Intelligent control device for land wind power spoiler

Abstract

The invention relates to the technical field of wind power generation, in particular to a land wind power spoiler intelligent control device which comprises a wind condition monitoring module, an artificial intelligence center control module and a plurality of modularized spoiler units. The wind condition monitoring module is installed at the top end of a wind power tower, and a combined sensor is adopted for collecting wind condition data in real time; data are transmitted in a specific mode; the artificial intelligence central control module is mounted at the bottom of the tower drum, is internally provided with a high-performance processing assembly, predicts wind regime changes by means of a deep learning model, and generates a control strategy in combination with a hybrid optimization algorithm; the modularized turbulent flow units are fixed to the outer side of a tower barrel through quick-release structures, the turbulent flow plates are made of high-strength materials and provided with bionic structures, the driving component drives the turbulent flow plates to adjust the opening angle, and the adjusting precision is ensured. The spoiler can be quickly locked to a safe angle when encountering an extreme wind condition, normal operation is gradually recovered through an observation period after the wind condition is relieved, the wind speed distribution in a wind power plant can be effectively improved, and the influence of turbulent flow on a wind turbine generator is reduced.

Description

Technical Field

[0001] This invention belongs to the field of wind power generation technology, specifically relating to an intelligent control device for onshore wind turbine spoilers. Background Technology

[0002] With the continuous growth of global demand for renewable energy, wind energy, as an important clean energy source, is playing an increasingly important role in the energy structure transformation. Onshore wind farms, as the main form of wind energy utilization, face numerous technical challenges in their construction and operation, one of which is the uneven wind speed distribution and turbulence within the wind farm. These problems not only affect the power generation efficiency of wind turbines but may also lead to mechanical damage and shortened lifespan.

[0003] In the layout and design of traditional wind turbines, physical models and empirical data are typically relied upon to optimize the arrangement of turbines and the utilization of wind resources. However, these methods have limitations when dealing with complex terrain and variable wind conditions. For example, the undulating terrain and obstructions can lead to uneven local wind speed distribution, thus affecting the power generation performance of the wind turbines. In addition, wind turbulence places higher demands on the stability and mechanical strength of the wind turbines.

[0004] Against this backdrop, turbulence-induced flow disturbances have gradually gained widespread attention as an effective solution. By altering the direction and speed of airflow, turbulence-induced flow disturbances can significantly improve the wind speed distribution within a wind farm and reduce the impact of turbulence on wind turbines. Traditional turbulence-induced flow disturbances are mostly fixed structures, with limited effectiveness and difficulty in adapting to complex and changing wind conditions.

[0005] In view of this, the present invention is hereby proposed. Summary of the Invention

[0006] To address the aforementioned technical problems in the existing technology, this invention provides an intelligent control device for onshore wind turbine spoilers, which can effectively improve the wind speed distribution inside the wind farm, reduce the impact of turbulence on the wind turbine, and thus improve the power generation efficiency and operational stability of the wind turbine.

[0007] To achieve the above objectives, the technical solution of the present invention is as follows: A smart control device for onshore wind turbine spoilers, comprising: The wind condition monitoring module is installed at a preset wind measurement location on the wind turbine tower to collect wind condition data in real time. The artificial intelligence central control module is installed at a preset installation position on the wind turbine tower. It contains a central control unit and multiple drive components. The central control unit is communicatively connected to the wind condition monitoring module and is used to analyze the wind condition data based on artificial intelligence algorithms and generate optimized control strategies. Multiple modular turbulence-disrupting units are circumferentially fixed to the outside of the wind turbine tower by a fixing mechanism. Each turbulence-disrupting unit includes an adjustable turbulence-disrupting component, an actuating component, and a transmission component. The actuating component is communicatively connected to the central control unit and is used to receive control commands. The actuating component is connected to the actuating component and is driven by the actuating component to adjust the opening angle of the turbulence-disrupting component through the transmission component.

