Multi-section hinged self-adaptive wind turbine blade tip winglet system

Abstract

The invention discloses a multi-section hinged self-adaptive wind turbine blade tip winglet system, and relates to the field of wind power. Comprising at least four sections of winglet structures which are hinged end to end, hinged parts are driven by corresponding servo motors to rotate, and each section of winglet rotates in a bending mode on the plane perpendicular to the front-stage winglet structure or rotates in the length direction of the front-stage winglet structure; a strain gauge is adhered to the root of each winglet structure; a temperature sensor, an icing sensor and a gradient heating film are distributed on the surface of each winglet structure; a winglet control cabinet is arranged in the fan blade body, the control cabinet is electrically connected with each section of servo motor and sensing equipment, and posture adjustment, heating and deicing are carried out on each section of winglet structure according to data collected by a fan master control system and the sensing equipment.

Description

Technical Field

[0001] This application relates to the field of wind power, and in particular to a multi-segment articulated adaptive wind turbine blade tip winglet system. Background Technology

[0002] In the field of wind power generation, blade tip winglets are a common device to improve the aerodynamic performance of wind turbines, but traditional technologies have significant limitations and are difficult to meet the comprehensive needs under complex actual working conditions.

[0003] Traditional technologies suffer from several drawbacks: First, some technologies, such as CN113007009A, have winglets with specific airfoil profiles. While these can improve aerodynamic performance at the design point, they cannot adapt to the complex and variable wind conditions (such as wind shear and turbulence) encountered in actual operation. Under non-design conditions, their effects are minimal or even negative. Second, as shown in CN102996367A, winglets driven by servo motors for overall deflection have a single control objective, lacking the ability to finely optimize aerodynamic efficiency and failing to address issues like tip icing. Furthermore, methods like CN119378116A, which optimize geometric parameters during the design phase, are offline designs and cannot be adjusted in real-time and adaptively during wind turbine operation. In summary, traditional tip winglets generally suffer from poor adaptability to operating conditions, inability to solve tip flutter problems, lack of anti-icing capabilities, and limited functionality.

[0004] Therefore, there is an urgent need to develop a new technology that can overcome the above-mentioned defects. Its core objective is to provide a multi-functional integrated system that can automatically adjust its attitude based on real-time wind conditions, blade status, and icing risk, while simultaneously improving aerodynamic efficiency, suppressing load fluctuations, controlling flutter stability, and performing efficient active de-icing. Summary of the Invention

[0005] This application provides a multi-segment articulated adaptive wind turbine blade tip winglet system, which has the advantages of improving operating condition adaptability, effectively suppressing flutter, and providing active de-icing function.

[0006] The system includes at least four small wing structures that are hinged together at the front and rear. The hinges are driven to rotate by corresponding servo motors, and the first wing is installed at the end of the wind turbine blade. Two of the winglets bend and rotate on a plane perpendicular to the wind turbine blades based on the hinge, while the remaining winglets bend and rotate on a plane perpendicular to the front winglet structure, or rotate along the length of the front winglet structure. Strain gauges for monitoring strain caused by aerodynamic loads are attached to the root of each winglet structure; temperature sensors for monitoring temperature and icing sensors for monitoring icing thickness are distributed on the surface of each winglet structure; and gradient heating films are applied to the surface of each winglet structure. The wind turbine blade body has a built-in winglet control cabinet. The control cabinet is electrically connected to each section of servo motors and sensing equipment. Based on the data collected by the wind turbine main control system and sensing equipment, the attitude of each section of winglet structure is adjusted and heated for de-icing.

[0007] Specifically, the first and second winglets are connected by a hinge mechanism, and the hinged parts of the remaining winglets are equipped with heated spherical hinge supports, which connect the two winglet structures through spherical hinge devices.

[0008] Specifically, dustproof devices are installed on the outside of the winglet structure at the joints of each section, including dust covers at the transition sections of the winglet and the joints of each support. The first winglet is connected to the original blade via a transition section. The front end of the transition section is laid up, injected, and cured according to the mold parameters of the blade tip. The rear end of the transition section is connected to the first winglet.

[0009] Specifically, the transition section is made of fiberglass cloth.

[0010] Specifically, an inertial measurement unit is installed on each winglet structure to measure the acceleration and angular velocity of the winglet segment.

[0011] Specifically, the wind turbine main control system acquires wind condition information and unit status parameters; the wind condition information includes wind speed, wind direction, wind shear and turbulence intensity information, and the unit status parameters include rotor speed, generator power, blade pitch angle and blade root bending moment parameters.

