Spline torsion force control method and system
By establishing a multi-bar model library and data-driven prediction algorithm, adjusting the torsion force of wind power blades, the problems of insufficient accuracy and slow response speed in environments with frequent wind speed changes are solved, and efficient and stable dynamic control of wind power blades is achieved.
Patent Information
- Application Number
- CN202411493961.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-24
- Publication Date
- 2024-12-17
AI Technical Summary
Traditional wind power blade torsion control methods have problems of insufficient accuracy and slow response speed in environments where wind speed changes frequently and unstable, resulting in the blades bearing increased stress, reducing energy conversion efficiency and increasing maintenance costs.
By establishing a spline model library based on spline stress and deformation characteristic data, combining real-time wind speed and wind direction data, the data-driven prediction algorithm is used to adjust the torsion force, generate torsion control instructions, and adjust the blade torsion angle and force in real time to achieve high-precision dynamics Torsion control.
It effectively improves the high-precision dynamic torsion control of wind power blades, improves efficiency and stability, reduces mechanical stress and fatigue losses, and reduces maintenance costs.
Smart Images
Figure CN119146000A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of automatic control technology, and in particular to a spline torsion force control method and system. Background Art
[0002] In the field of wind power generation, the control of the torsion force of the blades is a key factor in improving power generation efficiency and extending the life of the blades. At present, the torsion control of wind turbine blades usually relies on traditional methods such as PID control and fuzzy control. These methods can achieve basic torsion adjustment under certain conditions, but there are significant deficiencies in environments where wind speed changes frequently and is unstable. On the one hand, the control accuracy and response speed of traditional methods are limited, and it is difficult to respond to the rapid fluctuations of wind speed and wind direction in time, resulting in increased stress on the blades and reduced energy conversion efficiency; on the other hand, these methods lack adaptive capabilities and cannot adjust control parameters according to real-time wind conditions, which easily causes fatigue loss of the blades and increases maintenance costs.
[0003] The information disclosed in this background technology section is only intended to deepen the understanding of the overall background technology of the present disclosure, and should not be regarded as acknowledging or suggesting in any form that the information constitutes the prior art known to those skilled in the art. Summary of the invention
[0004] The present invention provides a spline torsion force control method and system, thereby effectively solving the problems pointed out in the background technology.
[0005] In order to achieve the above object, the technical solution adopted by the present invention is: A spline torsion force control method, comprising: Based on the spline stress and deformation characteristic data under different wind speeds and force conditions, a torsional force control model for the relationship between blade force and wind conditions in different regions of the blade is established to generate a diverse spline model library, which covers the force characteristics of different regions of the blade; Acquire real-time wind speed and wind direction data in the wind farm operating environment, and transfer the real-time wind speed and wind direction data as input parameters to the spline torsion force control model to calculate the optimal torsion force of the blade under the current wind conditions; Based on historical wind speed data and current wind condition change trends, a data-driven prediction algorithm is used to predict future wind speed and wind direction changes, and the optimal torsion force is adjusted in combination with the multi-strip model library; According to the adjusted optimal twisting force, a twisting control instruction is generated, and the twisting angle and force of the blade are adjusted.
[0006] Furthermore, based on the spline stress and deformation characteristic data under different wind speeds and force conditions, a torsional force control model for the relationship between blade force and wind conditions in different areas of the blade is established to generate a variety of spline model libraries, including: A plurality of splines are sampled from different key areas of the wind turbine blade, and the splines are used to reflect the local stress characteristics of the blade under different working conditions; Performing mechanical tests on each of the splines, the tests including collecting stress, strain and deformation behavior data under various wind speeds, wind directions, torques and stress conditions; According to the experimental data of each of the splines, a number of independent torsional force control models are established, each model is used to describe the force and torsional response of a specific spline area under specific wind conditions; The independent torsion force control models are integrated into a diverse model library, and the diverse model library contains a plurality of local force models for adapting to different wind conditions.