[0008] Furthermore, the wind condition monitoring module is a wind speed and direction monitor, which is installed at the top of the wind turbine tower; the wind speed and direction monitor adopts a combination of a three-cup wind speed sensor and an ultrasonic wind direction sensor, with a measurement range of 0-60m / s, an accuracy of ±0.1m / s, a sampling frequency of 10Hz, and communicates with the central control unit through optical fiber.

[0009] Furthermore, the artificial intelligence central control module is a central control integrated box, which is installed at a preset height above the ground at the bottom of the tower; The outer shell of the central control integrated box is made of corrosion-resistant material and the surface is treated with multiple layers of anti-corrosion. The driving component is a servo driver, and the central control unit is connected to the servo driver via an industrial Ethernet protocol, supporting data transmission at a preset rate and millisecond-level command response.

[0010] Furthermore, the central control integration box is connected to the execution component via a double-shielded waterproof cable with a rated protection level of IP67. All cables are arranged in dedicated cable trays inside the tower. The cable trays are made of aluminum alloy, lined with flame-retardant and heat-insulating material, and the surface is treated with anti-corrosion. Anti-vibration clamps are installed at key nodes.

[0011] Furthermore, the fixing mechanism is a quick-release ring hoop, made of aluminum alloy with surface treatment, and lined with flexible protective material, forming a grid structure with the transmission component to wrap around the wind turbine tower. The quick-release ring is fastened with bolts, and the installation time for a single ring does not exceed the preset time.

[0012] Furthermore, the aerodynamic component is a streamlined aerodynamic plate, made of high-strength aluminum alloy through heat treatment, and its surface is precision polished. The outer surface of the spoiler is provided with biomimetic microstructures, which are regularly arranged micron-sized pits. The diameter, depth and arrangement of the pits meet the preset parameter range.

[0013] Furthermore, the actuating component is a servo motor, and the transmission component is a rotating shaft; the servo motor uses an absolute encoder, and the control accuracy reaches ±0.1°; The servo motor and the rotating shaft are connected by a high-strength flange, and the flatness error of the flange connection surface does not exceed a preset threshold; the opening angle adjustment range of the turbulence component is 0° to 90°.

[0014] Furthermore, the central control unit adopts a multi-core processor architecture, is equipped with a preset capacity of running memory and solid-state storage, and the control system software is developed based on a real-time operating system; The central control unit analyzes wind data using an LSTM recurrent neural network model to predict wind field changes over a preset time period. Based on the prediction results, the system begins adjusting the turbulence units a preset time in advance. When preset extreme wind conditions are detected, the system triggers a safety mode within a preset time period, forcibly locking all turbulence units to a preset safety angle. After the extreme wind conditions are resolved, the system maintains a preset observation period, and then gradually releases the turbulence unit at a preset rate to restore the normal dynamic control mode.

[0015] Furthermore, the optimization strategy generation module of the central control unit adopts a hybrid optimization algorithm, first performing a global search through a genetic algorithm, and then performing fine optimization through a reinforcement learning algorithm; the reinforcement learning algorithm learns the optimal control strategy through the Q-learning algorithm, and the reward function comprehensively considers three objectives: vortex street energy dispersion, tower wind pressure peak and system energy consumption.

[0016] Furthermore, it is equipped with a backup power system that can maintain operation for a preset duration when the main power is interrupted.

