A wind power variable pitch control system and a wind power variable pitch system

Abstract

The application discloses a kind of wind power variable pitch control system and wind power variable pitch system, belong to wind power variable pitch control system technical field, is by intelligent optimization module, multistage blade control module, active noise control module, wind energy risk assessment module, internet of things and cloud platform module, high temperature adaptation module, friction damping technology module, active variable pitch control module, multimode blade regulation module composition.The application, using recurrent neural network and the intelligent optimization module of fuzzy logic improves wind speed prediction accuracy and blade angle adaptability.Multistage blade control module makes each blade can be independently controlled, improves flexibility and efficiency.Active noise control module reduces noise pollution, improves environmental friendliness.Internet of things and cloud platform module realizes centralized control and monitoring, improves efficiency and reduces cost.High temperature adaptation and friction damping technology module enhances system stability.Active variable pitch control and multimode blade regulation module improve responsiveness and adaptability.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of wind power variable pitch control system, and in particular, relates to a wind power variable pitch control system and a wind power variable pitch system. BACKGROUND

[0002] The wind power variable pitch control system is an important part of the wind power variable pitch system, which is used to adjust the blade angle of the wind turbine generator set to optimize wind energy conversion and output power of the wind turbine. The main function of the wind power variable pitch control system is to control the blade angle adjustment of the wind turbine generator set according to the real-time monitoring of wind speed and generator set operating state, so that the wind turbine can maintain stability and operate at the best efficiency under different wind speed conditions. The control system adjusts the wind energy capture and output power of the wind turbine by changing the blade angle to adapt to different wind speeds and load demands.

[0003] In the actual use process of the wind power variable pitch control system, the existing system usually uses a fixed model to predict wind speed. This method has poor prediction results when facing complex wind speed changes, and cannot achieve real-time optimization of blade angle settings. Secondly, most existing systems are passive in noise regulation, and the noise evaluation accuracy is insufficient, which may lead to excessive noise and affect the surrounding environment. Furthermore, the existing system is complicated and inefficient when dealing with multiple wind turbine generator control. In the face of extreme high temperature environment, the stability of the existing wind power control system is poor, which cannot guarantee high-quality output. Moreover, the stability control of the blade angle is not accurate enough, which further affects the overall stability and energy efficiency. Finally, the existing system lacks responsiveness and adaptability to the environment, which affects the ability to fully utilize wind energy resources.

[0004] Therefore, the present application is proposed. SUMMARY

[0005] To solve the above technical problems, the basic idea of the technical solution of the present application is as follows:

[0006] A wind power variable pitch control system is composed of an intelligent optimization module, a multi-stage blade control module, an active noise control module, a wind energy risk assessment module, an Internet of Things and cloud platform module, a high temperature adaptation module, a friction damping technology module, an active variable pitch control module, and a multi-modal blade regulation module.

[0007] The intelligent optimization module uses recurrent neural network and fuzzy logic method to predict wind speed, optimize blade angle setting and output power, and output wind speed prediction and blade optimization report.

[0008] The multi-stage blade control module independently controls the angle of each blade, inputs the wind speed prediction and blade optimization report for deep reinforcement learning optimization, and generates an independent blade angle regulation report.

[0009] The active noise control module detects and regulates noise through signal processing technology and fuzzy logic, adjusts blade angle and rotation speed to reduce noise, and generates a noise reduction report.

[0010] The wind energy risk assessment module performs wind energy resource assessment and risk analysis, and outputs a wind energy resource and risk analysis report.

[0011] The Internet of Things and cloud platform module realizes centralized control and monitoring of multiple wind turbine generators, and outputs a wind turbine remote control report.

[0012] The high-temperature adaptation module ensures stable operation of the system in high-temperature environments, and outputs a high-temperature adaptability report.

[0013] The friction damping technology module provides precise blade angle control, and outputs a blade angle stability report.

[0014] The active variable pitch control module senses and responds to the environment through active materials, and outputs an active response regulation report.

[0015] The multi-modal blade control module selects the appropriate blade control mode according to the wind field conditions, uses neural networks and genetic algorithms, and outputs a multi-modal blade control report.

[0016] As a further scheme of the present application: the intelligent optimization module includes a wind speed prediction unit, a blade angle optimization unit, and an output power optimization unit.

[0017] The wind speed prediction unit uses a recurrent neural network to predict wind speed, collects historical wind speed data, prepares data, builds a recurrent neural network model, and trains and validates the model.

[0018] The blade angle optimization unit optimizes the blade angle using fuzzy logic, converts the input wind speed and power requirements into blade angle adjustment strategies through fuzzy rules, fuzzy reasoning, and fuzzy controller design, and realizes stable and optimized output through feedback tuning.

[0019] The output power optimization unit adjusts the output power of the wind turbine according to wind speed and blade angle prediction to maximize power generation efficiency, establishes a power model, formulates a power optimization strategy for real-time adjustment, and obtains the best output power adjustment strategy.

[0020] As a further scheme of the present application: the multi-stage blade control module includes a blade angle adjustment unit, a deep learning optimization unit, and a blade control report generation unit.

