An automatic control yaw positioning system for a wind turbine generator

Abstract

The present invention discloses an automatic control yaw positioning system for a wind turbine generator. The present invention relates to the technical field of wind power generation and includes a wind turbine generator control system, which is communicatively connected to a wind turbine generator data acquisition module, a wind turbine generator data processing module, and a wind turbine generator data analysis module; the wind turbine generator data acquisition module uses an anemometer, a wind vane, and a temperature sensor to monitor the wind speed, wind direction, and component temperature in real time. The wind turbine generator data processing module predicts the wind direction by training a BP neural network model, automatically adjusts the yaw angle to ensure that the component temperature is within the normal range. The wind turbine generator data analysis module adjusts the yaw angle according to different wind speeds and wind directions based on the prediction results of the BP neural network model and sets different component temperature thresholds. The wind turbine generator control system is responsible for receiving the original data, performing the yaw operation, and monitoring the component temperature. The entire system works together to ensure the efficient operation of the wind turbine generator.

Description

Technical Field

[0001] The invention relates to the technical field of wind power generation, and in particular to a yaw positioning system for automatically controlling a wind power generator set. Background Art

[0002] The yaw positioning system of the automatic control wind turbine is standing at a development outlet full of infinite possibilities, and its development prospects are undoubtedly extremely broad. Against the background of the growing global demand for renewable energy, wind power generation, as a clean and renewable energy form, is receiving unprecedented attention. With the continuous breakthroughs in technology and the strong support of government policies, the wind power industry is ushering in an unprecedented period of rapid growth. The yaw positioning system, as a vital link in the wind turbine, has a decisive influence on the operating efficiency of the entire wind power generation system through the optimization and improvement of its performance. With the continuous advancement of intelligent and automated technology, the yaw positioning system is gradually getting rid of the traditional manual control mode and developing in a more intelligent and efficient direction. This not only greatly improves the efficiency of wind energy utilization, enabling wind turbines to maintain optimal working conditions in various complex environments, but also significantly reduces operation and maintenance costs, laying a solid foundation for the sustainable development of the wind power industry.

[0003] At present, electronic yaw systems have achieved remarkable results in the field of wind power generation, achieving more precise control of wind direction. This progress not only improves the operating efficiency of wind turbines, but also further optimizes the capture and utilization of wind energy. However, this is only a starting point for the development of yaw systems, and future development trends will focus more on intelligence and automation. With the rapid development of science and technology, advanced sensing technology and neural network algorithms are gradually being integrated into the design of yaw systems. The application of these technologies will enable the system to accurately predict wind direction changes in real time and automatically adjust the yaw angle according to the prediction results to ensure that the wind turbines are always in the best working condition. At the same time, these technologies will also enhance the system's adaptability in extreme weather conditions, such as cold or hot weather, to ensure that the system can operate continuously and stably. Looking to the future, the yaw positioning system of automatically controlled wind turbines will achieve more efficient, reliable and intelligent development driven by continuous technological innovation and continuous market expansion. Summary of the invention

[0004] In view of the deficiencies in the prior art, the present invention provides a yaw positioning system for automatically controlling a wind turbine generator set, which solves the problems in the above-mentioned background technology.

[0005] To achieve the above object, the present invention is realized through the following technical solutions: An automatic control yaw positioning system for a wind turbine generator set includes a wind turbine generator set control system, which is communicatively connected to a wind turbine generator set data acquisition module, a wind turbine generator set data processing module, and a wind turbine generator set data analysis module;

[0006] The wind turbine generator set data acquisition module includes: an anemometer, a wind vane, and a temperature sensor on the wind turbine generator set, which monitor the changes in wind speed and wind direction and detect the temperature of each component of the wind turbine generator set during operation;

[0007] The wind turbine generator set data processing module realizes the accurate prediction of the wind direction and the automatic adjustment of the yaw angle by training a BP neural network model;

[0008] The wind turbine generator set data analysis module, based on the prediction results of the BP neural network model, realizes the adjustment of the yaw angle of the wind turbine generator set under different wind speeds and wind directions and sets the thresholds for different temperatures of each component of the system;

[0009] The wind turbine generator set control system is responsible for receiving and processing the collected raw data, performing yaw, and detecting the temperature of each component of the system.