[0017] Compared with existing technologies, the intelligent control device for onshore wind turbine spoilers provided by this invention includes: a wind condition monitoring module, an artificial intelligence central control module, and multiple modular spoiler units. The wind condition monitoring module is installed at the top of the wind turbine tower, uses combined sensors to collect wind condition data in real time, and transmits the data in a specific way. The artificial intelligence central control module is installed at the bottom of the tower, with a corrosion-resistant outer shell and protective treatment. It has built-in high-performance processing components, uses a deep learning model to predict wind condition changes, and generates control strategies by combining a hybrid optimization algorithm. The modular spoiler units are fixed to the outside of the tower through a quick-release structure. The spoilers are made of high-strength materials and have a biomimetic structure. The opening angle is adjusted by a drive component to ensure adjustment accuracy. In the event of extreme wind conditions, the spoilers can be quickly locked to a safe angle. After the wind conditions are relieved, normal operation is gradually restored after an observation period. This can effectively improve the wind speed distribution inside the wind farm and reduce the impact of turbulence on the wind turbine units. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the installation on a wind turbine tower provided in an embodiment of the present invention; Figure 2A schematic diagram showing different opening angles of the spoiler provided in an embodiment of the present invention; Figure 3 This is a schematic diagram illustrating the connection between the servo motor and the rotating shaft provided in an embodiment of the present invention; Figure 4 A schematic diagram of a spoiler provided in an embodiment of the present invention; Figure 5 This is an architecture diagram of the control system provided in an embodiment of the present invention. Attached image description: 1. Wind turbine tower; 2. Tower foundation; 3. Wind speed and direction integrated monitoring instrument; 4. Central control integrated box; 5. Servo motor; 6. Rotating shaft; 7. Circumferential fixing device; 8. Spoiler; 9. Flange connection plate; 801. Bionic shark pattern. Detailed Implementation

[0020] The technical solution of the present invention will be clearly described below with reference to the accompanying drawings. Obviously, the described embodiments are not all embodiments of the present invention. All other embodiments obtained by those skilled in the art without creative effort are within the protection scope of the present invention.

[0021] It should be noted that, unless otherwise specifically stated, the relative arrangement and numerical expressions of the components and steps described in these embodiments should not be construed as limiting the scope of the invention.

[0022] The following description of exemplary embodiments is merely illustrative and is not intended to limit the invention or its application or use in any way. Techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail herein, but where applicable, such techniques, methods, and apparatus should be considered part of this specification.

[0023] Example 1 See Figure 1 , Figure 1 The present invention proposes an intelligent control device for onshore wind turbine spoilers. Through the collaborative work of a wind condition monitoring module, an artificial intelligence central control module, and multiple modular spoiler units, it achieves adaptive wind condition adjustment, effectively improving the wind resistance performance and power generation efficiency of wind turbine towers. Its specific structure and working method are as follows: The device consists of three core components: a wind condition monitoring module, an artificial intelligence central control module, and multiple modular airflow disturbance units. These are circumferentially fixed to the outside of the wind turbine tower via a fixing mechanism, forming a complete "perception-decision-execution" closed-loop control system. Each component is connected via a dedicated communication link and mechanical structure, ensuring stable signal transmission and precise mechanical movements. Specifically, it includes: M1, Wind Condition Monitoring Module The wind condition monitoring module employs an anemometer and wind direction monitor, installed at the optimal wind measurement location at the top of the wind turbine tower, for real-time acquisition of wind field data. This monitor uses a combination of a three-cup anemometer and an ultrasonic wind direction sensor, with a measurement range covering 0-60 m / s, a measurement accuracy of ±0.1 m / s, and a sampling frequency of 10 Hz. It can simultaneously acquire key parameters such as three-dimensional wind speed, wind direction, turbulence intensity, and gust frequency. The monitor establishes a communication connection with the artificial intelligence central control module via fiber optic cable, ensuring that raw wind condition data is transmitted to the central control unit in real-time and without loss.

[0024] M2, Artificial Intelligence Central Control Module Installed at a predetermined installation location on the wind turbine tower, for example, at a height of 1.5 meters above the ground, to facilitate later maintenance and operation; it contains a central control unit and multiple drive components. The central control unit is communicatively connected to the wind condition monitoring module and is used to analyze the wind condition data based on artificial intelligence algorithms and generate optimized control strategies. The central control integrated box 4 is made of 316L stainless steel, and the surface is treated with three layers of anti-corrosion treatment: sandblasting, epoxy primer coating, and polyurethane topcoat spraying, which can adapt to harsh outdoor environments.