[0021] The paddle angle adjusting unit adopts a PID control algorithm and a fuzzy logic control algorithm, calculates the angle that each paddle should be adjusted according to the current wind speed and power demand, and independently adjusts the angle of each paddle;

[0022] The deep learning optimization unit learns the optimal paddle angle adjustment strategy through interaction and training with the environment, optimizes the adjustment of the paddle angle by using a deep reinforcement learning method according to real-time wind speed and power demand, and dynamically adjusts the angle of the paddle to maximize the efficiency of the wind turbine generator;

[0023] The paddle control report generation unit records the real-time adjustment history of the paddle angle, the power output condition, and the system operation state information, and generates an independent control report for each paddle.

[0024] As a further scheme of the present application, the active noise control module includes a noise detection unit, a noise control unit, and a noise reduction strategy generation unit.

[0025] The noise detection unit detects noise by using signal processing technology, identifies and quantifies the characteristics of noise by using spectrum analysis, time domain analysis, and statistical analysis algorithms.

[0026] The noise control unit adjusts noise by using a fuzzy logic method, determines a noise control strategy based on fuzzy rules and fuzzy reasoning.

[0027] The noise reduction strategy generation unit generates a noise reduction scheme in combination with the results of the noise detection unit and the noise control unit.

[0028] As a further scheme of the present application, the wind energy risk assessment module includes a wind energy resource assessment unit and a risk analysis unit.

[0029] The wind energy resource assessment unit calculates the distribution of wind energy resources in the entire region and calculates indicators by using interpolation algorithms and statistical analysis algorithms, assesses the wind energy resources in a specific region or project by analyzing wind energy resource data, and provides quantitative assessment of wind energy resources.

[0030] The wind energy project is quantified and evaluated by using sensitivity analysis algorithms and risk evaluation algorithms, referring to geographical conditions, climate change, and wind variability factors.

[0031] As a further scheme of the present application, the Internet of Things and cloud platform module includes a centralized control unit, a remote monitoring unit, and a cloud platform data processing unit.

[0032] The centralized control unit applies optimization control and adaptive control algorithms to centrally control multiple wind turbine generators.

[0033] The remote monitoring unit collects wind turbine data, adopts a data collection optimization algorithm, an anomaly detection algorithm and a fault diagnosis algorithm to realize data monitoring and early warning.

[0034] The cloud platform data processing unit uses big data analysis, prediction and early warning algorithms to deeply analyze and process the wind turbine data.

[0035] As a further scheme of the application, the high-temperature adaptation module includes a high-temperature environment detection unit and a stable operation strategy generation unit.

[0036] The high-temperature environment detection unit collects environmental temperature data in real time through a temperature sensor, including a temperature threshold judgment algorithm, a temperature trend analysis algorithm and a temperature sensor data calibration algorithm.

[0037] The stable operation strategy generation unit receives environmental temperature data, adjusts the blade angle and rotor speed parameters to prevent system overheating according to the current environmental temperature and power curve data using a power adjustment algorithm, and selects a fault handling strategy according to the fault detection data and temperature information in the high-temperature environment using a fault handling strategy algorithm.

[0038] As a further scheme of the application, the friction damping technology module includes a damping detection unit and an angle stability strategy generation unit.

[0039] The damping detection unit uses vibration analysis and frequency spectrum analysis methods to monitor the blade friction damping state in real time and outputs a friction damping report.

[0040] The angle stability strategy generation unit adjusts the angle according to the friction damping report and a PID control algorithm, stably adjusts the blade angle, and generates a blade angle stability strategy.

[0041] The active variable pitch control module includes an environment perception unit and a blade regulation response unit.

[0042] The environment perception unit uses active materials and a sensor network to perceive wind speed and humidity parameters in the environment and generates an environment perception report.

[0043] The blade regulation response unit uses a deep learning algorithm to regulate the blades based on the environment perception report, adaptively adjusts the blade angle and position, and generates a blade regulation strategy.

[0044] As a further scheme of the application, the multi-modal blade regulation module includes a blade mode selection unit, a neural network optimization unit and a genetic algorithm optimization unit.

[0045] The blade mode selection unit uses data-driven discriminant analysis to select a blade regulation mode according to wind field conditions and determines blade regulation mode selection.

[0046] The neural network optimization unit uses a convolutional neural network to optimize the paddle control mode selection, optimizes the paddle control mode selection in real time, and generates a neural network optimization result;

[0047] The genetic algorithm optimization unit uses a genetic algorithm to perform secondary optimization based on the neural network optimization result, automatically adjusts the paddle parameters to achieve optimal efficiency, and generates a final paddle control strategy.

[0048] A wind power variable pitch system controlled by a wind power variable pitch control system, the wind power variable pitch system is composed of a wind energy harvesting module, a power conversion and optimization module, an energy storage and safety module, and an electric energy output and distribution module.

[0049] The wind energy harvesting module collects wind energy in real time and converts it into primary mechanical energy, uses wind speed and blade angle data, and calculates wind energy utilization rate based on air density and blade radius parameters, and outputs a primary mechanical energy report.