[0012] Specifically, the control cabinet has a built-in dynamic decision-making module and a collaborative control module. The dynamic decision-making module dynamically allocates the weights of control objectives based on the unit's operating conditions, and the decision-making logic... It is expressed as follows:

[0013] in, Indicates instantaneous power generation. This represents the variance of the leaf root waving moment. This indicates the total energy consumption for de-icing. , , These represent the corresponding weight coefficients, and the K value is used to quantify the overall optimization objective under the current working condition. The collaborative control module acquires weighting coefficients and calculates corresponding rotation increment commands based on the state data collected from each winglet structure and the state data of adjacent winglet structures.

[0014] Specifically, the dynamic decision-making module has a built-in fuzzy reasoning rule base, which matches the current system input with all rule premises and aggregates the corresponding weight coefficients.

[0015] Specifically, the collaborative control module includes features for the first... reward function of the segment small wing structure , means as follows:

[0016] in, The change in power generation. It is the first The change in load at the root of the winglet segment. Indicates the first The electrical energy consumed by Duan Xiaoyi during the de-icing process. This represents the overall adjustment coefficient.

[0017] Specifically, the motion commands calculated by the collaborative control module are sent to the blade controller to drive the servo motors corresponding to each winglet structure to move to the target angle; and / or control the gradient heating film applied to the winglet surface.

[0018] The beneficial effects of the technical solution provided in this application include at least the following: by including a multi-segment articulated winglet structure, sensor monitoring and control adjustment, adaptive attitude adjustment and active de-icing are realized, thereby improving the aerodynamic efficiency and structural reliability of the wind turbine under complex operating conditions. It has the advantages of improving operating condition adaptability, effectively suppressing flutter and providing active de-icing function. Attached Figure Description

[0019] Figure 1 This is a schematic diagram of the multi-segment articulated adaptive wind turbine blade tip winglet system provided in the embodiments of this application; Figure 2 This is a schematic diagram of a possible configuration of the winglet structure provided in an embodiment of this application; Figure 3 This is a schematic diagram of another possible form of the winglet structure provided in the embodiments of this application; Figure 4 This is a schematic diagram of another possible configuration of the winglet structure provided in the embodiments of this application; Figure 5 This is a schematic diagram of the installation of the wing-shaped dust cover provided in the embodiments of this application; Figure 6 The control system topology diagram is shown; Figure 7 A structural block diagram of a computer device provided in an exemplary embodiment of this application is shown. Detailed Implementation

[0020] To make the objectives, technical solutions, and advantages of this application clearer, the embodiments of this application will be described in further detail below with reference to the accompanying drawings.

[0021] In this article, "multiple" refers to two or more. "And / or" describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. The character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0022] In practical applications of wind turbine blade tip winglets, traditional devices, due to their fixed structure and single control strategy, are difficult to adapt to complex actual operating conditions such as wind shear and turbulence, resulting in limited improvement in aerodynamic performance. At the same time, blade tip flutter cannot be effectively suppressed, and there is a lack of icing monitoring and active de-icing mechanisms, resulting in limited functionality and affecting the overall performance of the system.

[0023] For example, during the operation of wind farms in winter with low temperatures and high turbulence, rapid fluctuations in wind speed and direction exacerbate the aerodynamic load fluctuations of traditional winglets, and continuous tip vibration occurs; icing on the winglet surface is detected but there is no treatment mechanism, leading to deterioration of the aerodynamic shape, increased power generation fluctuations, and increased stress on the blade structure, further resulting in unstable operation.

[0024] If the above problems are not resolved, the operational stability of wind turbines will decrease, the fatigue damage process of blades will be accelerated, and the risk of structural failure will increase; persistent icing problems will lead to aerodynamic performance degradation and an increased probability of unplanned downtime; the overall system reliability and service life will be affected, and the maintenance burden will increase.

[0025] To address this issue, this application proposes a multi-segment articulated adaptive wind turbine blade tip winglet system, composed of multiple relatively rotatable structural segments. This system is capable of dynamically adjusting its attitude and performing de-icing operations according to operating conditions. The system aims to improve the aerodynamic performance of the wind turbine, suppress load fluctuations, and mitigate the risk of icing. Figure 1 The system structure diagram shown includes two main parts: the mechanical structure and the control system.

