Method for reducing damage to yaw mechanism of wind power generation system through pneumatic unbalance adjustment

Abstract

The invention relates to the technical field of wind power generation, and discloses a method for reducing damage to a yaw mechanism of a wind power generation system through pneumatic unbalance adjustment, and the method comprises the following steps: S1, arranging sensors to monitor blades, a wind field and a vibration state; s2, fusing data, and calculating pneumatic unbalance; s3, constructing a model to predict the change of the wind field; s4, adjusting the balance load of the blade load; s5, optimizing a yaw angle adjustment strategy; s6, yaw action is reduced, and operation is optimized; and S7, health state prediction faults are monitored. The pneumatic load and the pneumatic unbalance degree of the blade are monitored in real time, the micro pneumatic actuator and the dynamic balance weight module are combined, the pneumatic performance and the load distribution of the blade are dynamically adjusted, the impact load and the vibration amplitude borne by the yaw mechanism are effectively reduced, in addition, a torque limiting and intelligent damping protection mechanism is adopted, and the service life of the yaw mechanism is prolonged. The fatigue damage accumulated value and the part abrasion degree of the yaw mechanism are fundamentally reduced, and therefore the service life of the yaw mechanism is prolonged.

Description

Technical Field

[0001] The invention relates to the technical field of wind power generation, and in particular to a method for reducing damage to a yaw mechanism of a wind power generation system by regulating aerodynamic imbalance. Background Art

[0002] As an important clean energy technology, wind power generation has been widely used around the world. The yaw mechanism in the wind power generation system is one of the key components. Its main function is to adjust the direction of the wind turbine so that the wind rotor always faces the incoming wind direction to capture the maximum wind energy. However, during long-term operation, the yaw mechanism is often affected by the aerodynamic imbalance between the blades, resulting in significant damage, which becomes an important issue affecting the stability and life of the wind turbine. Aerodynamic imbalance is a dynamic torque imbalance caused by the difference in force between the blades. This imbalance is usually caused by complex wind field conditions (such as wind speed gradient, turbulence, and transient wind direction changes) and differences in blade performance (such as aging or pollution). When aerodynamic imbalance occurs, the yaw mechanism needs to withstand additional impact loads and vibrations, which not only accelerates the wear of components such as gears and bearings, but also shortens the service life of the entire yaw system. In addition, frequent yaw actions will further aggravate mechanical fatigue and increase the risk of equipment failure.

[0003] In the prior art, the main methods for solving the aerodynamic imbalance problem include optimizing the blade airfoil design, adding fixed counterweights, and improving the yaw control strategy. However, these methods have obvious limitations. First, the existing fixed counterweight solution cannot adapt to the rapid changes in wind field conditions in real time, and it is difficult to solve the transient impact of aerodynamic imbalance. Secondly, traditional yaw systems mostly use real-time measurement data based on wind speed and wind direction, which fails to effectively predict wind field changes, resulting in delayed yaw adjustment response and increased energy loss and mechanical wear. Furthermore, the existing yaw mechanism lacks a dynamic protection mechanism for vibration and impact, and is prone to component fatigue failure due to high-frequency vibration and extreme loads. Finally, the traditional regular inspection and maintenance mode fails to monitor the real-time status of the yaw mechanism and predict faults, and unplanned downtime occurs frequently, resulting in high maintenance costs.

[0004] In summary, the existing technology has many deficiencies in dealing with the influence of aerodynamic imbalance on the yaw mechanism, and it is difficult to meet the requirements of wind power generation systems for high efficiency and reliability. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides a method for reducing damage to the yaw mechanism of a wind power generation system by adjusting aerodynamic imbalance, thereby solving the problems of impact load, vibration damage and fatigue failure of the yaw mechanism caused by aerodynamic imbalance in the wind power generation system.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: A method for reducing damage to a yaw mechanism of a wind power generation system by regulating aerodynamic imbalance, comprising the following steps:

[0007] S1. Arrange a multi-dimensional sensor network to monitor blade surface pressure, root strain, wind speed and direction, and turbulence intensity in real time;

[0008] S2, fuse and reduce noise of collected data to quantify dynamic aerodynamic imbalance;

[0009] S3. Construct a prediction model for wind speed, wind direction and turbulence intensity based on historical wind farm data;

[0010] S4, adjusting the aerodynamic load of the blade, and balancing the blade load through a micro-pneumatic control device and a dynamic weight module;

[0011] S5. Optimize the yaw angle adjustment strategy based on the yaw mechanism vibration and aerodynamic imbalance;

[0012] S6, reduce the yaw action frequency and optimize the system operation status through model predictive control;

[0013] S7. Perform real-time health monitoring and fault prediction on the operating status of the yaw mechanism.