[0050] The power conversion and optimization module applies electromagnetic induction principle and PID control algorithm for energy conversion and optimization, converts mechanical energy in the primary mechanical energy report into electrical energy, and optimizes energy according to the paddle control strategy, and outputs a primary electrical energy report.

[0051] The energy storage and safety module receives the primary electrical energy report, performs safety control based on the charge and discharge algorithm of the battery, and combines risk analysis data to generate a safety energy storage report.

[0052] The electric energy output and distribution module uses smart grid management and load forecasting algorithm, outputs and distributes electric energy according to the safety energy storage report, and generates an electric energy distribution completion report.

[0053] Advantages:

[0054] The intelligent optimization module using recurrent neural network and fuzzy logic improves the accuracy of wind speed prediction and the adaptability of blade angle setting, thereby increasing the overall energy efficiency of the system. The application of the multi-stage blade control module enables the angle of each blade to be independently controlled, improving flexibility and efficiency. Through the active noise control module, the system is more proactive and accurate in noise regulation, reducing noise pollution and improving environmental friendliness. Using the Internet of Things and cloud platform module, centralized control and monitoring of multiple wind turbine generators can be achieved, improving efficiency and reducing labor costs. The system's ability to operate stably in high-temperature environments makes it more adaptable and can maintain stable and efficient output in different environments. The friction damping technology module provides precise support for blade angle control, improving system stability. The active variable pitch control module and multi-modal blade regulation module significantly improve the responsiveness and adaptability of the system, enabling it to better cope with various wind conditions.

[0055] The specific embodiments of the application will be further described in detail below with reference to the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0056] In the drawings:

[0057] Figure 1 Flowchart of the wind power variable pitch control system of the present application;

[0058] Figure 2 Flowchart of the intelligent optimization module of the present application;

[0059] Figure 3 Flowchart of the multi-stage blade control module of the present application;

[0060] Figure 4 Flowchart of the active noise control module of the present application;

[0061] Figure 5 Flowchart of the wind energy risk assessment module of the present application;

[0062] Figure 6 Flowchart of the Internet of Things and cloud platform module of the present application;

[0063] Figure 7 Flowchart of the high-temperature adaptation module of the present application;

[0064] Figure 8 Flowchart of the friction damping technology module of the present application;

[0065] Figure 9 Flowchart of the active variable pitch control module of the present application;

[0066] Figure 10 Flowchart of the multi-modal blade regulation module of the present application;

[0067] Figure 11A flow chart of a wind power variable pitch system of the present application. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments will be described clearly and completely below with reference to the drawings in the embodiments of the present application. The following embodiments are used to illustrate the present application.

[0069] Please refer to Figure 1 A wind power variable pitch control system is composed of an intelligent optimization module, a multi-stage blade control module, an active noise control module, a wind energy risk assessment module, an Internet of Things and cloud platform module, a high-temperature adaptation module, a friction damping technology module, an active variable pitch control module, and a multi-modal blade regulation module.

[0070] The intelligent optimization module uses a recurrent neural network and a fuzzy logic method to predict wind speed, optimize blade angle settings and output power, output wind speed prediction and blade optimization reports.

[0071] The multi-stage blade control module independently controls the angle of each blade, inputs the wind speed prediction and blade optimization report for deep reinforcement learning optimization, and generates an independent blade angle regulation report.

[0072] The active noise control module detects and regulates noise through signal processing technology and fuzzy logic, adjusts the blade angle and speed to reduce noise, and generates a noise reduction report.

[0073] The wind energy risk assessment module performs wind energy resource assessment and risk analysis, and outputs a wind energy resource and risk analysis report.

[0074] The Internet of Things and cloud platform module realizes centralized control and monitoring of multiple wind turbine generators, and outputs a wind turbine generator remote control report.

[0075] The high-temperature adaptation module ensures stable operation of the system in a high-temperature environment, and outputs a high-temperature adaptability report.

[0076] The friction damping technology module provides precise blade angle control, and outputs a blade angle stability report.

[0077] The active variable pitch control module senses and responds to the environment through active materials, and outputs an active response regulation report.

[0078] The multi-modal blade regulation module selects a suitable blade regulation mode according to the wind field conditions, uses a neural network and a genetic algorithm, and outputs a multi-modal blade control report.

[0079] The wind power variable pitch control system is composed of intelligent optimization module, multi-stage blade control module, active noise control module, wind energy risk assessment module, Internet of Things and cloud platform module, high temperature adaptation module, friction damping technology module, active variable pitch control module and multi-modal blade regulation module. The system uses recurrent neural network and fuzzy logic method for wind speed prediction and blade angle optimization, independently controls the blade angle, and optimizes through deep reinforcement learning. The active noise control module detects and regulates noise, and the wind energy risk assessment module assesses resources and analyzes risks. The Internet of Things and cloud platform realizes centralized control and monitoring, and the high temperature adaptation module ensures the stable operation of the system in high temperature environment. The friction damping technology provides accurate blade angle control, the active variable pitch control module realizes active regulation by sensing and responding to the environment, and the multi-modal blade regulation module selects the most suitable mode according to the wind field conditions. The benefits of the overall system include improving power generation efficiency, reducing noise, assessing wind energy resources and risks, remote control, adapting to high temperature environment, etc., providing a more intelligent, efficient and reliable control solution for the wind power industry.