[0010] Further, the process of the wind turbine generator set data acquisition module real-time monitoring the changes in wind speed and wind direction through the anemometer and wind vane installed on the wind turbine generator set includes:

[0011] The anemometer senses the magnitude of the wind through the propeller inside it and converts it into an electrical signal. The above electrical signal is proportional to the wind speed. When the wind speed increases, the electrical signal increases accordingly. When the wind speed decreases, the electrical signal decreases accordingly. The wind vane is used to sense the direction of the wind. It is a device that can rotate freely and contains a potentiometer inside. When the wind direction changes, the wind vane rotates accordingly, generating a corresponding electrical signal, which represents the current wind direction. The collected wind speed and wind direction signals are converted into digital signals through analog-to-digital conversion.

[0012] Further, the process of the wind turbine generator set data acquisition module detecting the temperature of each component of the wind turbine generator set during operation through the temperature sensor includes:

[0013] The temperature sensor senses the temperature of the gearbox, generator, and bearing of the yaw positioning system through the thermosensitive element inside it. When the temperature changes, the resistance value of the thermosensitive element will change accordingly. This change is converted into an electrical signal, amplified, filtered, and converted into a digital signal through analog-to-digital conversion, and transmitted to the control system of the wind turbine generator set through a communication protocol.

[0014] Further, the process of the wind turbine data processing module inputting the collected data into the input layer of the BP neural network model includes:

[0015] Clean the collected data to remove noise and outliers, normalize the data so that it is in the same dimension and range, smooth the data to reduce the volatility and uncertainty of the data, construct a BP neural network model, which includes an input layer, a hidden layer, and an output layer. Use the historical data of wind speed, wind direction, and temperature as the input of the BP neural network for training the model so that it can learn the relationship between wind speed, wind direction, and wind direction prediction, as well as the correlation between the temperature of each component and yaw adjustment. The number of nodes in the input layer corresponds to the number of input features.

[0016] Further, the process of the wind turbine data processing module training the hidden layer of the BP neural network model includes:

[0017] The neurons in the hidden layer process the input data through weighted summation and activation functions, and extract features related to wind direction prediction and yaw angle adjustment. The features include the non-linear transformation of wind speed, wind direction, and temperature data. Since the problems of wind direction prediction and yaw angle adjustment are non-linear, the neurons in the hidden layer introduce non-linear factors through the Sigmoid activation function so that the model can handle complex non-linear relationships. The neurons in the hidden layer are interconnected and cooperate with each other to integrate the information from the input layer and form a comprehensive understanding of wind direction and yaw angle adjustment.

[0018] Further, the process of the wind turbine data processing module training the output layer of the BP neural network model includes:

[0019] In the task of predicting the wind direction, a regression model is used to output continuous wind direction angle values. A neuron in the output layer is used to output the predicted wind direction angle value. After the output value of this neuron is transformed by the sigmoid activation function, it is the predicted wind direction angle. In the task of yaw angle adjustment, a classification model is used to output discrete adjustment instructions. Three neurons in the output layer respectively correspond to three different adjustment instructions, and the adjustment instructions include turning left, turning right, and maintaining. After the output value of the neuron is transformed by the softmax function, a probability distribution is obtained, indicating the probability of each adjustment instruction. The system selects the adjustment instruction with the highest probability as the final output and sends it to the control system to perform yaw adjustment. The real-time collected data is input into the trained BP neural network model. The model calculates and outputs the predicted wind direction change and the health status of each component of the system according to the input data. The system calculates the yaw angle that needs to be adjusted according to the prediction result and the current operating state of the unit, and generates a control instruction. The yaw system controller adjusts the yaw angle according to the control instruction to keep the wind turbine blades always facing the direction of the wind and maintain the yaw system temperature within the normal operating range.