[0025] The integrated box houses the central control unit and multiple servo drives (drive components). The central control unit adopts a multi-core processor architecture, equipped with 8GB of RAM and 128GB of solid-state storage. The control system software is developed based on the Linux real-time operating system and supports parallel processing of multi-channel sensor data.

[0026] The central control unit communicates with the servo drives via the industrial Ethernet protocol, supporting a data transmission rate of 100Mbps and millisecond-level command response. Each servo drive is connected to its corresponding servo motor via a dedicated cable, employing a 24-bit high-precision encoder for accurate angle feedback. The servo motor and the spoiler's rotation shaft are connected via a high-strength flange, with the flange connection surface precision-machined to a flatness error of no more than 0.02mm, ensuring transmission accuracy. The servo motor uses an absolute encoder, achieving a control accuracy of ±0.1°, allowing precise adjustment of the spoiler's opening angle, with an adjustment range of 0° to 90°.

[0027] The integrated box is connected to the actuators (servo motor 5) of each modular turbulence unit via double-shielded waterproof cables with a rated protection level of IP67. All cables are uniformly arranged in a dedicated cable tray inside the tower. The cable tray is made of aluminum alloy, lined with flame-retardant and heat-insulating material, and coated with an epoxy resin anti-corrosion coating. Vibration-resistant clamps with a spacing of no more than 2 meters are installed at key nodes to prevent cable wear and vibration fatigue.

[0028] M3, multiple modular spoiler units The unit is circumferentially fixed to the outside of the wind turbine tower 1 by a fixing mechanism. Each of the turbulence units includes an adjustable turbulence component, an actuating component, and a transmission component. The driving component is communicatively connected to the central control unit and is used to receive control commands. The actuating component is connected to the driving component and is driven by the driving component to adjust the opening angle of the turbulence component through the transmission component.

[0029] The system employs quick-release aluminum alloy hoopes made of 6061-T6 aluminum alloy, anodized, and lined with flexible polyurethane protective material to ensure both secure fastening and prevent damage to the tower surface. The hoops and rotating shaft 6 form a 500mm grid structure, completely enclosing the wind turbine tower 1 and secured with stainless steel bolts. Installation of a single hoop takes no more than 10 minutes.

[0030] The streamlined spoiler 8 is made of aerospace-grade 7075 aluminum alloy and processed using the T6 heat treatment process, achieving a tensile strength of 572MPa. The surface of the spoiler 8 is CNC precision polished to a roughness Ra≤0.8μm. The outer surface is laser-engraved to form a biomimetic shark skin 801 microstructure. This structure consists of rhomboid micron-sized pits with a diameter of 0.2-0.5mm and a depth of 50-80μm, which can effectively disrupt the airflow boundary layer and reduce the separation effect. The biomimetic shark skin structure can effectively reduce wind resistance and promote the formation of a stable vortex street to efficiently disperse the vibration energy of the tower.

[0031] The flange connecting plate 9, as a key connecting component between the servo motor 5 and the rotating shaft 6, ensures precise power transmission; it is made of high-strength material, and the connecting surface is precision ground with a flatness error of ≤0.02mm to ensure the control accuracy of the spoiler angle (±0.1°). The actuator is a servo motor 5, which uses an absolute encoder to achieve a control accuracy of ±0.1°. The transmission component is a rotating shaft 6. The servo motor 5 and the rotating shaft 6 are connected by a high-strength flange, and the flatness error of the flange connection surface does not exceed 0.02mm to ensure transmission accuracy. The servo motor 5 is rigidly connected to the rotating shaft 6 of the spoiler 8, which can drive the spoiler 8 to achieve an angle adjustment from 0° (fully in contact with the tower) to 90° (perpendicular to the tower).

[0032] M4, Backup Power System The device is equipped with an independent backup power system, which can maintain continuous operation for 72 hours when the main power is interrupted, ensuring that the system can still execute safety protection commands normally under extreme weather conditions.

