Self-adaptive angle adjusting system for floating type offshore wind power blade

Abstract

The invention discloses a self-adaptive angle adjusting system for a floating type offshore wind power blade, and belongs to the technical field of offshore wind power equipment. The system comprises a multi-source sensing module, a central control module, a self-adaptive driving module and a state monitoring and feedback module, the multi-source sensing module collects multi-dimensional working condition parameters of an environment, a platform, blades and a unit in real time; the central control module preprocesses data through Kalman filtering, establishes a coupling model of platform motion and blade stress based on a blade element-momentum theory, adopts a self-adaptive algorithm combining model predictive control and a fuzzy neural network, solves an optimal blade angle by taking power maximization and load minimization as targets, and generates an adjustment instruction. The method can adapt to the complex marine environment and platform movement in real time, the adjustment precision and the response speed are improved, the blade load is balanced, the system robustness is enhanced, and efficient and stable operation of a unit is guaranteed.

Description

Technical Field

[0001] This invention relates to the field of offshore wind power technology, and in particular to a floating offshore wind turbine blade adaptive angle adjustment system. Background Technology

[0002] With the acceleration of the global energy structure transformation, offshore wind power, as a clean and renewable energy source, has become a key area of ​​development in the new energy sector due to its advantages such as abundant resource reserves, high power generation efficiency, and no occupation of land resources. Among them, floating offshore wind power can overcome the water depth limitations of fixed offshore wind power, enabling large-scale development in deep-sea areas, further expanding the application scope of offshore wind power and showing broad development prospects.

[0003] As the core component of offshore wind turbines for capturing wind energy, the blades' angle adjustment accuracy directly affects the turbine's power generation efficiency, operational stability, and equipment lifespan. Compared to stationary offshore wind power, floating offshore wind power platforms operate in a complex marine environment, subject to the combined effects of various dynamic loads such as wind, waves, currents, and tides. This results in the platform constantly being in a six-degree-of-freedom motion state (roll, pitch, heave, sway, sway, and yaw). This platform motion is directly transmitted to the wind turbine and blades, making the flow field environment in which the blades are located extremely complex and uncertain. On the one hand, the platform's swaying causes periodic changes in the actual windward angle of the blades, disrupting the optimal matching state between the blades and the airflow. On the other hand, instantaneous fluctuations in offshore wind speed and random changes in turbulence intensity further exacerbate the uneven stress on the blades, not only reducing wind energy capture efficiency but also potentially causing fatigue damage to the blades and even affecting the operational safety of the entire turbine.

[0004] Existing offshore wind turbine blade angle adjustment systems (i.e., pitch systems) are mainly designed for stationary wind power scenarios. Their adjustment logic often employs a segmented control strategy based on a preset wind speed threshold, or a simple proportional-integral-derivative (PID) control strategy. These systems suffer from the following significant drawbacks:

[0005] 1. Significant Response Lag: Existing pitch control systems' sensing modules mostly collect only one or a few parameters such as wind speed and rotational speed, failing to fully consider the impact of the floating platform's motion on the blade's windward angle. When the platform experiences severe shaking or a sudden change in wind speed, the system cannot promptly sense the actual forces acting on the blades and the changes in the flow field environment, resulting in a significant lag in the issuance and execution of adjustment commands, making real-time dynamic angle correction impossible.

[0006] 2. Insufficient Adaptive Adjustment Capability: Existing control strategies mostly rely on preset fixed parameter control and fail to adaptively optimize for the randomness of the marine environment and the dynamics of platform motion. For example, the amplitude and frequency of platform motion vary significantly under different sea states (such as light winds, strong winds, and large waves), and the optimal windward angle of the blades also changes accordingly. However, existing systems cannot automatically adjust control parameters according to actual operating conditions, resulting in low adjustment accuracy and difficulty in consistently maintaining the blades in the optimal wind energy capture state. In extreme operating conditions, improper adjustment may even lead to safety risks.

[0007] 3. Lack of load balancing control: The motion of the floating platform and the uneven distribution of wind speed can easily lead to periodic load fluctuations in the blades during rotation. These fluctuations can exacerbate blade fatigue damage and shorten blade lifespan. Existing pitch control systems mainly focus on improving power generation efficiency, without fully considering the balanced control of blade loads, and lack precise monitoring and targeted adjustment mechanisms for real-time blade loads.