[0007] Furthermore, the optimal torsional force of the blade under the current wind conditions is calculated, including: Determine the force-bearing area of the blade under the current wind conditions according to the wind speed and wind direction data, wherein the force-bearing area is divided into different structural areas of the blade according to the spline model; According to the mechanical properties of the corresponding area in the spline model, the stress-strain relationship of the current area is calculated, and the force condition of the blade under the current wind speed is calculated; The force and deformation data of each area are integrated to calculate the overall torsional force of the blade and generate an optimal torsional force value.
[0008] Furthermore, the stress and deformation data of each area are integrated by using the partition analysis combined with the weighted average method.
[0009] Furthermore, based on historical wind speed data and current wind condition change trends, a data-driven prediction algorithm is used to predict future wind speed and wind direction changes, and combined with the diverse strip model library, the optimal torsion force is adjusted, including: Collect historical wind speed and direction data during the operation of the wind farm, and establish a historical wind condition change trend model to identify long-term wind speed and wind direction change patterns and periodic patterns; Collect current wind speed and direction data, use sliding window technology to analyze the wind speed and wind direction change rate within a specified time period, and calculate the change trend of the current wind conditions; Combining the historical wind condition change trend model with the current wind condition change trend, using a data-driven prediction algorithm to predict future wind speed and wind direction changes, and generating wind condition prediction data for a period of time in the future; The predicted future wind speed and wind direction data are input into the variety strip model library, and the optimal torsional force of the blade under the future wind conditions is calculated according to the relationship between the force and wind conditions for different blade areas in the variety strip model library.
[0010] Furthermore, the window size of the sliding window technology is set to 10 minutes and the step size is 1 minute.
[0011] Furthermore, the ARIMA model is used for short-term wind speed prediction, and the LSTM neural network model is used for long-term prediction.
[0012] Further, according to the adjusted optimal twisting force, a twisting control instruction is generated, and the twisting angle and force of the blade are adjusted, including: According to the optimal torsion force calculated by the diversity model library, the optimal torsion force value is converted into a corresponding torsion control signal, and the control signal is used to adjust the torsion angle and force of the blade; The generated torsion control signal is transmitted to the blade actuator through a communication protocol, and the blade actuator adjusts the torsion angle and applied torque of the blade in real time according to the received torsion control signal; The blade torsion angle and applied torque value are monitored in real time. If there is a deviation between the actual torsion state detected and the target torsion state, correction is performed through the feedback loop.
[0013] A spline torsion force control system, the system comprising: A multi-strip model library generation module, based on the spline stress and deformation characteristic data under different wind speeds and force conditions, establishes a torsion force control model for the relationship between blade force and wind conditions in different regions of the blade, and generates a multi-strip model library, wherein the multi-strip model library covers the force characteristics of different regions of the blade; The optimal torsional force calculation module obtains the real-time wind speed and wind direction data in the wind farm operating environment, and transmits the real-time wind speed and wind direction data as input parameters to the spline torsional force control model to calculate the optimal torsional force of the blade under the current wind conditions; An optimal torsion force adjustment module, based on historical wind speed data and current wind condition change trends, uses a data-driven prediction algorithm to predict future wind speed and wind direction changes, and adjusts the optimal torsion force in combination with the diverse strip model library; The blade control instruction generation module generates a torsion control instruction according to the adjusted optimal torsion force, and adjusts the blade torsion angle and force.
[0014] Furthermore, the blade control instruction generating module includes: A control signal conversion unit, which converts the optimal torsion force value into a corresponding torsion control signal according to the optimal torsion force calculated by the diversity model library, wherein the control signal is used to adjust the torsion angle and force of the blade; A control signal transmission unit transmits the generated torsion control signal to a blade actuator through a communication protocol, and the blade actuator adjusts the torsion angle and applied torque of the blade in real time according to the received torsion control signal; The torsion state correction unit monitors the torsion angle of the blade and the applied torque value in real time. If there is a deviation between the actual torsion state detected and the target torsion state, correction is performed through a feedback loop.