[0080] Please refer to Figure 2 The intelligent optimization module includes wind speed prediction unit, blade angle optimization unit and output power optimization unit.

[0081] The wind speed prediction unit uses recurrent neural network for wind speed prediction, collects historical wind speed data, prepares data, builds recurrent neural network model, trains and validates the model.

[0082] The blade angle optimization unit uses fuzzy logic method to optimize blade angle, defines fuzzy rules, performs fuzzy reasoning, designs fuzzy controller, converts input wind speed and power requirements into blade angle adjustment strategy, and realizes stable and optimized output through feedback tuning.

[0083] The output power optimization unit adjusts the output power of the wind turbine according to the wind speed and blade angle prediction to maximize power generation benefit, establishes power model, formulates power optimization strategy for real-time adjustment, and obtains the best output power adjustment strategy.

[0084] The wind speed prediction unit uses recurrent neural network for accurate wind speed prediction, trains and validates the model through historical data, and provides prediction information of future wind speed for the system. The blade angle optimization unit uses fuzzy logic method to optimize blade angle, converts input wind speed and power requirements into blade angle adjustment strategy, and realizes feedback tuning to stabilize and optimize output. The output power optimization unit adjusts the output power of the wind turbine according to the wind speed and blade angle prediction, and realizes maximum power generation benefit through the establishment of power model and the formulation of optimization strategy.

[0085] Please refer to Figure 3, the multi-stage blade control module includes a blade angle adjustment unit, a deep learning optimization unit, and a blade regulation report generation unit;

[0086] The blade angle adjustment unit adopts a PID control algorithm and a fuzzy logic control algorithm to calculate the angle that each blade should adjust according to the current wind speed and power demand, and independently adjusts the angle of each blade.

[0087] The deep learning optimization unit learns the optimal blade angle adjustment strategy through interaction and training with the environment, and optimizes the adjustment of the blade angle using a deep reinforcement learning method according to real-time wind speed and power demand, dynamically adjusting the angle of the blade to maximize the efficiency of the wind turbine.

[0088] The blade regulation report generation unit records the real-time adjustment history of the blade angle, power output, and system operating state information, and generates an independent regulation report for each blade.

[0089] First, the blade angle adjustment unit adopts a PID control algorithm and a fuzzy logic control algorithm to independently adjust the angle of each blade according to real-time wind speed and power demand. This precise blade control can maximize the capture of wind energy, improve the efficiency of the wind turbine, and thus increase the energy production and power generation of the system. Second, the deep learning optimization unit uses a deep reinforcement learning method to learn the optimal blade angle adjustment strategy through interaction and training with the environment. This intelligent optimization can dynamically adjust the blade angle according to real-time wind speed and power demand, maximizing the efficiency of the wind turbine. Through learning and optimization, the system can adapt to different wind field conditions, making the wind power system more adaptable and stable. In addition, the blade regulation report generation unit records the real-time adjustment history of the blade angle, power output, and system operating state information, and generates an independent regulation report for each blade. Such a report provides a detailed analysis of the performance of the blade angle control and the operating status of the system, which helps to monitor and evaluate the performance of the system, and provides valuable reference for system improvement and optimization.

[0090] Please refer to Figure 4 , the active noise control module includes a noise detection unit, a noise regulation unit, and a noise reduction strategy generation unit.

[0091] The noise detection unit detects noise using signal processing technology, and identifies and quantifies the characteristics of noise through frequency spectrum analysis, time domain analysis, and statistical analysis algorithms.

[0092] The noise regulation unit adjusts noise through fuzzy logic methods, determines noise regulation strategies based on fuzzy rules and fuzzy reasoning.

[0093] The noise reduction strategy generation unit combines the results of the noise detection unit and the noise regulation unit to generate a noise reduction plan.

[0094] The noise detection unit utilizes signal processing techniques to detect noise in the environment. Through frequency spectrum analysis, time domain analysis, and statistical analysis algorithms, this unit can identify and quantify the characteristics of noise. By accurately analyzing and measuring noise, the system can understand its frequency distribution and intensity, and assess it. The noise regulation unit utilizes fuzzy logic methods for noise regulation. Based on predefined fuzzy rules and fuzzy inference mechanisms, this unit can determine noise regulation strategies. Through the judgment and reasoning of fuzzy logic, noise control parameters can be automatically adjusted according to noise detection results and set rules, achieving active regulation of noise. The noise reduction strategy generation unit integrates the results of the noise detection unit and the noise regulation unit to generate a noise reduction plan. Based on noise detection data and strategies provided by the noise regulation unit, this unit can intelligently generate adaptive noise reduction plans. By selecting appropriate technical means and control strategies, the system can reduce the impact of noise for different noise sources and environmental conditions.