[0033] The specific working process of the intelligent control device for onshore wind turbine spoilers provided by this invention is as follows: Data Acquisition and Preprocessing: The wind condition monitoring module acquires raw wind condition data at a frequency of 10Hz and transmits it to the central control unit via optical fiber. The central control unit preprocesses the data, first using a moving average filtering algorithm to eliminate high-frequency noise, then using wavelet transform to decompose the signal, extracting the effective frequency components, and generating a 128-dimensional feature vector after normalization.

[0034] Wind Condition Prediction and Strategy Generation: The central control unit analyzes the processed wind condition data using an LSTM recurrent neural network model. This model contains three hidden layers (256 neurons per layer, dropout rate 0.2). Taking the past 10 minutes of time-series data as input, it predicts the wind field change trend for the next 5 minutes, including wind speed changes, turbulence intensity development, and extreme event probability. The prediction results are updated every 30 seconds. The optimization strategy generation module uses a hybrid optimization algorithm. First, a genetic algorithm (population size 100, 50 iterations) is used for global search, and then a Q-learning algorithm of reinforcement learning is used for fine optimization. The reward function comprehensively considers three objectives: vortex street energy dispersion, tower wind pressure peak, and system energy consumption. Finally, it outputs the optimal angle combination (accuracy ±0.1°) for each of the 8 spoilers.

[0035] Command execution and closed-loop adjustment: The central control unit sends optimized control commands to each servo drive via real-time Ethernet, with an update cycle of 200ms. After receiving the command, the servo drive controls the servo motor 5 to move, driving the spoiler 8 to adjust to the target angle via the rotating shaft 6. After the spoiler 8 is adjusted, the feedback module re-collects actual wind condition data, compares it with the prediction results to calculate the error, and feeds it back to the AI ​​model for online learning. The model parameters are automatically updated every 24 hours, forming an adaptive control closed loop.

[0036] M5, Status Monitoring Module When the system detects a 10-second average wind speed exceeding 25 m / s, or when the predicted model outputs an extreme event probability greater than 80%, it immediately triggers a safety mode within 100 ms, forcibly locking all disturbance units to a preset safety angle of 30° (verified by wind tunnel testing to maintain structural safety under wind speeds of 60 m / s). After the extreme wind conditions subside, the system maintains a 10-minute observation period, during which wind stability is checked every 30 seconds. After the observation period ends, the central control system sends progressive commands to the servo motors, gradually releasing the disturbance units at a rate of 5° per minute. The entire process lasts 12 minutes, eventually returning to normal dynamic control mode. The system is also equipped with a backup power system, which can maintain operation for 72 hours in the event of a main power outage, ensuring safety protection under extreme weather conditions.

[0037] Example 2 See Figure 1 , Figure 1The present invention proposes an intelligent control device for onshore wind turbine spoilers. The spoiler system mainly consists of a wind speed and direction integrated monitoring instrument 3 installed at the top of the wind turbine tower 1, a central control integrated box 4 installed at the tower foundation 2, a spoiler 8 installed on the outside of the tower via a circumferential fixing device 7 and a rotating shaft 6, and a servo motor 5.

[0038] like Figure 2 and Figure 4 As shown, the device's turbulence-inducing function is achieved through the coordinated angle adjustment of multiple turbulence-inducing plates 8 arranged in a ring array. In practice, the number of turbulence-inducing units needs to be determined based on the actual wind conditions at the site. Each turbulence-inducing plate 8 is made of streamlined aluminum alloy, with a specially treated surface: first, a protective layer is formed by spraying polyurethane primer and fluorocarbon topcoat; then, a biomimetic sharkskin microstructure 801 is formed on the outer surface using laser engraving technology. This microstructure contains a regular array of pits with a diameter of 0.2-0.5 mm and a depth of 50-80 μm, which can effectively reduce the boundary layer separation effect when airflow passes through, thus improving aerodynamic performance.