[0015] The technical solution of the present invention can achieve the following technical effects: It effectively solves the problems of insufficient accuracy and slow response speed of traditional torsion force control methods when wind speed changes frequently, realizes high-precision dynamic torsion control of wind turbine blades, and improves efficiency and stability. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0017] Figure 1 It is a flow chart of a spline torsion force control method; Figure 2 A schematic diagram of the process of generating a diverse model library; Figure 3 A schematic diagram of the process for calculating the optimal twisting force of the blade under the current wind conditions; Figure 4 A schematic diagram of a process for adjusting the optimal torsional force; Figure 5 The figure is a schematic diagram of the process for adjusting the blade twisting angle and force. DETAILED DESCRIPTION
[0018] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.
[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.
[0020] Embodiment 1 like Figure 1 As shown, the present invention provides a spline torsion force control method, the method comprising: S1: Based on the spline stress and deformation characteristic data under different wind speeds and force conditions, a torsional force control model for the relationship between blade force and wind conditions in different regions of the blade is established to generate a multi-strip model library that covers the force characteristics of different regions of the blade; Specifically, the purpose of this step is to establish an accurate blade torsion force control model, generate a variety of spline model library by analyzing the stress and deformation characteristics of splines under different wind speeds and force conditions, and ensure that the force characteristics of each area of the blade are covered. Through this regional refinement modeling, the force distribution of the blade under complex wind conditions can be more accurately reflected, and the accuracy of torsion force control can be optimized, thereby improving the response performance and stability of the blade under different wind conditions, which provides basic data support for subsequent real-time control and prediction.
[0021] S2: Acquire the real-time wind speed and wind direction data in the wind farm operating environment, and pass the real-time wind speed and wind direction data as input parameters to the spline torsion force control model to calculate the optimal torsion force of the blade under the current wind conditions; Specifically, by obtaining the current real-time wind speed and wind direction data of the wind farm and passing these data as input parameters to the spline torsion force control model, the optimal torsion force of the blades under the current wind conditions is calculated in real time. This process ensures that the blades can be dynamically adjusted according to actual environmental conditions and their torsion angle and force can be changed in time to maximize wind energy capture efficiency, reduce force loss, and improve the operating stability and energy efficiency of the overall system.
[0022] S3: Based on historical wind speed data and current wind condition change trends, a data-driven prediction algorithm is used to predict future wind speed and wind direction changes, and the optimal twisting force is adjusted in combination with a diverse model library; Specifically, a data-driven prediction algorithm is used, combined with historical wind speed data and the changing trends of current wind conditions, to predict future changes in wind speed and direction. Through this prediction, combined with a diverse model library, the torsional force of the blades can be adjusted in advance to adapt to the predicted future wind conditions. Such forward-looking adjustments help the blades maintain optimal performance under changing environmental conditions, optimize energy capture efficiency, and reduce mechanical stress caused by sudden changes in wind speed, thereby improving the operating efficiency and durability of the blades.
[0023] S4: Generate a torsion control instruction according to the adjusted optimal torsion force, and adjust the torsion angle and force of the blade.
[0024] Specifically, control instructions are generated based on the adjusted optimal torsional force, specifically directing the blade actuator to adjust the torsional angle and force. This ensures that the blades can be accurately adjusted according to the optimal torsional force calculated in real time to adapt to current or predicted wind conditions. Through such adjustments, the blades can more effectively capture wind energy and reduce mechanical stress and fatigue.
[0025] It effectively solves the problems of insufficient accuracy and slow response speed of traditional torsion force control methods when wind speed changes frequently, realizes high-precision dynamic torsion control of wind turbine blades, and improves efficiency and stability.
[0026] As a preferred embodiment of the above, Figure 2 As shown in the figure, based on the spline stress and deformation characteristic data under different wind speeds and force conditions, a torsional force control model for the relationship between blade force and wind conditions in different areas of the blade is established, and a variety of spline model libraries are generated, including: A10: Several splines are sampled from different key areas of the wind turbine blade. The splines are used to reflect the local stress characteristics of the blade under different working conditions. A20: Mechanical testing of each spline, including the collection of stress, strain and deformation behavior data under various wind speeds, wind directions, torques and stress conditions; A30: Based on the experimental data of each spline, several independent torsion force control models are established. Each model is used to describe the force and torsion response of a specific spline area under specific wind conditions. A40: Integrate the independent torsion force control models into a diverse model library, wherein the diverse model library includes multiple local force models for adapting to different wind conditions.