[0008] 4. Poor system robustness: The marine environment is characterized by strong interference and high uncertainty. The control algorithm of the existing pitch system has weak anti-interference ability. When encountering extreme conditions such as sudden wind, waves and turbulence, the system is prone to problems such as regulation instability and excessive overshoot, which affects the operational stability of the unit.

[0009] To address these issues, researchers in related fields have conducted preliminary explorations. For example, some studies have introduced platform attitude sensors into the pitch control system, attempting to optimize angle adjustment by compensating for platform motion. However, such solutions simply superimpose the platform attitude angle into the pitch control command without establishing a coupling model between platform motion and blade flow field and forces, thus failing to achieve precise adaptive adjustment. Other studies have employed intelligent algorithms such as fuzzy control and neural networks to optimize pitch control, but existing algorithms often suffer from complex parameter tuning and poor real-time performance, making it difficult to meet the dynamic and high-speed adjustment requirements of floating offshore wind power.

[0010] Therefore, in view of the dynamic motion characteristics and complex marine environment of floating offshore wind power platforms, this invention proposes a blade angle adjustment system that can sense multi-source operating parameters in real time, accurately establish a coupling model, and adaptively optimize the adjustment strategy to achieve real-time, accurate, and stable adjustment of the blade angle. Summary of the Invention

[0011] The purpose of this invention is to overcome the shortcomings of existing floating offshore wind turbine blade angle adjustment systems, such as slow response, insufficient adaptive capability, lack of load balance control, and poor robustness, and to provide a floating offshore wind turbine blade adaptive angle adjustment system. To achieve the above objective, this invention adopts the following technical solution:

[0012] A floating offshore wind turbine blade adaptive angle adjustment system includes a multi-source sensing module, a central control module, an adaptive drive module, and a status monitoring and feedback module.

[0013] The multi-source sensing module is used to collect multi-dimensional operating parameters of the floating wind power platform, blades and surrounding environment in real time and transmit them to the central control module.

[0014] The central control module is used to receive operating parameters, calculate the optimal target angle of the blade based on the coupling model and adaptive control algorithm, generate angle adjustment commands and transmit them to the adaptive drive module.

[0015] The adaptive drive module is used to receive angle adjustment commands and drive the blades to perform angle adjustment actions.

[0016] The status monitoring and feedback module is used to monitor the actual adjustment angle of the blade, the operating status of the drive module, and the real-time load on the blade in real time, and feeds the monitoring data back to the central control module to form a closed-loop regulation.

[0017] Furthermore, the multi-source sensing module includes an environmental parameter acquisition unit, a platform attitude acquisition unit, a blade status acquisition unit, and a unit operation parameter acquisition unit;

[0018] The environmental parameter acquisition unit includes a three-dimensional ultrasonic anemometer and a wind vane, used to acquire wind speed, wind direction and turbulence intensity;

[0019] The platform attitude acquisition unit includes an inertial measurement unit and a pressure sensor, used to acquire the platform's six-degree-of-freedom attitude parameters and draft.

[0020] The blade state acquisition unit includes a strain sensor, a pressure sensor array, and a fiber optic gyroscope, which are used to acquire the bending strain at the blade root, the pressure distribution on the blade surface, the blade rotation angle, and the angular velocity.

[0021] The unit's operating parameter acquisition unit includes a speed sensor and a power sensor, used to acquire the spindle speed and generator output power.

[0022] Furthermore, the central control module includes a data preprocessing unit, a coupled model construction unit, an adaptive control algorithm unit, and an instruction generation unit;

[0023] The data preprocessing unit uses the Kalman filter algorithm to filter, denoise, and standardize the operating parameters.

[0024] The coupled model building unit is based on the blade element-momentum theory and the platform attitude angle correction term to establish a coupled model of platform motion with blade force and flow field, and calculate the actual windward angle and total load of the blade;

[0025] The adaptive control algorithm unit adopts an algorithm that combines model predictive control and fuzzy neural network, with the dual optimization objectives of maximizing generator output power and minimizing blade load, to calculate the optimal target angle of the blade.