[0020] Further, the process of the wind turbine data analysis module realizing the yaw angle adjustment of the wind turbine under different wind speeds and wind directions based on the prediction result of the BP neural network model includes:

[0021] When the cut-in wind speed is below 3 m / s, the wind turbine cannot generate electricity effectively. At this time, the yaw system is in the standby state and no yaw adjustment is performed. When the wind speed gradually rises above the cut-in wind speed but below the rated wind speed of 12 m / s, the yaw system adjusts the wind turbine rotor orientation in real time according to the data of the wind vane. The BP neural network model predicts the wind direction change according to the historical data and real-time data. When the wind speed reaches above the rated wind speed, the yaw system dynamically adjusts the yaw angle according to the changes in wind speed and wind direction and the operating state of the unit. In the case where the cut-out wind speed is above 25 m / s, the wind turbine automatically trips and shuts down, and the yaw system adjusts the wind turbine rotor to the side wind position. In addition, when the wind direction changes significantly, the BP neural network model quickly predicts the new wind direction according to the real-time data and controls the yaw system to continuously and smoothly adjust the wind turbine rotor orientation.

[0022] Further, the process of the wind turbine data analysis module setting the thresholds under different temperatures of each component of the system based on the prediction result of the BP neural network model includes:

[0023] When the gearbox temperature of the wind turbine is between 30°C and 70°C, the system operates normally. When the gearbox temperature reaches 80°C, the system issues a high-temperature alarm and activates the heat sink installed outside the gearbox. When the gearbox temperature reaches 90°C, the wind turbine shuts down automatically. When the generator temperature of the wind turbine is between 60°C and 120°C, the system operates normally. When the generator temperature reaches 130°C, the system issues a high-temperature alarm and activates the cooling water circulation system inside the generator. When the generator temperature reaches 150°C, the wind turbine shuts down automatically. When the bearing temperature of the wind turbine is between 30°C and 70°C, the system operates normally. When the bearing temperature reaches 80°C, the system issues a high-temperature alarm to ensure that the lubricating grease is sufficient and clean, and adjusts the load and speed of the wind turbine. When the bearing temperature reaches 95°C, the wind turbine shuts down automatically. When the gearbox temperature drops to -20°C or below, the generator temperature drops to -10°C or below, and the bearing temperature drops to -15°C or below, if any of these three situations occurs, the system issues a low-temperature alarm and heats the gearbox, generator, and bearing by activating heaters to bring them back to the normal temperature range, adjusts the blade angle to reduce the vibration and noise of the wind turbine caused by low temperature, and selects a low-temperature lubricating oil with a lower freezing point and good fluidity for the low-temperature environment to ensure that all components of the system can still maintain good lubrication effects at low temperatures.

[0024] Furthermore, the control system of the wind turbine is responsible for receiving and processing the collected raw data. The process of performing yaw and detecting the temperatures of various components of the system includes:

[0025] The control system receives the real-time monitoring data of wind speed, wind direction, and temperature transmitted by the data acquisition module, processes and analyzes the received data using the BP neural network model in the data processing module, predicts the change of wind direction and calculates the required yaw angle, and adjusts the yaw angle of the wind turbine through the actuator according to the processing result to keep the blades always facing the direction of the wind, monitors the operating temperatures of various components of the wind turbine, and takes corresponding protection measures when the temperature exceeds the normal range.

[0026] The present invention provides a yaw positioning system for automatically controlling a wind turbine. It has the following beneficial effects:

[0027] The yaw positioning system of this automatic control wind turbine generator set has achieved a major breakthrough in the field of wind power generation by deeply integrating advanced sensing technology and BP neural network algorithm. This system can capture the subtle changes in wind speed, wind direction, and the temperature of key components in real time, providing detailed data support for precise control. With the high-precision prediction ability of the BP neural network model, the system can foresee the subtle changes in wind direction and autonomously adjust the yaw angle to ensure that the wind turbine generator set always faces the wind precisely, thereby maximizing the capture of wind energy, significantly improving the power generation efficiency and energy utilization rate. More advancedly, this system is built-in with a powerful adaptability mechanism, which can maintain excellent operation stability under extreme climate conditions such as severe cold and heat, effectively avoiding the potential threats caused by environmental factors to the operation of the equipment, and further extending the service life of the equipment. In addition, the application of intelligent control strategies has greatly reduced the need for manual intervention, lightened the workload of operation and maintenance personnel, saved operation and maintenance costs, and improved the overall economic benefits. In summary, this yaw positioning system not only greatly improves the reliability and efficiency of wind power generation, but also opens up a new path for the sustainable utilization of wind energy resources, injecting strong impetus into the booming development of the green energy industry. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 The block diagram of a yaw positioning system for an automatic control wind turbine generator set according to an embodiment of the present application. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0029] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0030] As Figure 1 shown, the present invention provides a technical solution: a yaw positioning system for an automatic control wind turbine generator set, including a wind turbine generator set control system, and the wind turbine generator set control system is communicatively connected to a wind turbine generator set data acquisition module, a wind turbine generator set data processing module, and a wind turbine generator set data analysis module;

