-time operation data and real-time wind energy data of each wind turbine in the target area, as well as environmental meteorological data of the target area; Preprocessing the real-time wind energy data and the environmental meteorological data to obtain target data; Inputting the target data into a pre-trained deep learning model to obtain a wind speed prediction result corresponding to each wind turbine in the target area; According to the wind speed prediction result and the real-time operation data, the blade angle of each wind turbine is controlled to reach a corresponding target angle.
2. The method according to claim 1, characterized in that The preprocessing of the real-time wind energy data and the environmental meteorological data to obtain target data includes: Obtaining smoothed data according to the real-time wind energy data, the environmental meteorological data and a preset filtering algorithm; Perform feature recognition on the smoothed data to obtain the target data.
3. The method according to claim 1, characterized in that The training of the deep learning model includes: Acquire a model training sample, wherein the model training sample includes sample data and a data label corresponding to the sample data; Divide the model training samples into a training set, a validation set and a test set, wherein the training set is used for learning model parameters, the validation set is used for model selection and tuning, and the test set is used to evaluate the performance of the final model; The deep learning model is trained according to the training set, the validation set and the test set to obtain a trained deep learning model.
4. The method according to claim 3, characterized in that The data tags include actual wind speed values corresponding to the time series of the sample data.
5. The method according to claim 1, characterized in that The target data is input into a pre-trained deep learning model to obtain a wind speed prediction result corresponding to each wind turbine in the target area, including: Inputting the target data into a pre-trained deep learning model to obtain a wind speed prediction value corresponding to each wind turbine set in a time period to be predicted; The wind speed prediction result is obtained according to the wind speed prediction value.
6. The method according to claim 1, characterized in that The controlling the blade angle of each wind turbine generator set to reach a corresponding target angle according to the wind speed prediction result and the real-time operation data includes: The wind speed prediction result is compared with a preset wind speed range, and according to the real-time operation data and a preset fuzzy control algorithm, the blade angle of each wind turbine is controlled to reach a corresponding target angle.
7. A wind turbine blade angle control device, characterized in that: The device comprises: An acquisition module, used to acquire real-time operation data and real-time wind energy data of each wind turbine in the target area, as well as environmental meteorological data of the target area; A preprocessing module, used for preprocessing the real-time wind energy data and the environmental meteorological data to obtain target data; A prediction module, used to input the target data into a pre-trained deep learning model to obtain a wind speed prediction result corresponding to each wind turbine in the target area; The control module is used to control the blade angle of each wind turbine set to reach a corresponding target angle according to the wind speed prediction result and the real-time operation data.
8. The device according to claim 7, characterized in that The pre-processing module is used for: Obtaining smoothed data according to the real-time wind energy data, the environmental meteorological data and a preset filtering algorithm; Perform feature recognition on the smoothed data to obtain the target data.
9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.
10. An electronic device, characterized in that: include: a memory having a computer program stored thereon; A processor, configured to execute the computer program in the memory to implement the steps of the method according to any one of claims 1 to 6.