[0026] The mechanical structure comprises at least four winglet segments hinged together end-to-end. The hinges are driven to rotate by corresponding servo motors, with the leading winglet segment mounted to the tip of the wind turbine blade. A winglet structure is the basic unit constituting the blade tip winglet system; it typically has a specific aerodynamic shape and is formed as a whole by connecting end-to-end segments. Each winglet segment can be adjusted independently or collaboratively. The hinges are mechanical connectors linking adjacent winglet segments, allowing relative rotation between them. This connection method endows the winglet system with multi-degree-of-freedom motion capabilities.

[0027] Two of the winglets bend and rotate along the Y-axis on the plane perpendicular to the wind turbine blades, based on the hinge. The remaining winglets bend and rotate along the Y-axis on the plane perpendicular to the front winglet structure, or rotate along the Z-axis along the length of the front winglet structure.

[0028] Strain gauges, which monitor strain caused by aerodynamic loads, are attached to the root of each winglet structure. These strain gauges are sensors used to measure the strain on the surface of an object. By attaching them to the root of the winglet structure, the strain gauges can monitor the winglet deformation caused by aerodynamic loads, providing data for flutter identification and load assessment.

[0029] Temperature sensors for monitoring temperature and icing sensors for monitoring icing thickness are distributed across the surface of each winglet structure segment; a gradient heating film is also applied to the surface of each winglet structure segment. Temperature sensors are used to measure the temperature of an object's surface or the environment. In this system, temperature sensors are distributed across the winglet structure surface to monitor temperature changes in real time. Icing sensors are used to monitor icing conditions on an object's surface. These icing sensors are distributed across the winglet structure surface to monitor icing formation and thickness in real time to assess the risk of icing. The gradient heating film is an electric heating element with different heating power densities in different areas. This heating film is applied to the winglet structure surface and generates heat through electrical energy to actively melt or prevent icing.

[0030] The wind turbine blades house a winglet control cabinet, an electronic control unit integrated within the blade structure. This cabinet is electrically connected to the servo motors and sensors, receiving data from the sensors and the main control system. Based on preset logic or algorithms, it issues control commands to the servo motors and heating films, adjusting the attitude and performing heating and de-icing on each winglet segment. The main control system is the core control unit of the wind turbine generator set, responsible for monitoring and managing the overall operating status. This system provides wind condition information and turbine status parameters as input for the winglet control cabinet's decision-making.

[0031] This embodiment uses a four-segment winglet structure for illustration; see [link / reference]. Figure 1 The mechanical structure diagram is a system structure diagram. It is preferable to have a mechanical structure with four or more airfoil segments, as a single or two-segment airfoil cannot simultaneously achieve "tip vortex suppression" and "root load release". The four-segment design allows the airfoil to take the form of an "S" or wave shape, which is a flow field control effect that traditional straight airfoil cannot achieve.

[0032] The first winglet 2 and the second winglet 4 are connected by a hinge mechanism, allowing the two ends to rotate around the Y-axis to change the winglet angle. For example... Figure 2 , Figure 3 and Figure 4 Examples of winglet adjustment configurations are shown. The second-section winglet 4 and the third-section winglet 5, as well as the third-section winglet 5 and the fourth-section winglet 7, are connected by a spherical hinge, which allows for rotation with multiple degrees of freedom. This enables the bending and rotation around the Z-axis of the second and third sections, and the third and fourth sections of the winglets.

[0033] The entire system consists of a control cabinet 1, a single-axis rotary servo motor 3, a multi-axis rotary servo motor 6, a hinge device 8, a spherical hinge device 9, a heatable spherical hinge support 10, a control cabinet signal transmission line 11, a control cabinet power transmission line 12, and power supply lines 13 for the servo motors and heating modules.

[0034] The first winglet 2 and the second winglet 4 are connected by a hinge mechanism. The hinged parts of the remaining winglets are equipped with heated spherical hinge supports 10, which are connected to the two winglet structures through spherical hinge devices 9. For the working conditions of the wind turbine blade tip winglet hinge under extremely high linear velocity, huge centrifugal force, alternating aerodynamic load and harsh environment, the hinge device is preferably made of titanium alloy or carbon fiber composite material.

[0035] In addition, a dust protection device is installed on the outside of the winglet structure, such as... Figure 5 As shown, it includes dustproof devices distributed at the joints of each section, including the winglet transition section 14 and the dust cover 15 at each support joint.