[0026] The instruction generation unit generates a limited angle adjustment instruction based on the optimal target angle and the current actual angle of the blade.

[0027] Furthermore, in the coupled model construction unit, the actual windward angle α of the blade... e The calculation formula is α e = α0 + Δα, where α0 is the ideal angle of attack, Δα is the additional angle of attack caused by the platform motion, Δα = α·cosφ + β·sinφ, α is the platform roll angle, β is the platform pitch angle, and φ is the blade rotation angle; total blade load , For aerodynamic loads, This refers to the structural load.

[0028] Furthermore, the objective function of the adaptive control algorithm unit is: ,in For the ideal maximum output power, This represents the actual output power of the generator. ω1 and ω2 are the allowable load thresholds for the blades, respectively, and the weighting coefficients for power optimization and load balancing. The inputs to the fuzzy neural network are the wind speed change rate, the platform attitude angle change rate, and the blade load deviation. The outputs are the control time domain and weighting coefficients ω1 and ω2 for model predictive control.

[0029] Furthermore, the adaptive drive module includes a pitch actuator, a reduction mechanism, and a position closed-loop controller; the pitch actuator is a permanent magnet synchronous servo motor, the reduction mechanism is a planetary gear reducer, and the position closed-loop controller uses a PID algorithm to precisely control the motor speed and angle.

[0030] Furthermore, the status monitoring and feedback module includes an angle monitoring unit, a drive status monitoring unit, and a load feedback unit; the angle monitoring unit adopts a high-precision absolute encoder, the drive status monitoring unit includes a current sensor, a voltage sensor, and a temperature sensor, and the load feedback unit adopts a strain sensor.

[0031] The beneficial effects of this invention are as follows:

[0032] 1. Fast response and high adjustment accuracy: This invention collects multi-dimensional operating parameters such as wind speed, platform attitude, and blade status in real time through a multi-source sensing module. The Kalman filter algorithm is used to preprocess the data, which improves the real-time performance and accuracy of data acquisition. At the same time, a coupled model of platform motion and blade force is established, which can accurately quantify the impact of platform motion on the blade's windward angle. Combining model predictive control and adaptive control algorithm of fuzzy neural network, the real-time optimization of blade angle adjustment command is realized, which effectively solves the problem of response lag in existing systems and ensures that the blade is always in the optimal windward state.

[0033] 2. Strong Adaptability: The adaptive control algorithm adopted in this invention can adaptively adjust the control parameters (control time domain, weighting coefficient) according to real-time operating parameters such as wind speed change rate, platform attitude angle change rate, and blade load deviation. It can adapt to different sea conditions (light wind, strong wind, giant waves) and changes in platform motion state without manual intervention, effectively improving the system's adaptability to complex marine environments.

[0034] 3. Achieving load balancing control: This invention aims to maximize generator output power and minimize blade load. Through real-time monitoring and feedback of blade load, it can effectively balance blade load while adjusting blade angle, reduce blade fatigue damage, extend blade service life, and improve the operational reliability of the unit.

[0035] 4. High robustness: This invention, through the fusion sensing of multi-source parameters and closed-loop feedback control, combined with the anti-interference capability of adaptive control algorithms, can effectively resist the interference of extreme working conditions such as sea waves and turbulence, avoid problems such as system instability and excessive overshoot, and improve the operational stability of the unit. Attached Figure Description

[0036] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of the present invention and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0037] Figure 1 This is a block diagram of the internal structure of the multi-source sensing module of the present invention;

[0038] Figure 2 This is a block diagram of the internal structure of the central control module of the present invention;

[0039] Figure 3 This is a block diagram of the internal structure of the adaptive driving module of the present invention.

[0040] Figure 4This is a flowchart of the closed-loop regulation process of the present invention. Detailed Implementation

[0041] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. The components of the embodiments of the present invention described and shown in the accompanying drawings can generally be arranged and designed in various different configurations.

[0042] In the description of the embodiments of the present invention, it should also be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," and "link" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. Those skilled in the art can understand the specific meaning of the above terms in the present invention according to the specific circumstances.