[0014] Preferably, in step S1, the multidimensional sensor network includes the following components:

[0015] An array of pressure sensors arranged on the blade surface is used to collect the pressure distribution on the blade surface in real time;

[0016] The strain sensor installed at the blade root is used to measure the bending moment and load at the blade root;

[0017] Wind speed and direction sensors located at the top of the tower to monitor wind speed, direction and turbulence intensity;

[0018] The acceleration sensor at the yaw mechanism is used to monitor the vibration frequency and amplitude of the yaw mechanism.

[0019] Preferably, in step S2, the method for quantifying dynamic aerodynamic imbalance includes:

[0020] a. Calculate the total aerodynamic load based on the surface pressure distribution of the blade;

[0021] b. Quantify the aerodynamic imbalance by the following formula:

[0022] ΔF=max(F leaf,1 ,F leaf,2 ,F leaf,3 )-min(F leaf,1 ,F leaf,2 ,Fleaf,3 )

[0023] Among them, F leaf,i is the total aerodynamic load on the i-th blade.

[0024] Preferably, in step S3, the prediction model is based on a long short-term memory network model, and historical data of wind speed, wind direction and turbulence intensity are input to predict future wind speed, wind direction and turbulence intensity, which is used for dynamic prediction of wind fields.

[0025] Preferably, in step S4, the active adjustment of the blade aerodynamic load comprises the following steps:

[0026] a. Install a micro pneumatic actuator on the blade surface to adjust the lift coefficient C L and the drag coefficient C D Achieve blade load balance;

[0027] b. A dynamic counterweight module is set at the root of the blade to balance the torque difference between the blades by adjusting the mass of the counterweight.

[0028] Preferably, the micro pneumatic actuator adjusts the blade lift coefficient C by the following formula: L :

[0029]

[0030] Among them, k p is the proportionality coefficient, is the pressure gradient on the blade surface.

[0031] Preferably, in step S5, the optimization of the yaw angle is achieved by the following model predictive control method:

[0032] a. Predict the aerodynamic imbalance state under wind field conditions;

[0033] b. Determine the optimal yaw angle by optimizing the following objective function:

[0034]

[0035] Among them, α is the weight factor, is the yaw speed.

[0036] Preferably, in step S5, the vibration of the yaw mechanism needs to meet the following conditions:

[0037] A(t)≤A limit

[0038] Among them, A(t) is the vibration amplitude, A limit The upper limit of the vibration amplitude is set.

[0039] Preferably, in step S7, the fault prediction of the yaw mechanism is based on a random forest algorithm model, and the input includes the aerodynamic load, vibration data and action frequency of the yaw mechanism.

[0040] Preferably, in step S7, the health management evaluates the health status of the yaw mechanism through a fatigue accumulation model;

[0041] The fatigue accumulation model evaluates the fatigue damage accumulation of the yaw mechanism by the following formula:

[0042]

[0043] Where D is the fatigue damage degree, Δσ i is the stress range of the i-th cycle, σ failure is the fatigue limit of the material.

[0044] The present invention provides a method for reducing damage to the yaw mechanism of a wind power generation system by regulating aerodynamic imbalance. It has the following beneficial effects:

[0045] 1. The present invention monitors the aerodynamic load and aerodynamic imbalance of the blades in real time, combines a micro-pneumatic actuator and a dynamic counterweight module, and dynamically adjusts the aerodynamic performance and load distribution of the blades, thereby effectively reducing the impact load and vibration amplitude of the yaw mechanism. In addition, the torque limitation and intelligent damping protection mechanism are adopted to further alleviate the extreme load impact caused by aerodynamic imbalance, fundamentally reducing the fatigue damage accumulation value and component wear degree of the yaw mechanism, thereby extending the service life of the yaw mechanism, reducing the probability of failure due to mechanical fatigue, and providing a guarantee for the long-term stable operation of the wind power generation system.