[0031] The wind turbine generator set data acquisition module includes: an anemometer, a wind vane, and a temperature sensor on the wind turbine, which monitor the changes in wind speed and wind direction and detect the temperature of each component of the wind turbine generator set during operation;

[0032] The wind turbine generator set data processing module realizes the precise prediction of the wind direction and the automatic adjustment of the yaw angle by training a BP neural network model;

[0033] The wind turbine data analysis module, based on the prediction results of the BP neural network model, realizes the adjustment of the yaw angle of the wind turbine under different wind speeds and wind directions and sets the thresholds for different temperatures of each component of the system;

[0034] The wind turbine control system is responsible for receiving and processing the collected raw data, performing yaw, and detecting the temperatures of each component of the system.

[0035] The process by which the wind turbine data acquisition module, through an anemometer and a wind vane installed on the wind turbine, monitors the changes in wind speed and wind direction in real time includes:

[0036] The anemometer senses the magnitude of the wind through the propeller inside it and converts it into an electrical signal. The above electrical signal is proportional to the wind speed. When the wind speed increases, the electrical signal strengthens accordingly. When the wind speed decreases, the electrical signal weakens accordingly. The wind vane is used to sense the direction of the wind. It is a device that can rotate freely and contains a potentiometer inside. When the wind direction changes, the wind vane rotates accordingly, thereby generating a corresponding electrical signal. This signal represents the current wind direction. The collected wind speed and wind direction signals are converted into digital signals through analog-to-digital conversion.

[0037] The process by which the wind turbine data acquisition module detects the temperatures of each component of the wind turbine during operation through temperature sensors includes:

[0038] The temperature sensor senses the temperatures of the yaw positioning system gearbox, generator, and bearing through the thermosensitive element inside it. When the temperature changes, the resistance value of the thermosensitive element will change accordingly. This change is converted into an electrical signal, amplified, filtered, and converted into a digital signal through analog-to-digital conversion, and is transmitted to the control system of the wind turbine through a communication protocol.

[0039] The process by which the wind turbine data processing module inputs the collected data into the input layer of the BP neural network model includes:

[0040] Clean the collected data, remove noise and outliers, normalize the data so that it is in the same dimension and range, smooth the data to reduce the volatility and uncertainty of the data, construct a BP neural network model. The neural network model includes an input layer, a hidden layer, and an output layer. Use the historical data of wind speed, wind direction, and temperature as the input of the BP neural network to train the model so that it can learn the relationship between wind speed, wind direction and wind direction prediction and the correlation between the temperature of each component and yaw adjustment. The number of nodes in the input layer corresponds to the number of input features.

[0041] The process by which the wind turbine data processing module trains the hidden layer of the BP neural network model includes:

[0042] Neurons in the hidden layer process the input data through weighted summation and activation functions, extracting features related to wind direction prediction and yaw angle adjustment. These features include non-linear transformations of wind speed, wind direction, and temperature data. Since the problems of wind direction prediction and yaw angle adjustment are non-linear, neurons in the hidden layer introduce non-linear factors through the Sigmoid activation function, enabling the model to handle complex non-linear relationships. Each neuron in the hidden layer integrates information from the input layer through interconnection and collaboration to form a comprehensive understanding of wind direction and yaw angle adjustment.

[0043] The process of training the output layer of the BP neural network model by the wind turbine data processing module includes:

[0044] In the task of predicting the wind direction, a regression model is used to output continuous wind direction angle values. One neuron in the output layer is used to output the predicted wind direction angle value. After the output value of this neuron is transformed by the sigmoid activation function, it is the predicted wind direction angle. In the task of yaw angle adjustment, a classification model is used to output discrete adjustment instructions. Three neurons in the output layer correspond to three different adjustment instructions, which include turning left, turning right, and maintaining. After the output values of the neurons are transformed by the softmax function, a probability distribution is obtained, indicating the probability of each adjustment instruction. The system selects the adjustment instruction with the highest probability as the final output and sends it to the control system to perform yaw adjustment. The real-time collected data is input into the trained BP neural network model. The model calculates and outputs the predicted wind direction change and the health status of each component of the system according to the input data. The system calculates the yaw angle that needs to be adjusted according to the prediction result and the current operating state of the unit and generates a control instruction. The yaw system controller adjusts the yaw angle according to the control instruction to keep the wind turbine blades always facing the direction of the wind and maintain the yaw system temperature within the normal operating range.