[0027] First, several splines are sampled from different key areas of the wind turbine blade (such as the root, middle section, tip, etc.). Each spline represents the material properties and mechanical response behavior of the area. The splines in different areas are used to reflect the local stress of the blade under various wind speeds, wind directions and stress conditions. Since the stress, torque and other mechanical loads of different parts of the blade are very different when the wind farm is running, sampling from these key areas can capture the unique stress characteristics of each area; Next, these splines are mechanically tested, and the test content includes the stress, strain and deformation behavior of the splines under different wind speeds, wind directions, torques and stress conditions. Through the test, detailed mechanical response data of each spline under different conditions can be collected. These tests simulate the stress and deformation of the spline when the wind turbine blade is actually working, and provide accurate data on material properties, elasticity, rigidity and deformation characteristics. This step is very important because these data are the basis for the subsequent establishment of the control model; According to the experimental data of each spline, several independent torsional force control models are established for different areas of the blade, and each model specifically describes the force and torsional response of the area where the spline is located under specific wind conditions. For example, the model at the root reflects the stress-strain relationship under high torque and strong force, while the model at the tip of the blade may reflect more the lateral stress caused by lower torque and wind force. The model of each area is independent, and the control strategy is optimized based on its specific mechanical response behavior; finally, all independent torsional force control models are integrated into a unified multi-strip model library, which covers the force characteristics and torsional response of each area of the blade, and can select the most suitable model for real-time adjustment according to wind conditions. This means that when the wind power system obtains real-time wind speed and wind direction data, the control system can call different local models in the model library to accurately calculate and adjust the force conditions of each area of the blade.
[0028] As a preferred embodiment of the above, Figure 3 As shown, the optimal twisting force of the blade under the current wind conditions is calculated, including: B10: Determine the stress area of the blade under the current wind conditions based on the wind speed and wind direction data, and divide the stress area into different structural areas of the blade based on the spline model; B20: Calculate the stress-strain relationship of the current area according to the mechanical properties of the corresponding area in the spline model, and calculate the force condition of the blade under the current wind speed; B30: The force and deformation data of each area are integrated to calculate the overall torsional force of the blade and generate an optimal torsional force value.
[0029] Specifically, first, according to the real-time wind speed and direction data obtained, the main stress area of the wind turbine blade under the current wind conditions is determined. Due to the different structures and positions, different parts of the blade (such as the root, middle section, tip, etc.) are subjected to different stresses when the wind speed and wind direction change. This step analyzes the current wind speed and wind direction, and divides the blade into multiple structural areas based on the previously established spline model. These areas correspond to different mechanical performances. For example, the root of the blade is subjected to more torque, while the tip may be more subjected to lateral forces caused by wind speed. After determining the stress conditions of each area of the blade, the stress of these areas is calculated using the spline model. Strain relationship, the mechanical characteristics of each area have been established in the spline model, so this step uses these models, combined with real-time wind speed conditions, to calculate the stress and strain of each area of the blade under the current wind conditions. These calculations use mechanical formulas to process the deformation and force conditions of the blade under the action of wind, thereby reflecting the specific response behavior of different areas under the current wind conditions; finally, the stress-strain data of different areas are combined to generate an overall torsional force value, which represents the torque that should be applied to the blade under the current wind conditions to optimize the angle of the blade, ensure that the blade can operate stably and efficiently under the action of wind, and reduce structural stress and fatigue.
[0030] As a preferred embodiment of the above, the stress and deformation data of each area are comprehensively analyzed by using a partition analysis combined with a weighted average method.