[0046] 2. The present invention adopts a long short-term memory network model to perform high-precision prediction of wind speed, wind direction and turbulence intensity, realizes early perception of future wind field changes, optimizes the yaw angle adjustment strategy based on the prediction results, so that the wind wheel always maintains the best windward state, significantly reduces the yaw error, and improves the wind energy capture efficiency. In addition, by real-time adjustment of the aerodynamic performance of the blades and optimization of the yaw action logic, the present invention significantly improves the dynamic response capability of the system under complex wind field conditions, especially in the case of rapid changes in wind speed and wind direction, it shows higher adaptability, effectively ensuring the efficient operation of the wind turbine.

[0047] 3. The model predictive control method of the present invention optimizes the yaw angle adjustment logic, reduces the frequency and adjustment range of the yaw action, thereby reducing the working times and energy consumption of the yaw motor. In addition, the yaw angle optimization strategy avoids the mechanical wear caused by frequent yaw actions, reduces equipment failures and maintenance requirements. Combined with the health management module, the present invention can dynamically monitor the operating status of key components, predict possible failures in advance, optimize maintenance time intervals, and significantly reduce the number of unplanned downtimes. Overall, the present invention not only reduces the system energy consumption, but also significantly reduces the operating and maintenance costs, thereby improving the economy of the wind power generation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a flow chart of the steps of the present invention. DETAILED DESCRIPTION

[0049] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0050] Embodiment 1:

[0051] Specifically, in step S1, the multidimensional sensor network is the basis of the entire method, and its layout covers multiple key components of the blade, tower and yaw mechanism. The pressure sensor array on the blade surface monitors the distribution of local pressure on the blade surface in real time, capturing the aerodynamic characteristics of the blade under the action of the wind field; the strain sensor at the root of the blade is used to monitor the bending moment and overall load state of the blade, thereby accurately reflecting the coupled mechanical characteristics of the blade and the wind field; the wind speed and wind direction sensors at the top of the tower sense the macroscopic changes of the wind field in real time, including wind speed gradient, wind direction change and turbulence intensity; the acceleration sensor on the yaw mechanism monitors the vibration amplitude and frequency, and quantifies the dynamic impact of aerodynamic imbalance on the yaw mechanism. Through the data acquisition of these sensors, the force state of the blade and yaw system can be fully obtained, providing accurate input for subsequent data processing and dynamic adjustment, thereby providing data support for the dynamic adaptability of the system through real-time multi-dimensional monitoring, which helps to capture wind field changes and blade load anomalies in a timely manner, reduce response delays and system lags, and improve adjustment accuracy.

[0052] In step S2, a multi-dimensional data fusion algorithm is used to fuse and reduce noise from data from different sensors, thereby reducing sensor measurement errors and improving data accuracy and consistency. By calculating the total aerodynamic load on the blade surface, the collected blade pressure distribution data is integrated into a single numerical expression, and the aerodynamic imbalance value between blades is further calculated. The quantitative formula reflects the degree of aerodynamic imbalance by calculating the difference between the maximum and minimum values ​​of the total aerodynamic load of the blade. Therefore, through data fusion and noise reduction processing, the system's perception of dynamic aerodynamic imbalance is significantly improved, avoiding the errors that may occur in a single sensor, and ensuring the accuracy and reliability of the adjustment plan.

[0053] In step S3, the present invention uses a long short-term memory network to model and predict the historical data of wind speed, wind direction and turbulence intensity. The long short-term memory network model can effectively capture the nonlinear characteristics of wind field time series data, predict future wind speed changes, wind direction changes and turbulence intensity trends in advance, and provide the system with future wind field dynamic information. The prediction model can be adaptively updated according to historical data to more accurately reflect the changing trend of the wind field environment. Through the dynamic prediction of the wind field, the yaw system can adjust the operating parameters in advance to cope with complex wind field conditions, reduce the yaw error caused by wind direction fluctuations, and improve the response efficiency and energy capture capability of the system.

[0054] In step S4, active adjustment of the aerodynamic load of the blade is achieved by installing a micro-pneumatic actuator on the blade surface and arranging a dynamic counterweight module at the root of the blade. The micro-pneumatic actuator can dynamically change the aerodynamic performance of the blade by adjusting the lift and drag coefficients, thereby balancing the load differences between the blades. The dynamic counterweight module adjusts the counterweight mass and distribution position at the root of the blade in real time according to the quantitative results of the aerodynamic imbalance, further reducing the impact of the unbalanced torque on the yaw mechanism, thereby significantly reducing the aerodynamic imbalance between the blades through active aerodynamic adjustment and dynamic counterweight balance, fundamentally reducing the vibration and fatigue damage of the yaw mechanism, and extending the life of the equipment.