[0045] The process of the wind turbine data analysis module realizing yaw angle adjustment under different wind speeds and wind directions based on the prediction results of the BP neural network model includes:

[0046] When the cut-in wind speed is below 3 m / s, the wind turbine cannot generate electricity effectively. At this time, the yaw system is in the standby state and does not perform yaw adjustment. When the wind speed gradually rises above the cut-in wind speed but is below the rated wind speed of 12 m / s, the yaw system adjusts the orientation of the wind turbine according to the data of the wind vane in real time. The BP neural network model predicts the wind direction change based on historical data and real-time data. When the wind speed reaches above the rated wind speed, the yaw system dynamically adjusts the yaw angle according to the changes in wind speed and wind direction and the operating state of the unit. When the cut-out wind speed is above 25 m / s, the wind turbine automatically disconnects from the grid and shuts down, and the yaw system adjusts the wind turbine to the side-wind position. In addition, when the wind direction changes significantly, the BP neural network model quickly predicts the new wind direction based on real-time data and controls the yaw system to continuously and smoothly adjust the orientation of the wind turbine.

[0047] The process of setting the thresholds for different temperatures of each component of the system by the wind turbine data analysis module based on the prediction results of the BP neural network model includes:

[0048] When the temperature of the gearbox of the wind turbine is between 30°C and 70°C, the system operates normally. When the gearbox temperature reaches 80°C, the system issues a high-temperature alarm and starts the heat sink installed outside the gearbox. When the gearbox temperature reaches 90°C, the wind turbine automatically shuts down. When the temperature of the generator of the wind turbine is between 60°C and 120°C, the system operates normally. When the generator temperature reaches 130°C, the system issues a high-temperature alarm and starts the cooling water circulation system inside the generator. When the generator temperature reaches 150°C, the wind turbine automatically shuts down. When the temperature of the bearing of the wind turbine is between 30°C and 70°C, the system operates normally. When the bearing temperature reaches 80°C, the system issues a high-temperature alarm, ensures that the lubricating grease is sufficient and clean, and adjusts the load and speed of the wind turbine. When the bearing temperature reaches 95°C, the wind turbine automatically shuts down. When the gearbox temperature drops to -20°C and below, the generator temperature drops to -10°C and below, and the bearing temperature drops to -15°C and below, if any of these three situations occurs, the system issues a low-temperature alarm and heats the gearbox, generator, and bearing by starting heaters to restore them to the normal temperature range, adjusts the blade angle to reduce the vibration and noise of the wind turbine caused by low temperature, and selects low-temperature lubricating oil with a lower freezing point and good fluidity for the low-temperature environment to ensure that all components of the system can still maintain good lubrication at low temperatures.

[0049] The wind turbine control system is responsible for receiving and processing the collected raw data. The process of performing yaw and detecting the temperature of each component of the system includes:

[0050] The control system receives the real-time monitoring data of wind speed, wind direction and temperature transmitted by the data acquisition module, uses the BP neural network model in the data processing module to process and analyze the received data, predicts the change of wind direction and calculates the required yaw angle. According to the processing results, the yaw angle of the wind turbine generator is adjusted through the actuator, so that the blades are always aligned with the wind direction, monitors the operating temperature of each component of the wind turbine generator, and takes corresponding protection measures when the temperature exceeds the normal range.

[0051] The usage method of this system:

[0052] First, use an anemometer, a wind vane and a temperature sensor to monitor the wind speed, wind direction and the operating temperature of each component of the wind turbine generator in real time. Subsequently, the data processing module receives these real-time data and uses the trained BP neural network model to accurately predict the wind direction. At the same time, the yaw angle is automatically adjusted according to the prediction results to ensure that the component temperature of the wind turbine generator is within the normal range. Then, the data analysis module further optimizes the yaw angle according to the prediction results of the BP neural network for different wind speed and wind direction conditions, and sets corresponding protection thresholds according to the component temperature. Finally, the control system receives all the original data, performs the yaw operation, and continuously monitors the component temperature. Once an abnormality is found, protection measures are immediately taken to ensure that the wind turbine generator can operate efficiently and safely.