[0039] In actual operation, the wind speed and direction integrated monitoring instrument 3 collects wind field data in real time at a sampling frequency of 10Hz. After preprocessing, the collected raw data is input into the LSTM neural network model of the central control system. Based on historical wind data sequences, this model predicts the wind field change trend in the next 2-5 minutes and generates corresponding angle adjustment strategies. Control commands are transmitted to the servo motors 5 of each spoiler unit through servo drives, driving the spoilers 8 to achieve angle adjustments from 0° (fully attached to the tower) to 90° (perpendicular to the tower). Through this dynamic adjustment, a controllable Karman vortex street is formed behind the wind turbine tower 1, dispersing the vortex-induced vibration energy originally concentrated in a single direction to multiple frequency bands, effectively reducing the wind-induced vibration of the tower.

[0040] The control system begins with high-speed parallel data acquisition and deep preprocessing. The integrated wind speed and direction monitoring instrument installed at the top of the tower samples at a frequency of 10 times per second. ), continuously collecting three-dimensional wind speed components ( ), wind direction angle ( The raw data stream includes temperature (T) and air pressure (P). This raw data first enters the preprocessing pipeline: a moving average filter with a window length of N=10 is used for initial smoothing, the mathematical expression of which is:

[0041] in, The original signal, The signal is after filtering. Then, a more refined frequency domain decomposition and threshold denoising are performed using a three-level wavelet transform based on the Daubechies4 wavelet basis, effectively separating the effective components from the turbulent fluctuation signal. The preprocessed data is then normalized.

[0042] Each parameter is mapped to a standard interval of [0,1]. Finally, a 128-dimensional feature vector is generated from a 10-minute time series window using a feature extraction module. These features include time-domain statistics (mean, variance). Skewness, kurtosis, frequency domain characteristics (power spectrum dominant frequency, energy percentage), and custom characteristics (gust factor). (Wind direction change rate), providing high-quality, standardized input for subsequent AI analysis.

[0043] After preprocessing, the system enters the deep learning-based wind condition prediction and pattern recognition stage. The generated 128-dimensional feature vector is fed into a specially designed deep LSTM recurrent neural network model. This network contains three hidden layers, each with 256 neurons, and a dropout rate of 0.2 is set to prevent overfitting. The model is trained using historical data sequences from the past 10 minutes as input, and its training process is achieved by minimizing a multi-task loss function.

[0044] in, , These are the weighting coefficients. The loss function is a binary cross-entropy function. The model outputs multi-task prediction results in parallel: a high-resolution wind speed trend curve for the next 5 minutes, the evolution path of turbulence intensity, and the probability of extreme wind conditions. The model updates its prediction results every 30 seconds, and its core capability lies in its ability to identify complex wind field dynamic patterns.

[0045] Based on high-precision wind condition forecasting, the system initiates a multi-objective optimization process. This process employs a two-stage hybrid optimization algorithm, with the objective function defined as:

[0046] in, The spoiler angle vector, weighted by coefficients. , , The first stage uses a genetic algorithm for global exploration, setting a population size of 100 individuals, and quickly searches the solution space through selection, crossover, and mutation operations. The second stage introduces reinforcement learning for fine-tuning, where the agent learns the optimal policy through the Q-learning algorithm.

[0047] Among them, learning rate Discount factor The reward function is designed as follows:

[0048] The final output is the optimal angle combination α for each spoiler. The accuracy is controlled within ±0.1°.

[0049] Finally, the system enters the high-real-time instruction execution and online learning phase. Optimized control instructions are sent to each servo drive via a real-time industrial Ethernet protocol. A 200ms update cycle and a command response time of less than 100ms ensure real-time control. After each spoiler adjusts to the target angle according to the instructions, the feedback module collects actual wind data for error feedback.

[0050] Among them, online learning rate When the 10-second average wind speed exceeds 25 m / s (or the probability of an extreme event is greater than 80%), the system immediately triggers a safety mode, locking all spoilers to a safe angle that meets mechanical constraints.