[0031] Specifically, first, according to the structural characteristics of the blade, it is divided into multiple different stress areas (such as the root, middle section, tip, etc. of the blade). For each area, the stress-strain relationship of the area under the current wind speed and wind direction is calculated based on the spline model to evaluate its stress and deformation under the current wind conditions. The stress characteristics of each area are different. For example, the root of the blade usually bears a larger torque, while the tip bears more lateral force caused by the wind speed. Therefore, the stress and deformation of each area will be analyzed separately to accurately reflect the mechanical response of different areas. After obtaining the stress and deformation data of each area, the weighted average method is used to integrate the results of each area. The weight of each area is allocated according to their importance in the overall structure and the amount of stress they bear. For example, the root of the blade may be assigned a higher weight due to the larger force it bears, while the weight of the tip area of the blade is relatively small. The specific calculation method is to take a weighted average of the torsional forces of each area to calculate the optimal torsional force of the blade as a whole.
[0032] As a preferred embodiment of the above, Figure 4 As shown, step S3, based on the historical wind speed data and the current wind condition change trend, using the data-driven prediction algorithm to predict the future wind speed and wind direction changes, and combining with the multi-strip model library, adjusting the optimal torsion strength includes: S31: Collect historical wind speed and wind direction data during the operation of the wind farm, and establish a historical wind condition change trend model to identify long-term wind speed and wind direction change patterns and periodic patterns; S32: Collect current wind speed and wind direction data, use sliding window technology to analyze the wind speed and wind direction change rate within a specified time period, and calculate the change trend of the current wind conditions; S33: Combine the historical wind condition change trend model with the current wind condition change trend, use data-driven prediction algorithms to predict future wind speed and wind direction changes, and generate wind condition forecast data for a period of time in the future; S34: inputting the predicted future wind speed and wind direction data into the diversity strip model library, and calculating the optimal torsional force of the blade under the future wind conditions according to the relationship between the force and wind conditions for different blade areas in the diversity strip model library.
[0033] Specifically, detailed data collection is carried out from the historical wind speed and wind direction data accumulated during the operation of the wind farm. These data usually cover changes in different seasons, climates and years, reflecting the long-term wind speed and wind direction fluctuations in the area where the wind farm is located. By analyzing these data, the long-term change patterns and periodic patterns of wind speed and wind direction can be identified, such as seasonal fluctuations, day and night wind speed differences, and strong wind trends in specific periods of time. Based on these analysis results, a historical wind condition change trend model is established. This model captures the periodic changes in wind speed and wind direction, serves as the basis for future wind condition predictions, and provides a reliable basis for subsequent adjustments; real-time collection of wind speed and wind direction data for the current wind farm, Wind speed and direction sensors are used to record changes in current wind speed and direction at fixed time intervals. In order to evaluate the changing trend of short-term wind conditions, the sliding window technology is used to analyze the wind speed and direction data in a certain period of time in the past. The sliding window method can calculate the rate of change of wind speed and wind direction by smoothing the data in a short period of time, thereby capturing the changing trend of the current wind conditions; the historical wind condition change trend model is combined with the current wind condition change trend, and a data-driven prediction algorithm is used to predict future changes in wind speed and wind direction. The historical wind condition model provides long-term wind speed and wind direction laws, while the current wind condition change trend captures the short-term wind speed and direction changes in the current wind farm. By combining the two, wind speed and wind direction forecast data for a period of time in the future is generated. The forecast data covers changes in wind conditions in the next few minutes, hours or even longer, accurately reflects possible changing trends in wind speed and wind direction in the future, and helps make forward-looking adjustments; the predicted future wind speed and wind direction data are input into the multi-strip model library, which contains force models for different areas of the blade (such as the root, middle section, tip, etc.), and calculates the stress and deformation of each area based on different wind conditions. According to the future wind speed and wind direction data, the multi-strip model library calculates the force condition of each area under future wind conditions, and generates the optimal torsional force of the entire blade. By combining the calculation results of each area, the generated torsional force value ensures that the blade can maintain the best force state under the predicted future wind conditions, thereby reducing mechanical stress and optimizing the angle and performance of the blade. The advance calculation of the torsional force helps the wind turbine blades to make adjustments before the wind conditions change, thereby improving operating efficiency and stability.