[0095] Please refer to Figure 5 , the wind energy risk assessment module includes a wind energy resource assessment unit and a risk analysis unit;

[0096] The wind energy resource assessment unit utilizes interpolation algorithms and statistical analysis algorithms to calculate the wind energy resource distribution of the entire region and calculate relevant indicators. By analyzing wind energy resource data, this unit can quantitatively assess the wind energy resource situation of a specific region or project, providing quantitative assessment of wind energy resources.

[0097] Using sensitivity analysis algorithms and risk evaluation algorithms, and referring to geographical conditions, climate change, and wind variability factors, the potential risks of wind energy projects are quantified and evaluated.

[0098] The wind energy resource assessment unit utilizes interpolation algorithms and statistical analysis algorithms to calculate the wind energy resource distribution of the entire region and calculate relevant indicators. By analyzing wind energy resource data, this unit can quantitatively assess the wind energy resource situation of a specific region or project. Such assessment can provide reliable basis for the planning and construction of wind power projects, helping to determine the best wind power site and select appropriate wind turbine units. The risk analysis unit uses sensitivity analysis algorithms and risk evaluation algorithms, taking into account geographical conditions, climate change, and wind variability factors, to quantify and evaluate the potential risks of wind energy projects. By considering and analyzing various risk factors, this unit can identify risks that may affect wind power projects and provide corresponding evaluation results. Such evaluation helps to control and respond to risks of wind power projects, improving the feasibility and sustainability of the project.

[0099] Please refer toFigure 6 The Internet of Things and cloud platform module includes a centralized control unit, a remote monitoring unit, and a cloud platform data processing unit.

[0100] The centralized control unit applies optimization control and adaptive control algorithms to centrally control multiple wind turbine generators.

[0101] The remote monitoring unit collects wind turbine generator data, uses data collection optimization algorithms, anomaly detection algorithms, and fault diagnosis algorithms to achieve data monitoring and early warning.

[0102] The cloud platform data processing unit uses big data analysis, prediction, and early warning algorithms to deeply analyze and process wind turbine generator data.

[0103] The centralized control unit applies optimization control and adaptive control algorithms to centrally control multiple wind turbine generators. This unit can coordinate and manage each unit, optimizing the operation state of the wind power generation system. Through centralized control, power regulation, load balancing, and fault handling can be achieved, improving the overall efficiency and reliability of wind power generation. The remote monitoring unit is responsible for collecting wind turbine generator data and using data collection optimization algorithms, anomaly detection algorithms, and fault diagnosis algorithms for data monitoring and early warning. Through real-time monitoring and analysis of wind turbine generator data, this unit can timely detect and warn potential anomalies or faults, improving the monitoring and maintenance efficiency of the wind power generation system and reducing the impact of faults on system operation. The cloud platform data processing unit uses big data analysis, prediction, and early warning algorithms to deeply analyze and process wind turbine generator data. This unit can process large amounts of data and use algorithms for data mining and pattern recognition. Through data analysis and prediction, it can provide detailed data reports, operation recommendations, and early warning information to help managers make timely decisions and optimize operation strategies.

[0104] Please refer to Figure 7 The high-temperature adaptation module includes a high-temperature environment detection unit and a stable operation strategy generation unit.

[0105] The high-temperature environment detection unit collects real-time environmental temperature data through temperature sensors, including temperature threshold judgment algorithms, temperature trend analysis algorithms, and temperature sensor data calibration algorithms.

[0106] The stable operation strategy generation unit receives environmental temperature data, adjusts blade angle and rotor speed parameters to prevent system overheating according to current environmental temperature and power curve data using power adjustment algorithms, and selects fault handling strategies based on fault detection data and temperature information in high-temperature environments using fault handling strategy algorithms.

[0107] The high-temperature environment detection unit collects real-time environmental temperature data through temperature sensors and processes them using temperature threshold judgment algorithms, temperature trend analysis algorithms, and temperature sensor data calibration algorithms. Through these algorithms and methods, the temperature situation in a high-temperature environment can be accurately monitored and evaluated. Such real-time temperature data and analysis results provide an important basis for the subsequent operation strategy generation of the high-temperature adaptation module. The stable operation strategy generation unit receives environmental temperature data provided by the high-temperature environment detection unit and, based on this data, applies power adjustment algorithms to adjust the blade angle and rotor speed parameters of the wind power generation system to prevent overheating. This unit also uses fault handling strategy algorithms to select appropriate fault handling strategies based on fault detection data and temperature information in a high-temperature environment. By adjusting the angle, speed, and taking appropriate fault handling strategies, this unit can ensure stable operation of the system in a high-temperature environment and reduce the risk of system overheating.

[0108] Please refer to Figure 8 , the friction damping technology module includes a damping detection unit, an angle stability strategy generation unit;

[0109] The damping detection unit uses vibration analysis and frequency spectrum analysis methods to monitor the blade friction damping state in real time and outputs a friction damping report.

[0110] The angle stability strategy generation unit adjusts the angle based on the friction damping report and PID control algorithm, and generates a blade angle stability strategy.