[0051] in, These are the calibration values ​​for wind tunnel testing. After the wind conditions stabilize, the system undergoes a 10-minute observation period followed by a 12-minute gradual release process (release rate). ( / min), gradually restore the normal control mode, and form a complete perception-decision-execution-learning closed loop.

[0052] like Figure 3 As shown, the servo drive and central control system are centrally installed in the central control integration box 4. This integration box is installed at the tower foundation 2, and its outer shell is made of corrosion-resistant aluminum alloy. All cables are arranged inside the tower, and the cable trays are made of aluminum alloy with an epoxy resin anti-corrosion coating. Vibration-resistant clamps are installed at key nodes to ensure the reliability and durability of the system.

[0053] The spoiler is mounted on the outside of the wind turbine tower 1 via a quick-release circumferential fixing device 7 and a rotating shaft 6. The circumferential fixing device 7 employs a split-type snap-fit ​​design, consisting of two 180° semi-circular rings, maintaining a tolerance of ±2mm with the outer diameter of the wind turbine tower 1. The circumferential fixing device 7 is 200mm wide and 15mm thick, and is fixed to the outside of the tower using stainless steel bolts. The rotating shaft 6 is a solid shaft design, possessing sufficient rigidity to suppress vibration.

[0054] like Figure 5As shown, the specific implementation of the system's control logic includes: First, data acquisition and preprocessing are performed. Wind speed and direction sensors (corresponding to wind speed and direction monitoring instruments) collect parameters such as wind speed, wind direction, and turbulence intensity in real time. The artificial intelligence central control module (corresponding to the control unit) uses moving average filtering and wavelet transform algorithms to denoise the data, and then performs normalization and feature extraction. Subsequently, the LSTM recurrent neural network model in the artificial intelligence central control module is used to predict wind conditions and identify sudden changes in wind speed, turbulence patterns, and extreme wind trend. Based on the prediction results, the system uses an optimization algorithm combining genetic algorithm and reinforcement learning in the artificial intelligence central control module to generate the optimal angle combination strategy with the objective functions of maximizing vortex street energy dispersion, minimizing the peak wind pressure on the tower surface, and maintaining the lowest system energy consumption. Finally, the control commands are sent from the artificial intelligence central control module to the servo driver. The servo driver drives the servo motor, which in turn drives the turbulence unit to perform adjustments. The adjusted wind condition data is collected by the feedback module and sent back to the artificial intelligence central control module, forming a closed-loop adaptive control.

[0055] When the system detects that the 10-second average wind speed exceeds the set threshold of 25m / s through the status monitoring module, or when the prediction model outputs an extreme event probability greater than 80%, the safety mode is immediately triggered. The artificial intelligence central control module controls the servo motor through the servo driver to forcibly lock all turbulence units to a safe angle of 30°. After the extreme wind conditions are resolved, the system maintains a 10-minute observation period. After the wind conditions stabilize, the locked state is gradually released, and normal dynamic control is restored.

[0056] The above specific embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to examples, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A smart control device for onshore wind turbine spoilers, characterized in that, include: The wind condition monitoring module is installed at a preset wind measurement location on the wind turbine tower to collect wind condition data in real time. The artificial intelligence central control module is installed at a preset installation position on the wind turbine tower. It contains a central control unit and multiple drive components. The central control unit is communicatively connected to the wind condition monitoring module and is used to analyze the wind condition data based on artificial intelligence algorithms and generate optimized control strategies. Multiple modular turbulence-disrupting units are circumferentially fixed to the outside of the wind turbine tower by a fixing mechanism. Each turbulence-disrupting unit includes an adjustable turbulence-disrupting component, an actuating component, and a transmission component. The actuating component is communicatively connected to the central control unit and is used to receive control commands. The actuating component is connected to the actuating component and is driven by the actuating component to adjust the opening angle of the turbulence-disrupting component through the transmission component.