[0036] The first winglet 2 is connected to the original blade via a transition section 14 to ensure the stability of the structural connection. The transition section 14 is made of fiberglass cloth, and its front end is laid up, poured, and cured according to the mold parameters of the blade tip; the rear end of the transition section 14 is connected to the first winglet 2. After the winglet is manufactured, the transition section 14 is fitted onto the original blade to complete the connection between the winglet segment and the original blade.

[0037] Flexible protective covers are bonded between the first and second sections, the second and third sections, and the third and fourth sections of the winglets to reduce the erosion of the internal structure by wind, sand and rain in harsh environments, thereby improving the service life of the structure.

[0038] In addition, this application incorporates a sensing system, namely various sensing and data acquisition devices, on the winglet structure. These devices may include the following functionally: 1) Local perception (encapsulated inside the winglets): Strain gauges: Adhesive to the root of each winglet section to monitor strain caused by aerodynamic loads, used for flutter identification and load assessment.

[0039] Temperature and icing sensors: distributed on the surface of the winglet to monitor temperature changes and icing thickness in real time.

[0040] Inertial Measurement Unit: Measures the acceleration and angular velocity of the winglet for dynamic response analysis.

[0041] 2) Global Awareness (from the wind turbine main control system): Wind information: Obtain various wind condition parameters such as wind speed, wind direction, wind shear, and turbulence intensity.

[0042] Unit status: Obtain key operating parameters such as wind turbine speed, generator power, blade pitch angle, and blade root bend.

[0043] In this embodiment, the control cabinet has a built-in dynamic decision-making module and a collaborative control module. The dynamic decision-making module dynamically allocates the weights of control objectives according to the unit's operating conditions, and the decision logic... It is expressed as follows:

[0044] in, Indicates instantaneous power generation. This represents the variance of the leaf root waving moment. This indicates the total energy consumption for de-icing. , , These represent the corresponding weighting coefficients, and the K value is used to quantify the overall optimization objective under the current operating conditions. Weighting coefficients , , The results were derived through fuzzy inference using input variables. These input variables included normalized turbulence intensity, blade root bending moment rate of change, estimated icing risk, and power deviation.

[0045] The collaborative control module obtains weighting coefficients and calculates the corresponding rotation increment command based on the state data (such as load and temperature) collected from each winglet structure and the state data of adjacent winglet structures.

[0046] The dynamic decision-making module has a built-in fuzzy inference rule base. It matches the current system input with all rule premises and aggregates the corresponding weight coefficients. Example of a fuzzy inference rule base: a) If the turbulence intensity is judged to be "high" and the rate of change of the blade root bending moment is "large", then For "high", "Low" It is "low"; b) If the icing risk is assessed as "high" and the power deviation is "small", then For "high", For "middle", It is "low".

[0047] There are usually dozens or even hundreds of such rules. The system will match the current fuzzy state of all inputs with the premise of each rule and calculate the trigger strength of that rule.

[0048] After the decision-making module outputs the weights of each target, the control module is responsible for calculating the optimal motion commands for the four winglets. This scheme uses a multi-independent-body reinforcement learning structure to achieve cooperative control. Independent component configuration: The four winglets are treated as four independent entities.

[0049] Condition monitoring: Each winglet observes its own condition (such as winglet load, surface temperature, etc.) as well as the condition information of adjacent winglets.

[0050] Motion control: The independent body outputs the incremental rotation of itself around the Y-axis and Z-axis.

[0051] Reward function: Reward function for an independent entity As the core of control, it encompasses both individual contributions and emphasizes overall coordination:

[0052] in, This represents the change in power generation. Indicates the first The change in load at the root of the winglet; if the load increases, this item will become negative, thus reducing the total reward. This means penalizing the behavior of "increasing load"; the load distribution of the winglets varies in different positions; through individualized load penalties, the system can manage the force distribution of the winglets more precisely. Indicates the first The electrical energy consumed by Duan Xiaoyi when performing the de-icing action is directly quantified into the reward function; the independent self-learning achieves an effective de-icing effect with the least amount of electrical energy, or temporarily does not start heating when the risk of icing is not high. This represents the overall adjustment coefficient, used to quantify the adverse aerodynamic interference that a certain winglet segment causes to the flow field around its adjacent winglets. This penalty forces each individual body not only to focus on its own actions and global results, but also to predict and consider the impact of its actions on the working environment of its adjacent winglets.

[0053] The motion commands calculated by the collaborative control module are sent to the blade controller to drive the servo motors corresponding to each segment of the winglet structure to move to the target angle; and / or control the gradient heating film applied to the surface of the winglet.