[0055] In step S5, the yaw angle adjustment strategy is optimized through model predictive control technology. Based on the wind field prediction model and real-time monitoring data, the system can predict the aerodynamic imbalance state and calculate the optimal yaw angle adjustment path by optimizing the objective function. The objective function considers the trade-off between aerodynamic imbalance and yaw motor action energy consumption, reducing unnecessary yaw actions while ensuring wind energy capture efficiency. In addition, during the yaw angle adjustment process, the vibration amplitude must meet the safety threshold condition to prevent excessive damage to the yaw mechanism by high-frequency vibration. In this way, the yaw action frequency and system energy consumption are reduced through the optimized yaw angle adjustment strategy, while reducing the risk of high-frequency vibration, further improving the operating efficiency and reliability of the yaw system.

[0056] In step S6, by comprehensively analyzing the wind field prediction results and the real-time status of the yaw mechanism, the present invention uses model predictive control technology to optimize the planning of the yaw action. By reducing the frequency and amplitude of the yaw action, the working intensity of the yaw motor is significantly reduced, and the wear of mechanical parts caused by frequent adjustments is avoided. At the same time, the optimized yaw control logic can maximize the maintenance of the wind wheel in the best windward position and improve the efficiency of wind energy capture. Reducing the frequency of yaw action not only reduces the energy consumption of the yaw system, but also slows down the wear rate of components, greatly extending the maintenance interval and service life of the system.

[0057] In step S7, the sensor network is used to collect data such as the aerodynamic load, vibration frequency, and movement frequency of the yaw mechanism in real time, and a fault prediction model is constructed in combination with the random forest algorithm. The fault prediction model can identify potential component failure trends and generate maintenance warnings in advance. In addition, the fatigue accumulation model is used to dynamically evaluate the health status of the yaw mechanism, and the fatigue damage degree of the components is quantitatively calculated to provide a basis for optimizing the maintenance plan. In this way, the probability of unplanned downtime is significantly reduced through real-time health monitoring and fault prediction, and serious faults are avoided through early maintenance, which prolongs the reliable operation time of the system and reduces the operation and maintenance costs.

[0058] Example 2: Yaw system optimization method based on wind field dynamic prediction

[0059] Specific steps:

[0060] Deploy sensors to monitor wind speed, direction and turbulence intensity and record historical data.

[0061] The wind field data prediction model is used to predict the dynamic changes of future wind fields in advance.

[0062] According to the prediction results, the yaw angle adjustment strategy is optimized in advance to keep the wind turbine in the best windward state.

[0063] By intelligently adjusting the aerodynamic performance of the blades, we can respond to sudden changes in the wind field and avoid drastic changes in aerodynamic imbalance.

[0064] Summarize:

[0065] Through the wind field dynamic prediction technology, this embodiment improves the adaptability of the wind turbine generator set to wind field changes, reduces yaw errors, and improves wind energy utilization efficiency.

[0066] Embodiment 3: Yaw mechanism damage mitigation method based on intelligent vibration protection

[0067] Specific steps:

[0068] An acceleration sensor is installed on the yaw mechanism to monitor the vibration amplitude and frequency in real time.

[0069] The monitored vibration data are correlated with wind field parameters and aerodynamic imbalance.

[0070] An intelligent damping device is installed at the yaw mechanism gear to dynamically adjust the damping according to the vibration amplitude to reduce vibration impact.

[0071] Add a torque limiting protection mechanism to the yaw drive system to prevent transient impacts of extreme loads on the yaw mechanism.

[0072] Summarize:

[0073] Through intelligent vibration protection and torque limiting technology, this embodiment reduces the damage to the yaw mechanism caused by high-frequency vibration and extreme loads, and improves the reliability of system operation.

[0074] Example 4: Yaw mechanism maintenance method based on fault prediction and health management

[0075] Specific steps:

[0076] Sensors are deployed to monitor the load, vibration, temperature and other operating data of the yaw mechanism in real time.

[0077] The fatigue damage accumulation value of the yaw mechanism is dynamically calculated using the health status assessment method.