[0043] A floating offshore wind turbine blade adaptive angle adjustment system includes a multi-source sensing module, a central control module, an adaptive drive module, and a status monitoring and feedback module.

[0044] The multi-source sensing module is used to collect multi-dimensional operating parameters of the floating wind power platform, blades and surrounding environment in real time, and transmit the collected parameters to the central control module.

[0045] The central control module receives operating parameters transmitted by the multi-source sensing module, calculates the optimal target angle of the blade based on the preset coupling model and adaptive control algorithm, generates the corresponding angle adjustment command, and transmits it to the adaptive drive module.

[0046] The adaptive drive module is used to receive angle adjustment commands transmitted from the central control module, drive the blades to perform angle adjustment actions, and achieve precise control of the blade angle.

[0047] The status monitoring and feedback module is used to monitor the actual adjustment angle of the blade, the operating status of the drive module and the real-time load of the blade in real time, and feeds the monitoring data back to the central control module to form a closed-loop regulation.

[0048] 1. Multi-source sensing module

[0049] The multi-source sensing module includes an environmental parameter acquisition unit, a platform attitude acquisition unit, a blade status acquisition unit, and a unit operation parameter acquisition unit;

[0050] The environmental parameter acquisition unit includes a three-dimensional ultrasonic anemometer and a wind vane installed on the top of the wind turbine nacelle, which are used to collect wind speed v, wind direction θ and turbulence intensity I in real time, with a acquisition frequency of 10-20Hz.

[0051] The platform attitude acquisition unit includes an inertial measurement unit (IMU) installed at the center of gravity of the floating platform and a pressure sensor installed at the bottom of the platform. The inertial measurement unit is used to acquire the platform's six degrees of freedom attitude parameters in real time, including roll angle α, pitch angle β, yaw angle γ, sway displacement x, sway displacement y, and heave displacement z; the pressure sensor is used to acquire the platform's draft h to help determine the platform's motion state.

[0052] The blade state acquisition unit includes a strain sensor installed at the blade root, a pressure sensor array installed on the blade surface, and a fiber optic gyroscope installed at the blade tip. The strain sensor is used to acquire the bending strain ε at the blade root in real time and calculate the load F at the blade root. The pressure sensor array is used to acquire the pressure distribution P(x,y,t) on the blade surface and obtain the blade flow field information. The fiber optic gyroscope is used to acquire the real-time rotation angle φ and angular velocity ω of the blade.

[0053] The unit's operating parameter acquisition unit includes a speed sensor mounted on the main shaft and a power sensor mounted on the generator, used to acquire the main shaft speed n and the generator output power P in real time. out .

[0054] 2. Central Control Module

[0055] The central control module is the core of the system, including a data preprocessing unit, a coupled model construction unit, an adaptive control algorithm unit, and an instruction generation unit;

[0056] (1) Data preprocessing unit: used to filter, denoise, and standardize the raw parameters collected by the multi-source sensing module, remove abnormal data, and improve data accuracy; specifically, the Kalman filter algorithm is used to filter dynamic parameters such as wind speed and platform attitude angle. The state equation and observation equation of the Kalman filter are as follows:

[0057] State equation: X(k) = AX(k-1) + BU(k) + W(k)

[0058] Observation equation: Z(k) = HX(k) + V(k)

[0059] Where X(k) is the system state vector at time k, A is the state transition matrix, B is the control input matrix, U(k) is the control input at time k, W(k) is the process noise vector, which follows a Gaussian distribution N(0,Q), and Q is the process noise covariance matrix; Z(k) is the observation vector at time k, H is the observation matrix, V(k) is the observation noise vector, which follows a Gaussian distribution N(0,R), and R is the observation noise covariance matrix;

[0060] (2) Coupled model building unit: used to establish a coupled model between the motion of the floating platform and the forces and flow field of the blades, and to quantify the influence of the platform motion on the windward angle and forces of the blades;

[0061] First, based on the blade element-momentum theory (BEM theory), a basic aerodynamic model of the blade is established to calculate the aerodynamic loads on the blade under an ideal steady-state flow field; the core formula of the blade element-momentum theory is:

[0062]

[0063]

[0064] Among them, C T C is the thrust coefficient. P Here, denoted as power coefficient and 'a' as axial induction factor;