[0111] The damping detection unit uses vibration analysis and frequency spectrum analysis methods to monitor the blade friction damping state in real time and outputs a friction damping report. This unit can accurately evaluate the friction damping condition of the blade by analyzing the vibration characteristics and frequency spectrum information of the blade. By monitoring the friction damping state of the blade, friction damping abnormalities can be detected in a timely manner, providing real-time monitoring results and friction damping reports. The angle stability strategy generation unit adjusts the angle of the blade based on the friction damping report and PID control algorithm, and generates a blade angle stability strategy. Based on the information in the friction damping report, this unit combines the PID control algorithm to adjust the angle of the blade to a stable state. Through stable adjustment of the blade angle, the efficiency and reliability of the wind power generation system can be improved, the friction between the blade and the wind can be reduced, and energy loss can be reduced.

[0112] Please refer to Figure 9 , the active variable pitch control module includes an environment perception unit and a blade control response unit.

[0113] The environment perception unit uses active materials and sensor networks to perceive wind speed and humidity parameters in the environment and generates an environment perception report.

[0114] The paddle regulation response unit uses deep learning algorithms for paddle regulation based on the environmental perception report, adaptively adjusts the paddle angle and position, and generates a paddle regulation strategy.

[0115] The environmental perception unit uses active materials and sensor networks to perceive wind speed, humidity, and other parameters in the environment and generates a detailed environmental perception report. Through the application of active materials and sensor networks, this unit can accurately perceive the environmental conditions of the wind power generation system. The environmental perception report provides important information about environmental parameters such as wind speed and humidity, providing a basis for subsequent paddle regulation. The paddle regulation response unit uses deep learning algorithms for paddle regulation based on the environmental perception report, adaptively adjusts the paddle angle and position, and generates a paddle regulation strategy. This unit uses deep learning algorithms to process data in the environmental perception report and intelligently adjusts the angle and position of the paddle based on model learning and optimization to optimize the performance of the wind power generation system. By adaptively regulating the paddle, the system's power generation efficiency and output stability can be improved, adapting to changes in different environmental conditions.

[0116] Please refer to Figure 10 , the multi-modal paddle regulation module includes a paddle mode selection unit, a neural network optimization unit, and a genetic algorithm optimization unit.

[0117] The paddle mode selection unit uses data-driven discriminant analysis to select the paddle regulation mode based on wind field conditions and determines the paddle regulation mode selection.

[0118] The neural network optimization unit uses convolutional neural networks for optimization based on paddle regulation mode selection, performs real-time optimization of paddle regulation mode selection, and generates neural network optimization results.

[0119] The genetic algorithm optimization unit uses genetic algorithms for secondary optimization based on neural network optimization results, automatically adjusts paddle parameters to achieve optimal performance, and generates the final paddle regulation strategy.

[0120] The blade mode selection unit utilizes a data-driven discriminant analysis method to select the optimal blade regulation mode based on wind field conditions, determining the selection of the blade regulation mode. By analyzing wind field conditions and other relevant factors, this unit can intelligently select the blade regulation mode that is suitable for the current environment, thereby achieving flexible and efficient blade regulation. The neural network optimization unit utilizes a convolutional neural network for real-time optimization based on the selection of the blade regulation mode. Through neural network optimization, the blade regulation mode can be optimized and adjusted in real time. The neural network is trained and learned using existing data to provide optimal guidance for different blade modes, maximizing the power output and performance stability of the wind power generation system. The genetic algorithm optimization unit uses genetic algorithms for secondary optimization based on the results of neural network optimization. Genetic algorithms can generate new combinations of blade control parameters by simulating the evolutionary process and using a fitness function to evaluate their performance, thereby finding the optimal blade parameter configuration. This process can automatically adjust the blade parameters to achieve the best performance of the system, improving the energy utilization rate and economic benefits of the wind power generation system.

[0121] Please refer to Figure 11 A wind power variable pitch system is controlled by a wind power variable pitch control system, and the wind power variable pitch system is composed of a wind energy collection module, a power conversion and optimization module, an energy storage and safety module, and an electric energy output and distribution module.

[0122] The wind energy collection module collects wind energy in real time and converts the wind energy into primary mechanical energy. Using wind speed and blade angle data, the wind energy utilization rate is calculated based on parameters such as air density and blade radius, and a primary mechanical energy report is output.

[0123] The power conversion and optimization module applies electromagnetic induction principles and PID control algorithms for energy conversion and optimization, converting the mechanical energy in the primary mechanical energy report into electrical energy, and optimizing the energy according to the blade regulation strategy, outputting a primary electrical energy report.

[0124] The energy storage and safety module receives the primary electrical energy report, performs safety control based on battery charge and discharge algorithms, and combines risk analysis data to generate a safety energy storage report.

[0125] The electric energy output and distribution module uses smart grid management and load forecasting algorithms to output and distribute electric energy based on the safety energy storage report, generating an electric energy distribution completion report.