[0078] Combined with the fault prediction model, the potential failure trend of the yaw mechanism is analyzed based on the monitoring data.

[0079] Develop optimal maintenance plans based on health status and fault prediction results to reduce unplanned downtime.

[0080] Summarize:

[0081] Through fault prediction and health management technology, this embodiment optimizes the maintenance process and reduces the unplanned downtime rate and maintenance cost of the yaw mechanism.

[0082] Example 5: Full-process system improvement method based on composite optimization strategy

[0083] Specific steps:

[0084] The key data of the wind farm, blades and yaw mechanism are monitored in real time through a sensor network.

[0085] Combine wind farm dynamic prediction technology and aerodynamic load adjustment methods to optimize yaw angle adjustment and blade performance in advance.

[0086] Add vibration protection and torque limiting mechanisms to further alleviate damage accumulation in the yaw mechanism.

[0087] Utilize fault prediction and health management technologies to dynamically evaluate the health status of the yaw mechanism and optimize maintenance plans.

[0088] Summarize:

[0089] This embodiment integrates multiple optimization technologies, from wind field prediction to yaw adjustment and health management, to achieve comprehensive protection and optimization of the entire process of the yaw mechanism, improve system efficiency and extend equipment life.

[0090] Summary of the embodiments:

[0091] Embodiment 1: By adjusting the aerodynamic load of the blades, the load is balanced and the impact of aerodynamic imbalance on the yaw mechanism is reduced.

[0092] Embodiment 2: By dynamically predicting the wind field, the yaw adjustment strategy is optimized to improve the efficiency of wind energy utilization.

[0093] Embodiment 3: Alleviate the vibration and extreme load damage of the yaw mechanism through vibration protection and torque limitation.

[0094] Example 4: Reduce unplanned downtime and maintenance costs through fault prediction and health management.

[0095] Embodiment 5: Integrate multiple optimization technologies to provide full-process protection and efficient operation solutions for the yaw mechanism.

[0096] Experiment 1: Pneumatic Load Regulation Test

[0097] Purpose:

[0098] The effect of reducing the damage of aerodynamic imbalance to the yaw mechanism by aerodynamic load adjustment in Example 1 was verified.

[0099] Testing process:

[0100] Equipment preparation: Install the pressure sensor and dynamic weight device.

[0101] Testing phase:

[0102] Run the fan for 48 hours in the initial state (without pneumatic load adjustment).

[0103] Activate the pneumatic load regulation function and run the fan for another 48 hours.

[0104] Data collection:

[0105] The blade load difference (aerodynamic imbalance value) is recorded.

[0106] Monitor the vibration amplitude and fatigue accumulation state of the yaw mechanism.

[0107] Experimental data:

[0108]

[0109] Experimental results:

[0110] The aerodynamic load adjustment significantly reduces the blade load difference and fatigue accumulation of the yaw mechanism, and the vibration amplitude of the yaw mechanism is reduced by more than 50%, verifying the effectiveness of this embodiment.

[0111] Experiment 2: Wind farm dynamic prediction test

[0112] Purpose:

[0113] Verify the effect of optimizing the yaw angle through dynamic prediction of the wind field in Example 2.

[0114] Testing process:

[0115] Equipment preparation: Deploy wind speed and direction sensors and load wind field prediction algorithms.

[0116] Testing phase:

[0117] Do not enable wind farm dynamic prediction and run the wind turbine for 24 hours.

[0118] Enable wind farm dynamic prediction to run wind turbines for 24 hours.

[0119] Data collection:

[0120] Yaw error and wind energy capture efficiency are recorded.

[0121] Count the number of yaw actions.

[0122] Experimental data:

[0123]

[0124]

[0125] Experimental results:

[0126] Dynamic prediction of wind fields significantly reduces yaw errors, improves wind energy capture efficiency, and significantly reduces the frequency of yaw movements.

[0127] Experiment 3: Smart Vibration Protection Test

[0128] Purpose:

[0129] Verify the effect of the vibration protection in Example 3 on alleviating fatigue damage of the yaw mechanism.

[0130] Testing process:

[0131] Equipment preparation: Install vibration sensors and intelligent damping devices on the yaw mechanism.

[0132] Testing phase:

[0133] Run the fan for 24 hours without vibration protection enabled.

[0134] Run the fan for 24 hours with vibration protection enabled.