[0054] The execution process mainly involves the blade controller issuing commands to the heating film or servo motor. Figure 6 The control system topology diagram is shown. Unit data (including data collected by the risk control system) and system data (position data from sensors and motors, etc.) are input to the system master controller (i.e., the decision-making module). The system master controller analyzes and infers from the data to generate weighting coefficients. , , Furthermore, the system master controller sends data to each blade controller (cooperative control module), and the corresponding blade controller and reward function adaptively adjust and control the corresponding heating film and servo motor.

[0055] Based on the above process, the detection process of this system can be summarized as follows: Step 1: Multi-source information perception and fusion Acquisition of local sensing information: obtained by sensors encapsulated inside each winglet segment, including load strain monitored by strain gauges, surface condition monitored by temperature and icing sensors, and dynamic response measured by inertial measurement unit; Collect global perception information: from the wind turbine main control system, including wind condition information such as wind speed, wind direction, and turbulence intensity, as well as unit status parameters such as wind turbine speed, generator power, blade pitch angle, and blade root bending moment; Step 2: Multi-objective dynamic decision-making and weight allocation Sensing information is input to the multi-objective dynamic decision-making module, which dynamically calculates and outputs the weight coefficients of three core control objectives (increased power generation, reduced load, and efficient de-icing) based on real-time operating conditions. , , ); Inputs: Normalized turbulence intensity, blade root bending moment change rate, estimated icing risk, power deviation, and other variables; Processing: Decision-making is performed using a built-in fuzzy reasoning rule base. For example, the rule base includes: "If the turbulence intensity is judged as 'high' and the rate of change of blade root bending moment is 'large', then..." For 'high', For 'low', The system matches the current input with all rule premises and aggregates the final precise weight coefficients. Output: Forms the decision logic K, and the weight coefficients. , , Then it is directly passed to the next level controller; Step 3: Cooperative Control Based on Reinforcement Learning The weight coefficients output by the dynamic decision-making module are input to the collaborative control module, which adopts a multi-independent reinforcement learning architecture to treat the four-segment winglets as four independent individuals for collaborative control. Status observation: Each winglet observes its own status (such as load and temperature) and the status information of adjacent winglets; Action output: Each individual outputs its own rotation increment commands around the Y-axis (deflection) and Z-axis (torsion); Reward-driven: The reward function for each individual. Ensure that the motion learning of each winglet is in the global weights ( , , Under the guidance of [the relevant authority], we pursue both the maximization of overall benefits and the optimization and coordination of individual behaviors; Step 4: Instruction Execution and Action Implementation The optimal action command calculated by the collaborative control module is then sent to the actuator: Winglet attitude adjustment: Drives the miniature servo motors inside each winglet segment to move precisely to the target angle, achieving complex attitude changes such as "S" or wave shapes; Active de-icing execution: When de-icing is required, the gradient heating film applied to the surface of the winglet is controlled to heat the film according to a zoned strategy from the tip to the root, so as to reduce peak power consumption and improve de-icing efficiency. Step 5: Closed-loop feedback and continuous optimization The entire system forms a closed loop. When the attitude of the winglet changes, the local sensors on it (such as strain gauges and IMUs) will detect the new load and vibration state. At the same time, the global parameters of the wind turbine (such as power and blade root bending moment) will also change. These new data are fed back to the sensing system in the first step as input, starting the next control cycle. Through this continuous "sensing-decision-execution-feedback" cycle, the system can adaptively respond to changing wind conditions and achieve continuous optimization of comprehensive performance.

[0056] Figure 7 This illustration shows a structural block diagram of a computer device provided in an exemplary embodiment of this application. The device can be a desktop computer, laptop computer, handheld computer, or cloud server, among other computer devices. The computer device may include, but is not limited to, a processor and memory. The processor and memory can be connected via a bus or other means. The processor can be a Central Processing Unit (CPU). The processor can also be other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs) or other programmable logic devices, graphics processing units (GPUs), embedded neural network processing units (NPUs) or other dedicated deep learning coprocessors, discrete gate or transistor logic devices, discrete hardware components, or combinations of the above-mentioned types of chips.

[0057] This application also discloses a computer-readable storage medium. Specifically, the computer-readable storage medium is used to store a computer program, which, when executed by a processor, implements the methods described in the above-described method embodiments. Those skilled in the art will understand that implementing all or part of the processes in the methods described in the above-described embodiments of this application can be accomplished by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when executed, it can include the processes of the embodiments described above. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk drive (HDD), or solid-state drive (SSD), etc.; the storage medium can also include combinations of the above types of memory.