[0126] The wind energy collection module collects wind energy in real time and converts it into primary mechanical energy, evaluates the effective utilization of wind energy resources by calculating the wind energy utilization rate and generating a primary mechanical energy report. The power conversion and optimization module converts mechanical energy into electrical energy using electromagnetic induction principles and PID control algorithms, optimizes energy, improves energy conversion efficiency, and outputs a primary electrical energy report. The energy storage and safety module controls safety through battery management and risk analysis data, realizes safe storage and release of electrical energy, and generates a safe energy storage report. The electrical energy output and distribution module uses smart grid management and load forecasting algorithms to effectively output and distribute electrical energy based on the safe energy storage report.

[0127] Working principle:

[0128] The intelligent optimization module uses recurrent neural networks and fuzzy logic methods to predict wind speed and optimize blade angle settings and output power, generating a wind speed prediction and blade optimization report. The multi-stage blade control module independently controls the angle of each blade, optimizes and regulates the angle of each blade according to the wind speed prediction and blade optimization report using deep reinforcement learning methods, and generates an independent blade angle regulation report. At the same time, the active noise control module detects and regulates noise through signal processing technology and fuzzy logic, reduces noise levels by adjusting blade angle and speed, and generates a noise reduction report. The wind energy risk assessment module evaluates and analyzes the risk of wind energy resources and outputs a wind energy resource and risk analysis report to assess the feasibility and risk level of wind power projects. The Internet of Things and cloud platform module realizes centralized control and monitoring of multiple wind turbine generators, performs remote monitoring through data acquisition, anomaly detection, and fault diagnosis algorithms, and generates a wind turbine generator remote control report. The high-temperature adaptation module ensures the stable operation of the wind power system in high-temperature environments, generates a high-temperature adaptability report through environmental temperature detection and stable operation strategies. The friction damping technology module provides precise blade angle control, generates a blade angle stability report through damping detection and angle stability strategies. The active variable pitch control module generates an active response regulation report by sensing the environment and responding to active materials, achieving the goal of adjusting the blade angle and position according to different environments. The multi-modal blade regulation module selects the appropriate blade regulation mode according to the wind field conditions, optimizes the blade control strategy using neural networks and genetic algorithms, and generates a multi-modal blade control report.

[0129] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above examples, and the above examples and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the claimed present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A wind turbine variable pitch control system, characterized by, The wind power variable pitch control system is composed of an intelligent optimization module, a multi-stage blade control module, an active noise control module, a wind energy risk assessment module, an Internet of Things and cloud platform module, a high-temperature adaptation module, a friction damping technology module, an active variable pitch control module, and a multi-modal blade control module. The intelligent optimization module uses a recurrent neural network and a fuzzy logic method to predict wind speed, optimize blade angle settings, and output power, and outputs a wind speed prediction and blade optimization report. The multi-stage blade control module independently controls the angle of each blade, inputs the wind speed prediction and blade optimization report for deep reinforcement learning optimization, and generates an independent blade angle control report. The active noise control module detects and controls noise through signal processing technology and fuzzy logic, adjusts the blade angle and speed to reduce noise, and generates a noise reduction report. The wind energy risk assessment module performs wind energy resource assessment and risk analysis, and outputs a wind energy resource and risk analysis report. The Internet of Things and cloud platform module enables centralized control and monitoring of multiple wind turbine generators, and outputs a wind turbine generator remote control report. The high-temperature adaptation module ensures stable operation of the system in high-temperature environments, and outputs a high-temperature adaptability report. The friction damping technology module provides precise blade angle control, and outputs a blade angle stability report. The active variable pitch control module senses and responds to the environment through active materials, and outputs an active response control report. The multi-modal blade control module selects the appropriate blade control mode based on wind field conditions, uses neural networks and genetic algorithms, and outputs a multi-modal blade control report. The intelligent optimization module includes a wind speed prediction unit, a blade angle optimization unit, and an output power optimization unit. The wind speed prediction unit uses a recurrent neural network to predict wind speed by collecting historical wind speed data, preparing the data, building a recurrent neural network model, and training and validating the model. The blade angle optimization unit uses a fuzzy logic method to optimize the blade angle by defining fuzzy rules, performing fuzzy reasoning, and designing a fuzzy controller to convert input wind speed and power requirements into blade angle adjustment strategies, and achieving stable and optimized output through feedback tuning. The output power optimization unit adjusts the output power of the wind turbine based on wind speed and blade angle prediction to maximize power generation efficiency by establishing a power model and developing a power optimization strategy for real-time adjustment to obtain the best output power adjustment strategy.

2. The wind power variable pitch control system of claim 1, wherein, The multi-stage blade control module includes a blade angle adjustment unit, a deep learning optimization unit, and a blade control report generation unit. The blade angle adjustment unit uses a PID control algorithm and a fuzzy logic control algorithm to calculate the angle each blade should adjust based on the current wind speed and power requirements, and independently adjusts the angle of each blade. The deep learning optimization unit learns the best blade angle adjustment strategy through interaction and training with the environment, and uses deep reinforcement learning methods to optimize blade angle adjustment based on real-time wind speed and power requirements to dynamically adjust the angle of the blades to maximize the efficiency of the wind turbine. The blade regulation report generation unit records the real-time adjustment history of the blade angle, the power output condition, and the system operation state information, and generates an independent regulation report for each blade.