[0053] It should be noted that in this article, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or also includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising a..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the element.

[0054] Although the embodiments of the present invention have been shown and described, for those of ordinary skill in the art, it can be understood that various changes, modifications, substitutions and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An automatic control yaw positioning system for a wind turbine generator, characterized in that: It includes a wind turbine control system, which is communicatively connected to a wind turbine data acquisition module, a wind turbine data processing module, and a wind turbine data analysis module; The wind turbine data acquisition module includes: an anemometer, a wind vane, and a temperature sensor on the wind turbine, which monitor the changes in wind speed and direction and detect the temperature of each component of the wind turbine during operation; The wind turbine data processing module realizes the accurate prediction of the wind direction and the automatic adjustment of the yaw angle by training a BP neural network model; The wind turbine data analysis module, based on the prediction results of the BP neural network model, realizes the yaw angle adjustment of the wind turbine under different wind speeds and wind directions and sets the thresholds under different temperatures of each component of the system; The wind turbine control system is responsible for receiving and processing the collected raw data, performing yaw, and detecting the temperature of each component of the system; The process by which the wind turbine data acquisition module, through the anemometer and wind vane installed on the wind turbine, monitors the changes in wind speed and direction in real time includes: The anemometer senses the magnitude of the wind through the propeller inside it and converts it into an electrical signal. The above electrical signal is proportional to the wind speed. When the wind speed increases, the electrical signal strengthens accordingly. When the wind speed decreases, the electrical signal weakens accordingly. The wind vane is used to sense the direction of the wind. It is a device that can rotate freely and contains a potentiometer inside. When the wind direction changes, the wind vane rotates accordingly, generating a corresponding electrical signal, which represents the current wind direction. The collected wind speed and wind direction signals are converted into digital signals through analog-to-digital conversion; The process by which the wind turbine data acquisition module, through the temperature sensor, detects the temperature of each component of the wind turbine during operation includes: The temperature sensor senses the temperature of the yaw positioning system gearbox, generator, and bearing through the thermosensitive element inside it. When the temperature changes, the resistance value of the thermosensitive element will change accordingly. This change is converted into an electrical signal, amplified, filtered, and then converted into a digital signal through analog-to-digital conversion, and is transmitted to the control system of the wind turbine through a communication protocol; The process by which the wind turbine data processing module inputs the collected data into the input layer of the BP neural network model includes: Clean the collected data, remove noise and outliers, normalize the data so that it is in the same dimension and range, smooth the data to reduce the volatility and uncertainty of the data, construct a BP neural network model, which includes an input layer, a hidden layer, and an output layer. Use the historical data of wind speed, wind direction, and temperature as the input of the BP neural network to train the model so that it can learn the relationship between wind speed, wind direction and wind direction prediction, as well as the correlation between the temperature of each component and yaw adjustment. The number of nodes in the input layer corresponds to the number of input features.

2. An automatic control yaw positioning system for a wind turbine generator according to claim 1, characterized in that: The process by which the wind turbine data processing module trains the hidden layer of the BP neural network model includes: The neurons in the hidden layer process the input data through weighted summation and activation functions, extracting features related to wind direction prediction and yaw angle adjustment. These features include non-linear transformations of wind speed, wind direction, and temperature data. Since the wind direction prediction and yaw angle adjustment problems are non-linear, the neurons in the hidden layer introduce non-linear factors through the Sigmoid activation function, enabling the model to handle complex non-linear relationships. The neurons in the hidden layer integrate the information from the input layer through interconnection and collaboration, forming a comprehensive understanding of wind direction and yaw angle adjustment.