2. The intelligent control device for onshore wind turbine spoilers according to claim 1, characterized in that, The wind condition monitoring module is a wind speed and direction monitor, which is installed at the top of the wind turbine tower. The wind speed and direction monitor uses a combination of a three-cup wind speed sensor and an ultrasonic wind direction sensor, with a measurement range of 0-60m / s, an accuracy of ±0.1m / s, a sampling frequency of 10Hz, and communicates with the central control unit via optical fiber.

3. The intelligent control device for onshore wind turbine spoilers according to claim 1, characterized in that, The artificial intelligence central control module is a central control integrated box, which is installed at a preset height from the ground at the bottom of the tower. The outer shell of the central control integrated box is made of corrosion-resistant material and the surface is treated with multiple layers of anti-corrosion. The driving component is a servo driver, and the central control unit is connected to the servo driver via an industrial Ethernet protocol, supporting data transmission at a preset rate and millisecond-level command response.

4. The intelligent control device for onshore wind turbine spoilers according to claim 3, characterized in that, The central control integration box is connected to the execution component via a double-shielded waterproof cable with a rated protection level of IP67. All cables are arranged in dedicated cable trays inside the tower. The cable trays are made of aluminum alloy, lined with flame-retardant and heat-insulating material, and the surface is treated with anti-corrosion. Anti-vibration clamps are installed at key nodes.

5. The intelligent control device for onshore wind turbine spoilers according to claim 1, characterized in that, The fixing mechanism is a quick-release ring hoop, made of aluminum alloy with surface treatment. The ring hoop is lined with flexible protective material and forms a grid structure with the transmission component to wrap the wind turbine tower. The quick-release ring is fastened with bolts, and the installation time for a single ring does not exceed the preset time.

6. The intelligent control device for onshore wind turbine spoilers according to claim 1, characterized in that, The aerodynamic component is a streamlined aerodynamic plate, made of high-strength aluminum alloy through heat treatment, and its surface is precision polished. The outer surface of the spoiler is provided with biomimetic microstructures, which are regularly arranged micron-sized pits. The diameter, depth and arrangement of the pits meet the preset parameter range.

7. The intelligent control device for onshore wind turbine spoilers according to claim 1, characterized in that, The actuating component is a servo motor, and the transmission component is a rotating shaft; the servo motor uses an absolute encoder, and the control accuracy reaches ±0.1°; The servo motor and the rotating shaft are connected by a high-strength flange, and the flatness error of the flange connection surface does not exceed a preset threshold; the opening angle adjustment range of the turbulence component is 0° to 90°.

8. The intelligent control device for onshore wind turbine spoilers according to claim 1, characterized in that, The central control unit adopts a multi-core processor architecture, is equipped with a preset capacity of running memory and solid-state storage, and the control system software is developed based on a real-time operating system. The central control unit analyzes wind data using an LSTM recurrent neural network model to predict the wind field change trend over a preset time period; the system adjusts the turbulence unit based on the prediction results at a preset time in advance. When preset extreme wind conditions are detected, the system triggers a safety mode within a preset time, forcibly locking all turbulence units to a preset safety angle; After the extreme wind conditions are resolved, the system maintains a preset observation period, and then gradually releases the turbulence unit at a preset rate to restore the normal dynamic control mode.

9. The intelligent control device for onshore wind turbine spoilers according to claim 8, characterized in that, The optimization strategy generation module of the central control unit adopts a hybrid optimization algorithm. First, a genetic algorithm is used for global search, and then a reinforcement learning algorithm is used for fine optimization. The reinforcement learning algorithm learns the optimal control strategy through the Q-learning algorithm, and the reward function comprehensively considers three objectives: vortex street energy dispersion, tower wind pressure peak and system energy consumption.

10. The intelligent control device for onshore wind turbine spoilers according to claim 1, characterized in that, It is also equipped with a backup power system, which can maintain operation for a preset duration when the main power is interrupted.

Images