[0034] As a preference of the above embodiment, the window size of the sliding window technology is set to 10 minutes and the step size is 1 minute.
[0035] Specifically, a 10-minute window size can effectively smooth out short-term fluctuations in wind speed and direction, capture relatively stable wind condition change trends, and avoid noise interference. The 1-minute step size ensures high-frequency updates, allowing the latest wind condition information to be obtained in real time every minute, improving the timeliness and accuracy of the response. This setting ensures that the system can quickly and sensitively adjust the torsion force of the blades to respond to changes in wind speed and direction while maintaining real-time and stability.
[0036] As a preferred embodiment of the above embodiment, the ARIMA model is used for short-term wind speed prediction, and the LSTM neural network model is used for long-term prediction.
[0037] Specifically, the ARIMA model is used for short-term wind speed forecasting because it is good at handling linear trends and seasonal fluctuations in the short term, and is suitable for accurately predicting wind speed in the next few minutes or hours based on current wind speed data and its historical changes. Through time series analysis, it can capture short-term changing trends in wind speed and provide stable short-term forecasts; while the LSTM neural network model is used for long-term forecasting. LSTM (Long Short-Term Memory Network) is suitable for capturing the complex nonlinear characteristics of wind speed changes over time due to its advantages in handling long-term dependencies, especially for identifying long-term wind speed fluctuations and periodic changes. By combining the short-term accuracy of the ARIMA model and the long-term prediction ability of the LSTM model, it can effectively predict wind speed changes on different time scales to ensure the optimal adjustment of wind turbine blades under different wind conditions.
[0038] As a preferred embodiment of the above, Figure 5 As shown, step S4 generates a torsion control instruction according to the adjusted optimal torsion force, and adjusts the torsion angle and force of the blade, including: S41: according to the optimal torsion force calculated by the diversity model library, converting the optimal torsion force value into a corresponding torsion control signal, the control signal is used to adjust the torsion angle and force of the blade; S42: transmitting the generated torsion control signal to the blade actuator through the communication protocol, and the blade actuator adjusts the torsion angle and applied torque of the blade in real time according to the received torsion control signal; S43: monitor the torsion angle of the blade and the applied torque value in real time, and if there is a deviation between the actual torsion state detected and the target torsion state, make correction through a feedback loop.
[0039] Specifically, the optimal torsion force value is used as input, and after appropriate algorithms and conversion mechanisms (such as proportional control or PID adjustment), a corresponding control signal is generated. The control signal represents the specific torsion angle and force that the blade actuator needs to adjust. This signal can be a voltage signal, a current signal or a digital signal. After signal processing, it can directly control the action of the actuator so that the torsion of the blade can match the optimal force, thereby ensuring the optimization of the operation of the wind power system; the generated torsion control signal is transmitted to the blade actuator through a specific communication protocol. The communication protocol may include a wired protocol (such as CAN bus) or a wireless transmission protocol to ensure that the control signal can be transmitted to the actuator quickly and accurately. After receiving the control signal, the blade actuator responds to the signal instruction in real time to adjust the torsion of the blade. The actuator adjusts the attitude of the blade according to the control signal, so that the blade can adapt to the current wind speed and wind direction changes to ensure the optimal stress state; the actual torsion angle and applied torque value of the blade are monitored in real time by the sensor, and the feedback data provided by the sensor is compared with the preset target torsion state. If there is a difference or deviation between the monitoring data and the target state, the feedback loop immediately starts the correction mechanism. Through the feedback loop, the system will adjust the torsion control signal according to the deviation to make the actual state of the blade as close to the target torsion state as possible. In this way, the system can dynamically adjust the attitude of the blade to ensure that it can maintain the optimal stress and operating state when the wind speed changes. This closed-loop feedback control mechanism can significantly improve the accuracy and response speed of the system, reduce mechanical fatigue, and optimize the overall performance of the wind power system.