[0135] Data collection:

[0136] Record the vibration amplitude and frequency of the yaw mechanism.

[0137] Measuring yaw mechanism fatigue damage.

[0138] Experimental data:

[0139]

[0140] Experimental results:

[0141] Intelligent vibration protection significantly reduces the vibration amplitude and fatigue damage value of the yaw mechanism, extending the reliability life of the equipment.

[0142] Experiment 4: Fault prediction and health management test

[0143] Purpose:

[0144] Verify the impact of fault prediction and health management on the unplanned downtime rate in Example 4.

[0145] Testing process:

[0146] Equipment preparation: Load the health status monitoring and fault prediction modules.

[0147] Testing phase:

[0148] The fan is operated continuously for 1000 hours without enabling the fault prediction function.

[0149] Enable the fault prediction function and run the fan continuously for 1000 hours.

[0150] Data collection:

[0151] Record the number of unplanned downtimes.

[0152] Statistics on maintenance intervals and replacement times of key components.

[0153] Experimental data:

[0154]

[0155] Experimental results:

[0156] Fault prediction and health management effectively reduce the number of unplanned downtime and improve equipment maintenance efficiency.

[0157] Experiment 5: Full-process system improvement test

[0158] Purpose:

[0159] Verify the effect of the full-process optimization strategy in Example 5 on improving the comprehensive performance of the yaw mechanism.

[0160] Testing process:

[0161] Equipment preparation: Integrate wind farm forecasting, aerodynamic load regulation, vibration protection and fault prediction functions.

[0162] Testing phase:

[0163] Run the wind turbine for 100 hours without integrating the full process optimization.

[0164] Enable full-process optimization and run the fan for 100 hours.

[0165] Data collection:

[0166] Wind energy capture efficiency, yaw mechanism fatigue damage and yaw motion frequency were recorded.

[0167] Experimental data:

[0168]

[0169] Experimental results:

[0170] The full-process optimization strategy significantly improves the system's wind energy capture efficiency, while significantly reducing yaw mechanism fatigue damage and yaw motion frequency.

[0171] Experimental summary:

[0172] Experiment 1: Pneumatic load regulation significantly reduces aerodynamic imbalance and fatigue damage, reduces vibration amplitude, and extends the service life of the yaw mechanism.

[0173] Experiment 2: Wind field prediction reduces yaw error, improves wind energy utilization efficiency, and reduces yaw action frequency.

[0174] Experiment 3: Vibration protection reduces vibration amplitude and frequency, reduces fatigue damage, and improves the operational reliability of the yaw mechanism.

[0175] Experiment 4: Health management significantly reduces the number of unplanned downtimes, improves maintenance efficiency, and extends maintenance intervals.

[0176] Experiment 5: Full-process optimization comprehensively improves the operating performance of the yaw mechanism, enhances system efficiency, reduces fatigue damage, and achieves comprehensive optimization of the wind power generation system.

[0177] in conclusion:

[0178] The test results show that all embodiments of the present invention can significantly improve the operating performance of the yaw mechanism of the wind power generation system. In particular, in the case of full-process optimization, multiple technical advantages are integrated to achieve comprehensive optimization of the yaw mechanism from pneumatic adjustment, vibration protection to fault prediction, verifying the technical advancement and practical value of the present invention.

[0179] Comparative experiment 1: The influence of blade aerodynamic load adjustment on yaw mechanism damage

[0180] Existing technical solutions:

[0181] Aerodynamic imbalance is reduced only by fixing the counterweight and optimizing the blade shape, without achieving dynamic real-time adjustment.

[0182] The aerodynamic load is fixed and cannot cope with the dynamic changes of the wind field and transient wind speed fluctuations.

[0183] Technical solution of the present invention:

[0184] Micro pneumatic actuators are installed on the blade surface to dynamically adjust the lift and drag coefficients of the blades to achieve real-time aerodynamic balance.

[0185] A dynamic counterweight module is installed at the root of the blade to dynamically adjust the counterweight distribution according to the aerodynamic imbalance value to reduce the unbalanced torque.

[0186] Testing process:

[0187] Wind farm environment: turbulence intensity is 15%, wind speed range is 5-20m / s, and operating time is 48 hours.

[0188] Test method:

[0189] The fans are operated respectively using the prior art and the technology of the present invention.