[0058] This specific embodiment is merely an explanation of the present invention and is not intended to limit the invention. After reading this specification, those skilled in the art can make modifications to this embodiment without contributing any inventive step, but such modifications are protected by patent law as long as they are within the scope of the claims of the present invention.

Claims

1. A multi-segment articulated adaptive wind turbine blade tip winglet system, characterized in that, It includes at least four small wing structures that are hinged together at the front and rear. The hinged parts are driven to rotate by corresponding servo motors. The first wing is installed at the end of the wind turbine blade. Two of the winglets bend and rotate on a plane perpendicular to the wind turbine blades based on the hinge, while the remaining winglets bend and rotate on a plane perpendicular to the front winglet structure, or rotate along the length of the front winglet structure. Strain gauges for monitoring strain caused by aerodynamic loads are attached to the root of each winglet structure; temperature sensors for monitoring temperature and icing sensors for monitoring icing thickness are distributed on the surface of each winglet structure; and gradient heating films are applied to the surface of each winglet structure. The wind turbine blade body has a built-in winglet control cabinet. The control cabinet is electrically connected to each section of servo motors and sensing equipment. Based on the data collected by the wind turbine main control system and sensing equipment, the attitude of each section of winglet structure is adjusted and heated for de-icing.

2. The multi-segment articulated adaptive wind turbine blade tip winglet system according to claim 1, characterized in that, The first and second winglets are connected by a hinge mechanism, while the hinged parts of the remaining winglets are equipped with heated spherical hinge supports, which connect the two winglet structures through a spherical hinge device.

3. The multi-segment articulated adaptive wind turbine blade tip winglet system according to claim 2, characterized in that, Dustproof devices are installed on the outside of the wing structure at the joints of each section, including dust covers at the wing transition section and the joints of each support. The first winglet is connected to the original blade via a transition section. The front end of the transition section is laid up, injected, and cured according to the mold parameters of the blade tip. The rear end of the transition section is connected to the first winglet.

4. The multi-segment articulated adaptive wind turbine blade tip winglet system according to claim 3, characterized in that, The transition section is made of fiberglass cloth.

5. The multi-segment articulated adaptive wind turbine blade tip winglet system according to claim 4, characterized in that, An inertial measurement unit is also installed on each winglet structure to measure the acceleration and angular velocity of the winglet segment.

6. The multi-segment articulated adaptive wind turbine blade tip winglet system according to claim 1, characterized in that, The wind turbine main control system acquires wind condition information and unit status parameters; the wind condition information includes wind speed, wind direction, wind shear and turbulence intensity information, and the unit status parameters include rotor speed, generator power, blade pitch angle and blade root bending moment parameters.

7. The multi-segment articulated adaptive wind turbine blade tip winglet system according to claim 1, characterized in that, The control cabinet contains a dynamic decision-making module and a collaborative control module. The dynamic decision-making module dynamically allocates the weights of control objectives based on the unit's operating conditions, and the decision logic... It is expressed as follows: in, Indicates instantaneous power generation. This represents the variance of the leaf root waving moment. This indicates the total energy consumption for de-icing. , , These represent the corresponding weight coefficients. The value is used to quantify the overall optimization objective under the current operating conditions; The weighting coefficients obtained by the collaborative control module are partly derived from wind conditions and unit status analysis, and partly from status data collected from each winglet structure and status data of adjacent winglet structures.

8. The multi-segment articulated adaptive wind turbine blade tip winglet system according to claim 7, characterized in that, The dynamic decision-making module has a built-in fuzzy inference rule base. It matches the current system input with all rule premises and aggregates the corresponding weight coefficients.

9. The multi-segment articulated adaptive wind turbine blade tip winglet system according to claim 8, characterized in that, The collaborative control module includes features for the first... reward function of the segment small wing structure , means as follows: in, The change in power generation. It is the first The change in load at the root of the winglet segment. Indicates the first The electrical energy consumed by Duan Xiaoyi during the de-icing process. This represents the overall adjustment coefficient.

10. The multi-segment articulated adaptive wind turbine blade tip winglet system according to claim 9, characterized in that, The motion commands calculated by the collaborative control module are sent to the blade controller to drive the servo motors corresponding to each segment of the winglet structure to move to the target angle; and / or control the gradient heating film applied to the surface of the winglet.

Images