[0040] Embodiment 2 Based on the same inventive concept as the spline torsion force control method in the aforementioned embodiment, the present invention further provides a spline torsion force control system, the system comprising: The module for generating a multi-strip model library is based on the stress and deformation characteristic data of splines under different wind speeds and force conditions. It establishes a torsional force control model for the relationship between blade force and wind conditions in different areas of the blade and generates a multi-strip model library. The multi-strip model library covers the force characteristics of different areas of the blade. The optimal torsional force calculation module obtains the real-time wind speed and wind direction data in the wind farm operating environment. The real-time wind speed and wind direction data are passed as input parameters to the spline torsional force control model to calculate the optimal torsional force of the blade under the current wind conditions. The optimal torsion force adjustment module uses data-driven prediction algorithms to predict future wind speed and wind direction changes based on historical wind speed data and current wind condition change trends, and adjusts the optimal torsion force in combination with a variety of model libraries; The blade control instruction generation module generates a torsion control instruction according to the adjusted optimal torsion force, and adjusts the blade torsion angle and force.
[0041] The above control system in the present invention can effectively implement the spline torsion force control method, and the technical effects that can be achieved are as described in the above embodiments, which will not be repeated here.
[0042] As a preferred embodiment of the above, the blade control instruction generating module includes: A control signal conversion unit converts the optimal torsion force value into a corresponding torsion control signal according to the optimal torsion force calculated by the diverse strip model library, and the control signal is used to adjust the torsion angle and force of the blade; A control signal transmission unit transmits the generated torsion control signal to the blade actuator through a communication protocol, and the blade actuator adjusts the torsion angle and applied torque of the blade in real time according to the received torsion control signal; The torsion state correction unit monitors the torsion angle of the blade and the applied torque value in real time. If there is a deviation between the actual torsion state detected and the target torsion state, correction is performed through a feedback loop.
[0043] Similarly, the above-mentioned optimization schemes for the system can also respectively achieve the optimization effects corresponding to the method in Example 1, which will not be repeated here.
[0044] Although the present application has been described in conjunction with specific features and embodiments thereof, it is obvious that various modifications and combinations may be made thereto without departing from the spirit and scope of the present application. Accordingly, this specification and the accompanying drawings are merely exemplary illustrations of the present application as defined therein, and are deemed to have covered any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.
Claims
1. A method for controlling the torsion force of a spline, characterized in that: include: Based on the spline stress and deformation characteristic data under different wind speeds and force conditions, a torsional force control model for the relationship between blade force and wind conditions in different regions of the blade is established to generate a diverse spline model library, which covers the force characteristics of different regions of the blade; Acquire real-time wind speed and wind direction data in the wind farm operating environment, and transfer the real-time wind speed and wind direction data as input parameters to the spline torsion force control model to calculate the optimal torsion force of the blade under the current wind conditions; Based on historical wind speed data and current wind condition change trends, a data-driven prediction algorithm is used to predict future wind speed and wind direction changes, and the optimal torsion force is adjusted in combination with the multi-strip model library; According to the adjusted optimal twisting force, a twisting control instruction is generated, and the twisting angle and force of the blade are adjusted.
2. The spline torsion force control method according to claim 1, characterized in that: Based on the spline stress and deformation characteristic data under different wind speeds and force conditions, a torsional force control model for the relationship between blade force and wind conditions in different areas of the blade is established to generate a variety of spline model libraries, including: A plurality of splines are sampled from different key areas of the wind turbine blade, and the splines are used to reflect the local stress characteristics of the blade under different working conditions; Performing mechanical tests on each of the splines, the tests including collecting stress, strain and deformation behavior data under various wind speeds, wind directions, torques and stress conditions; According to the experimental data of each of the splines, a number of independent torsional force control models are established, each model is used to describe the force and torsional response of a specific spline area under specific wind conditions; The independent torsion force control models are integrated into a diverse model library, and the diverse model library contains a plurality of local force models for adapting to different wind conditions.