[0190] Monitor parameters such as blade load difference (aerodynamic imbalance value), yaw mechanism vibration amplitude, fatigue damage accumulation value, etc.

[0191] Experimental data table:

[0192]

[0193] Experimental results analysis:

[0194] The technical solution of the present invention significantly reduces the pneumatic imbalance value and the vibration amplitude of the yaw mechanism, and the wear and fatigue accumulation value of the yaw gear are greatly reduced, verifying the superiority of the dynamic adjustment technology.

[0195] Comparative experiment 2: The impact of wind field dynamic prediction on yaw control optimization

[0196] Existing technical solutions:

[0197] The yaw angle adjustment is based on the real-time measurement data of the wind speed sensor, and no wind field prediction technology is used.

[0198] When wind speed and direction change rapidly, the yaw control system responds with lag, resulting in large yaw errors.

[0199] Technical solution of the present invention

[0200] Long short-term memory network (LSTM) is used to dynamically predict wind speed, wind direction and turbulence intensity.

[0201] Optimize the yaw angle adjustment strategy in advance to reduce the yaw error caused by wind direction changes and improve the efficiency of wind energy utilization.

[0202] Testing process:

[0203] Wind farm environment: turbulence intensity is 20%, wind speed range is 8-25m / s, and operation time is 24 hours.

[0204] Test method:

[0205] The fans are operated respectively using the prior art and the technology of the present invention.

[0206] Monitor parameters such as yaw error, wind energy capture efficiency, and number of yaw movements.

[0207] Experimental data table:

[0208]

[0209] Experimental results analysis:

[0210] The present invention significantly reduces the yaw error through the wind field dynamic prediction technology, while reducing the yaw action frequency and energy consumption, and exhibits higher dynamic response capability, especially in an environment with rapid wind speed changes.

[0211] Comparative Experiment 3: Impact of Fault Prediction and Health Management on System Maintenance Costs

[0212] Existing technical solutions:

[0213] Yaw mechanism fault maintenance relies on manual periodic inspection and passive fault response.

[0214] Due to the lack of real-time health management and prediction methods, faults are prone to accumulate, the unplanned downtime rate is high, and the maintenance cost is high.

[0215] Technical solution of the present invention:

[0216] The load, vibration and temperature data of the yaw mechanism are monitored in real time through a sensor network.

[0217] The random forest model is used to predict the failure trend of the yaw mechanism, combined with fatigue accumulation analysis to optimize maintenance plans and reduce unplanned downtime.

[0218] Testing process:

[0219] Test conditions: 1000 hours of operation, operating in a high turbulence wind field (turbulence intensity 25%).

[0220] Test method:

[0221] The fans are operated respectively using the prior art and the technology of the present invention.

[0222] Record parameters such as the number of unplanned downtime, replacement time of key components, and average maintenance interval.

[0223] Experimental data table:

[0224]

[0225] Experimental results analysis:

[0226] The present invention significantly reduces the number of unplanned downtimes through fault prediction and health management technologies, improves system operation reliability, optimizes maintenance intervals and key component replacement time, and significantly reduces maintenance costs.

[0227] Summary:

[0228] Experiment 1: Pneumatically adjust the pneumatic imbalance value, vibration amplitude, and fatigue accumulation to reduce yaw mechanism damage and extend the service life of the equipment.

[0229] Experiment 2: Wind farm prediction of yaw error, wind energy capture efficiency, and yaw action times to improve wind energy utilization efficiency and reduce yaw action frequency and energy consumption.

[0230] Experiment 3: Health management Number of unplanned downtime, maintenance interval, operation reliability, and maintenance cost Reduce maintenance costs and improve system operation reliability.

[0231] Comprehensive analysis:

[0232] Through comparative experiments, it is verified that the present invention is significantly superior to the existing technologies in terms of aerodynamic load regulation, wind farm dynamic prediction, fault prediction and health management, and especially shows excellent technical advantages in terms of yaw mechanism protection and operation optimization. These improvements effectively improve the efficiency and reliability of wind power generation systems and have important practical application value.