[0065] Secondly, considering the influence of the floating platform's motion, a platform attitude angle correction term is introduced to establish a coupled aerodynamic model; the actual windward angle α of the blades... e It consists of the ideal angle of attack α0 and the additional angle of attack Δα caused by the platform motion, that is:

[0066]

[0067] The additional angle of attack Δα is determined by the platform's roll angle α, pitch angle β, and blade rotation angle φ, and is calculated using the following formula:

[0068] Δα = α·cosφ + β·sinφ

[0069] Based on the corrected actual angle of attack α e By combining the pressure distribution P(x,y,t) on the blade surface and the blade rotational angular velocity ω, the aerodynamic load calculation model of the blade is modified to obtain the real-time aerodynamic load of the blade considering the platform motion coupling effect. ;

[0070] Simultaneously, the structural loads calculated by combining the strain ε at the blade root are obtained. Establish the total load model for the blades:

[0071]

[0072] (3) Adaptive control algorithm unit: The adaptive control algorithm based on the combination of model predictive control (MPC) and fuzzy neural network is used to calculate the optimal target angle of the blade;

[0073] First, to maximize generator output power and total blade load. Minimization is the dual optimization objective; the objective function J is established as follows:

[0074]

[0075] in, For the ideal maximum output power, This represents the allowable load threshold for the blade. , These are the weighting coefficients for power optimization and load balancing, which are dynamically adjusted according to actual operating conditions.

[0076] Secondly, based on the blade load model and flow field model obtained from the coupled model construction unit, a prediction model for the system is established to predict the future period (prediction time domain N). p The effect of blade angle change on output power and load;

[0077] Finally, the parameters of the model predictive control are adaptively tuned using a fuzzy neural network. The inputs to the fuzzy neural network are the wind speed change rate Δv, the platform attitude angle change rate Δα, Δβ, and the blade load deviation ΔF. The output is the control time domain N of the model predictive control. c and weighting coefficients , This enables real-time optimization of control parameters;

[0078] (4) Command generation unit: Based on the optimal target angle calculated by the adaptive control algorithm unit and combined with the current actual angle of the blade, the unit generates the corresponding angle adjustment command. The formula for calculating the adjustment command is:

[0079]

[0080] in, For the optimal target angle, This is the current actual angle of the blade; at the same time, the adjustment command is limited to ensure that the adjustment angle is within the safe operating range of the blade (usually 0°-90°).

[0081] 3. Adaptive Driver Module

[0082] The adaptive drive module includes a pitch actuator, a reduction mechanism, and a position closed-loop controller;

[0083] The pitch actuator uses a permanent magnet synchronous servo motor, which features fast response speed, high control accuracy and high power density, and can meet the needs of rapid blade angle adjustment.

[0084] The reduction mechanism uses a planetary gear reducer to reduce the motor speed and increase the output torque, ensuring that the blades can be driven to achieve angle adjustment.

[0085] The position closed-loop controller is used to receive angle adjustment commands transmitted from the central control module. The encoder collects the motor's angular position in real time, and a PID algorithm is used to precisely control the motor speed and angle, driving the blades to quickly and smoothly adjust to the target angle. The control law for PID control is:

[0086]

[0087] Where u(t) is the motor control voltage, K p K is the proportionality coefficient. i K is the integral coefficient. d Here are the differential coefficients, and e(t) is the angular deviation (e(t = ...). - ).

[0088] 4. Status Monitoring and Feedback Module

[0089] The condition monitoring and feedback module includes an angle monitoring unit, a drive condition monitoring unit, and a load feedback unit;

[0090] The angle monitoring unit uses a high-precision absolute encoder, which is installed at the output end of the pitch actuator to collect the actual adjustment angle of the blades in real time. The accuracy can reach 0.01°, and the angle data is fed back to the central control module for correction of adjustment commands;

[0091] The drive condition monitoring unit includes a current sensor, a voltage sensor, and a temperature sensor, used to monitor the operating current I of the pitch actuator in real time. m Operating voltage U m and winding temperature T m When the detected parameters exceed the safety threshold, an alarm signal is promptly sent to the central control module to ensure the safe operation of the drive module.