3. An automatic control yaw positioning system for a wind turbine according to claim 2, characterized in that: The process of training the output layer of the BP neural network model by the wind turbine data processing module includes: In the task of predicting the wind direction, a regression model is used to output continuous wind direction angle values. One neuron in the output layer is used to output the predicted wind direction angle value. After the output value of this neuron is transformed by the sigmoid activation function, it is the predicted wind direction angle. In the task of yaw angle adjustment, a classification model is used to output discrete adjustment instructions. Three neurons in the output layer correspond to three different adjustment instructions, which include turning left, turning right, and maintaining. After the output values of the neurons are transformed by the softmax function, a probability distribution is obtained, indicating the probability of each adjustment instruction. The system selects the adjustment instruction with the highest probability as the final output and sends it to the control system to perform yaw adjustment. The real-time collected data is input into the trained BP neural network model. The model calculates and outputs the predicted wind direction change and the health status of each component of the system according to the input data. The system calculates the yaw angle that needs to be adjusted based on the prediction result and the current operating state of the unit, and generates a control instruction. The yaw system controller adjusts the yaw angle according to the control instruction, so that the wind turbine blades always face the direction of the wind and keep the yaw system temperature within the normal operating range.

4. An automatic control yaw positioning system for a wind turbine generator according to claim 3, characterized in that: The process of the wind turbine data analysis module realizing yaw angle adjustment under different wind speeds and wind directions based on the prediction results of the BP neural network model includes: When the cut-in wind speed is below 3 m / s, the wind turbine cannot generate electricity effectively. At this time, the yaw system is in a standby state and no yaw adjustment is performed. When the wind speed gradually rises above the cut-in wind speed but below the rated wind speed of 12 m / s, the yaw system adjusts the wind turbine rotor orientation in real time according to the data of the wind vane. The BP neural network model predicts the wind direction change based on historical data and real-time data. When the wind speed reaches above the rated wind speed, the yaw system dynamically adjusts the yaw angle according to the changes in wind speed and wind direction and the operating state of the unit. In the case where the cut-out wind speed is above 25 m / s, the wind turbine automatically disconnects from the grid and shuts down, and the yaw system adjusts the wind turbine rotor to the side-wind position. In addition, when the wind direction changes significantly, the BP neural network model quickly predicts the new wind direction based on real-time data and controls the yaw system to continuously and smoothly adjust the wind turbine rotor orientation.

5. An automatic control yaw positioning system for a wind turbine generator according to claim 4, characterized in that: The process of the wind turbine data analysis module setting thresholds for different temperatures of each component of the system based on the prediction results of the BP neural network model includes: When the gearbox temperature of the wind turbine is between 30°C and 70°C, the system works normally. When the gearbox temperature reaches 80°C, the system issues a high-temperature alarm and starts the radiator installed outside the gearbox. When the gearbox temperature reaches 90°C, the wind turbine shuts down automatically. When the generator temperature of the wind turbine is between 60°C and 120°C, the system works normally. When the generator temperature reaches 130°C, the system issues a high-temperature alarm and starts the cooling water circulation system inside the generator. When the generator temperature reaches 150°C, the wind turbine shuts down automatically. When the bearing temperature of the wind turbine is between 30°C and 70°C, the system works normally. When the bearing temperature reaches 80°C, the system issues a high-temperature alarm, ensures that the lubricating grease is sufficient and clean, adjusts the load and speed of the wind turbine. When the bearing temperature reaches 95°C, the wind turbine shuts down automatically. When the gearbox temperature drops to -20°C or below, the generator temperature drops to -10°C or below, and the bearing temperature drops to -15°C or below, if any of the above three situations occurs, the system issues a low-temperature alarm and heats the gearbox, generator, and bearing by starting the heater to restore them to the normal temperature range, adjusts the blade angle to reduce the vibration and noise of the wind turbine caused by low temperature, and selects a low-temperature lubricating oil with a lower freezing point and good fluidity for the low-temperature environment to ensure that all components of the system can still maintain good lubrication at low temperatures.

6. An automatic control yaw positioning system for a wind turbine generator according to claim 5, characterized in that: The control system of the wind turbine is responsible for receiving and processing the collected raw data. The process of performing yaw and detecting the temperature of each component of the system includes: The control system receives the real-time monitoring data of wind speed, wind direction, and temperature transmitted by the data acquisition module, processes and analyzes the received data using the BP neural network model in the data processing module, predicts the change of wind direction and calculates the required yaw angle, and adjusts the yaw angle of the wind turbine through the actuator according to the processing result to make the blades always face the direction of the wind, monitors the operating temperature of each component of the wind turbine, and takes corresponding protection measures when the temperature exceeds the normal range.

Images