3. The spline torsion force control method according to claim 1, characterized in that: Calculate the optimal twisting force of the blade under the current wind conditions, including: Determine the force-bearing area of the blade under the current wind conditions according to the wind speed and wind direction data, wherein the force-bearing area is divided into different structural areas of the blade according to the spline model; According to the mechanical properties of the corresponding area in the spline model, the stress-strain relationship of the current area is calculated, and the force condition of the blade under the current wind speed is calculated; The force and deformation data of each area are integrated to calculate the overall torsional force of the blade and generate an optimal torsional force value.
4. The spline torsion force control method according to claim 3, characterized in that: The stress and deformation data of each area are comprehensively analyzed by using partition analysis combined with the weighted average method.
5. The spline torsion force control method according to claim 1, characterized in that: Based on historical wind speed data and current wind condition change trends, a data-driven prediction algorithm is used to predict future wind speed and wind direction changes, and combined with the multi-strip model library, the optimal torsion force is adjusted, including: Collect historical wind speed and direction data during the operation of the wind farm, and establish a historical wind condition change trend model to identify long-term wind speed and wind direction change patterns and periodic patterns; Collect current wind speed and direction data, use sliding window technology to analyze the wind speed and wind direction change rate within a specified time period, and calculate the change trend of the current wind conditions; Combining the historical wind condition change trend model with the current wind condition change trend, using a data-driven prediction algorithm to predict future wind speed and wind direction changes, and generating wind condition prediction data for a period of time in the future; The predicted future wind speed and wind direction data are input into the variety strip model library, and the optimal torsional force of the blade under the future wind conditions is calculated according to the relationship between the force and wind conditions for different blade areas in the variety strip model library.
6. The spline torsion force control method according to claim 5, characterized in that: The window size of the sliding window technique is set to 10 minutes and the step size is 1 minute.
7. The spline torsion force control method according to claim 5, characterized in that: The ARIMA model is used for short-term wind speed forecasting, and the LSTM neural network model is used for long-term forecasting.
8. The spline torsion force control method according to claim 1, characterized in that: According to the adjusted optimal torsion force, a torsion control instruction is generated, and the torsion angle and force of the blade are adjusted, including: According to the optimal torsion force calculated by the diversity model library, the optimal torsion force value is converted into a corresponding torsion control signal, and the control signal is used to adjust the torsion angle and force of the blade; The generated torsion control signal is transmitted to the blade actuator through a communication protocol, and the blade actuator adjusts the torsion angle and applied torque of the blade in real time according to the received torsion control signal; The blade torsion angle and applied torque value are monitored in real time. If there is a deviation between the actual torsion state detected and the target torsion state, correction is performed through the feedback loop.
9. A spline torsion force control system, characterized in that: The system comprises: A multi-strip model library generation module, based on the spline stress and deformation characteristic data under different wind speeds and force conditions, establishes a torsion force control model for the relationship between blade force and wind conditions in different regions of the blade, and generates a multi-strip model library, wherein the multi-strip model library covers the force characteristics of different regions of the blade; The optimal torsional force calculation module obtains the real-time wind speed and wind direction data in the wind farm operating environment, and transmits the real-time wind speed and wind direction data as input parameters to the spline torsional force control model to calculate the optimal torsional force of the blade under the current wind conditions; An optimal torsion force adjustment module, based on historical wind speed data and current wind condition change trends, uses a data-driven prediction algorithm to predict future wind speed and wind direction changes, and adjusts the optimal torsion force in combination with the diverse strip model library; The blade control instruction generation module generates a torsion control instruction according to the adjusted optimal torsion force, and adjusts the blade torsion angle and force.
10. The spline torsion force control system according to claim 9, characterized in that: The blade control instruction generation module includes: A control signal conversion unit, which converts the optimal torsion force value into a corresponding torsion control signal according to the optimal torsion force calculated by the diversity model library, wherein the control signal is used to adjust the torsion angle and force of the blade; A control signal transmission unit transmits the generated torsion control signal to a blade actuator through a communication protocol, and the blade actuator adjusts the torsion angle and applied torque of the blade in real time according to the received torsion control signal; The torsion state correction unit monitors the torsion angle of the blade and the applied torque value in real time. If there is a deviation between the actual torsion state detected and the target torsion state, correction is performed through a feedback loop.