[0233] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for reducing damage to the yaw mechanism of a wind power generation system by regulating aerodynamic imbalance, characterized in that: The following steps are involved: S1. Arrange a multi-dimensional sensor network to monitor blade surface pressure, root strain, wind speed and direction, and turbulence intensity in real time; S2, fuse and reduce noise of collected data to quantify dynamic aerodynamic imbalance; S3. Construct a prediction model for wind speed, wind direction and turbulence intensity based on historical wind farm data; S4, adjusting the aerodynamic load of the blade, and balancing the blade load through a micro-pneumatic control device and a dynamic weight module; S5. Optimize the yaw angle adjustment strategy based on the yaw mechanism vibration and aerodynamic imbalance; S6, reduce the yaw action frequency and optimize the system operation status through model predictive control; S7. Perform real-time health monitoring and fault prediction on the operating status of the yaw mechanism.

2. The method for reducing damage to the yaw mechanism of a wind power generation system by adjusting aerodynamic imbalance according to claim 1 is characterized in that: In step S1, the multidimensional sensor network includes the following components: An array of pressure sensors arranged on the blade surface is used to collect the pressure distribution on the blade surface in real time; The strain sensor installed at the blade root is used to measure the bending moment and load at the blade root; Wind speed and direction sensors located at the top of the tower to monitor wind speed, direction and turbulence intensity; The acceleration sensor at the yaw mechanism is used to monitor the vibration frequency and amplitude of the yaw mechanism.

3. The method for reducing damage to the yaw mechanism of a wind power generation system by adjusting aerodynamic imbalance according to claim 1, characterized in that: In step S2, the method for quantifying dynamic aerodynamic imbalance includes: a. Calculate the total aerodynamic load based on the surface pressure distribution of the blade; b. Quantify the aerodynamic imbalance by the following formula: ΔF=max(F leaf,1 ,F leaf,2 ,F leaf,3 )-min(F leaf,1 ,F leaf,2 ,F leaf,3 ) Among them, F leaf,i is the total aerodynamic load on the i-th blade.

4. The method for reducing damage to the yaw mechanism of a wind power generation system by adjusting aerodynamic imbalance according to claim 1, characterized in that: In the step S3, the prediction model is based on a long short-term memory network model, which inputs historical data of wind speed, wind direction and turbulence intensity to predict future wind speed, wind direction and turbulence intensity, which is used for dynamic prediction of wind fields.

5. The method for reducing damage to the yaw mechanism of a wind power generation system by adjusting aerodynamic imbalance according to claim 1, characterized in that: In step S4, the active adjustment of the blade aerodynamic load includes the following steps: a. Install a micro pneumatic actuator on the blade surface to adjust the lift coefficient C L and the drag coefficient C D Achieve blade load balance; b. A dynamic counterweight module is set at the root of the blade to balance the torque difference between the blades by adjusting the mass of the counterweight.

6. The method for reducing damage to the yaw mechanism of a wind power generation system by regulating aerodynamic imbalance according to claim 5, characterized in that: The micro pneumatic actuator adjusts the blade lift coefficient C by the following formula L : Among them, k p is the proportionality coefficient, is the pressure gradient on the blade surface.

7. The method for reducing damage to the yaw mechanism of a wind power generation system by regulating aerodynamic imbalance according to claim 1, characterized in that: In step S5, the optimization of the yaw angle is achieved by the following model predictive control method: a. Predict the aerodynamic imbalance state under wind field conditions; b. Determine the optimal yaw angle by optimizing the following objective function: Among them, α is the weight factor, is the yaw speed.

8. The method for reducing damage to the yaw mechanism of a wind power generation system by regulating aerodynamic imbalance according to claim 1, characterized in that: In step S5, the vibration of the yaw mechanism must meet the following conditions: A(t)≤A limit Among them, A(t) is the vibration amplitude, A limit The upper limit of the vibration amplitude is set.

9. The method for reducing damage to the yaw mechanism of a wind power generation system by regulating aerodynamic imbalance according to claim 1, characterized in that: In the step S7, the fault prediction of the yaw mechanism is based on a random forest algorithm model, and the input includes the aerodynamic load, vibration data and action frequency of the yaw mechanism.

10. The method for reducing damage to the yaw mechanism of a wind power generation system by regulating aerodynamic imbalance according to claim 1, characterized in that: In the step S7, the health management evaluates the health status of the yaw mechanism through a fatigue accumulation model; The fatigue accumulation model evaluates the fatigue damage accumulation of the yaw mechanism by the following formula: Where D is the fatigue damage degree, Δσ i is the stress range of the i-th cycle, σ failure is the fatigue limit of the material.

Images