3. The wind power variable pitch control system of claim 1, wherein, The active noise control module includes a noise detection unit, a noise regulation unit, and a noise reduction strategy generation unit. The noise detection unit detects noise using signal processing techniques, identifies and quantifies the characteristics of the noise through frequency spectrum analysis, time domain analysis, and statistical analysis algorithms. The noise regulation unit adjusts the noise through fuzzy logic methods, determines the noise regulation strategy based on fuzzy rules and fuzzy reasoning. The noise reduction strategy generation unit generates a noise reduction scheme based on the results of the noise detection unit and the noise regulation unit.

4. The wind power variable pitch control system of claim 1, wherein, The wind energy risk assessment module includes a wind energy resource assessment unit and a risk analysis unit. The wind energy resource assessment unit uses interpolation algorithms and statistical analysis algorithms to calculate the distribution of wind energy resources in the entire region and calculate indicators, assesses the wind energy resources in a specific area or project by analyzing wind energy resource data, and provides quantitative assessment of wind energy resources. The sensitivity analysis algorithm and risk evaluation algorithm are used to quantify and evaluate the potential risks of wind energy projects by considering geographical conditions, climate change, and wind variability factors.

5. The wind power variable pitch control system of claim 1, wherein, The Internet of Things and cloud platform module includes a centralized control unit, a remote monitoring unit, and a cloud platform data processing unit. The centralized control unit applies optimization control and adaptive control algorithms to centrally control multiple wind turbine generators. The remote monitoring unit collects wind turbine generator data and uses data acquisition optimization algorithms, anomaly detection algorithms, and fault diagnosis algorithms to achieve data monitoring and early warning. The cloud platform data processing unit uses big data analysis, prediction, and early warning algorithms to analyze and process the wind turbine generator data in depth.

6. The wind power variable pitch control system of claim 1, wherein, The high-temperature adaptation module includes a high-temperature environment detection unit and a stable operation strategy generation unit. The high-temperature environment detection unit collects environmental temperature data in real time through temperature sensors, including temperature threshold judgment algorithms, temperature trend analysis algorithms, and temperature sensor data calibration algorithms. The stable operation strategy generation unit receives environmental temperature data, adjusts the blade angle and rotor speed parameters based on the current environmental temperature and power curve data to prevent system overheating, and selects a fault handling strategy based on fault detection data and temperature information in a high-temperature environment.

7. The wind power variable pitch control system of claim 1, wherein, The friction damping technology module includes a damping detection unit and an angle stabilization strategy generation unit. The damping detection unit uses vibration analysis and frequency spectrum analysis methods to monitor the blade friction damping state in real time and outputs a friction damping report. The angle stabilization strategy generation unit adjusts the blade angle based on the friction damping report and PID control algorithm to generate a blade angle stabilization strategy. The active variable pitch control module includes an environment perception unit and a blade regulation response unit. The environment perception unit uses active materials and sensor networks to perceive wind speed and humidity parameters in the environment and generates an environment perception report. The paddle regulation response unit uses a deep learning algorithm to regulate the paddle based on environmental perception reports, adaptively adjusts the paddle angle and position, and generates a paddle regulation strategy.

8. The wind power variable pitch control system of claim 1, wherein, The multi-modal paddle regulation module includes a paddle mode selection unit, a neural network optimization unit, and a genetic algorithm optimization unit. The paddle mode selection unit uses data-driven discriminant analysis to select the paddle regulation mode according to the wind field conditions and determines the paddle regulation mode selection. The neural network optimization unit uses a convolutional neural network to optimize the paddle regulation mode selection based on the paddle regulation mode selection, performs real-time optimization on the paddle regulation mode selection, and generates a neural network optimization result. The genetic algorithm optimization unit uses a genetic algorithm to perform secondary optimization based on the neural network optimization result, automatically adjusts the paddle parameters to achieve optimal efficiency, and generates a final paddle regulation strategy.

9. A wind power variable pitch system, characterized in that The wind power variable pitch system is controlled by the wind power variable pitch control system according to any one of claims 1-8, and the wind power variable pitch system is composed of a wind energy collection module, a power conversion and optimization module, an energy storage and safety module, and an electric energy output and distribution module. The wind energy collection module collects wind energy in real time and converts it into primary mechanical energy, uses wind speed and blade angle data, calculates wind energy utilization based on air density and blade radius, and outputs a primary mechanical energy report. The power conversion and optimization module applies electromagnetic induction principles and PID control algorithms for energy conversion and optimization, converts mechanical energy in the primary mechanical energy report into electrical energy, and optimizes energy according to the paddle regulation strategy, and outputs a primary electrical energy report. The energy storage and safety module receives the primary electrical energy report, performs safety control based on battery charge and discharge algorithms, and combines risk analysis data to generate a safety energy storage report. The electric energy output and distribution module uses smart grid management and load forecasting algorithms to output and distribute electric energy based on the safety energy storage report, and generates an electric energy distribution completion report.

Images