[0092] The load feedback unit uses strain sensors installed at the blade root to collect real-time load data of the blade. The load data is fed back to the central control module as input to the adaptive control algorithm to achieve closed-loop control with load balancing.

[0093] In summary, this invention can adapt to complex marine environments and platform movements in real time, improve adjustment accuracy and response speed, balance blade load, enhance system robustness, and ensure efficient and stable operation of the unit.

[0094] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A floating offshore wind turbine blade adaptive angle adjustment system, characterized in that, It includes a multi-source sensing module, a central control module, an adaptive driving module, and a status monitoring and feedback module; The multi-source sensing module is used to collect multi-dimensional operating parameters of the floating wind power platform, blades and surrounding environment in real time and transmit them to the central control module. The central control module is used to receive operating parameters, calculate the optimal target angle of the blade based on the coupling model and adaptive control algorithm, generate angle adjustment commands and transmit them to the adaptive drive module. The adaptive drive module is used to receive angle adjustment commands and drive the blades to perform angle adjustment actions. The status monitoring and feedback module is used to monitor the actual adjustment angle of the blade, the operating status of the drive module, and the real-time load on the blade in real time, and feeds the monitoring data back to the central control module to form a closed-loop regulation.

2. The adaptive angle adjustment system for floating offshore wind turbine blades according to claim 1, characterized in that: The multi-source sensing module includes an environmental parameter acquisition unit, a platform attitude acquisition unit, a blade status acquisition unit, and a unit operation parameter acquisition unit. The environmental parameter acquisition unit includes a three-dimensional ultrasonic anemometer and a wind vane, used to acquire wind speed, wind direction and turbulence intensity; The platform attitude acquisition unit includes an inertial measurement unit and a pressure sensor, used to acquire the platform's six-degree-of-freedom attitude parameters and draft. The blade state acquisition unit includes a strain sensor, a pressure sensor array, and a fiber optic gyroscope, which are used to acquire the bending strain at the blade root, the pressure distribution on the blade surface, the blade rotation angle, and the angular velocity. The unit's operating parameter acquisition unit includes a speed sensor and a power sensor, used to acquire the spindle speed and generator output power.

3. The adaptive angle adjustment system for floating offshore wind turbine blades according to claim 1, characterized in that: The central control module includes a data preprocessing unit, a coupled model construction unit, an adaptive control algorithm unit, and an instruction generation unit. The data preprocessing unit uses the Kalman filter algorithm to filter, denoise, and standardize the operating parameters. The coupled model building unit is based on the blade element-momentum theory and the platform attitude angle correction term to establish a coupled model of platform motion with blade force and flow field, and calculate the actual windward angle and total load of the blade; The adaptive control algorithm unit adopts an algorithm that combines model predictive control and fuzzy neural network, with the dual optimization objectives of maximizing generator output power and minimizing blade load, to calculate the optimal target angle of the blade. The instruction generation unit generates a limited angle adjustment instruction based on the optimal target angle and the current actual angle of the blade.

4. The adaptive angle adjustment system for floating offshore wind turbine blades according to claim 3, characterized in that: In the coupled model construction unit, the actual windward angle α of the blade e The calculation formula is α e = α0 + Δα, where α0 is the ideal angle of attack, Δα is the additional angle of attack caused by the platform motion, Δα = α·cosφ + β·sinφ, α is the platform roll angle, β is the platform pitch angle, and φ is the blade rotation angle; Total blade load , For aerodynamic loads, This refers to the structural load.

5. The adaptive angle adjustment system for floating offshore wind turbine blades according to claim 3, characterized in that: The objective function of the adaptive control algorithm unit is: ,in For the ideal maximum output power, This represents the actual output power of the generator. ω1 and ω2 are the allowable load thresholds for the blades, respectively, and the weighting coefficients for power optimization and load balancing. The inputs to the fuzzy neural network are the wind speed change rate, the platform attitude angle change rate, and the blade load deviation. The outputs are the control time domain and weighting coefficients ω1 and ω2 for model predictive control.

6. The adaptive angle adjustment system for floating offshore wind turbine blades according to claim 1, characterized in that: The adaptive drive module includes a pitch actuator, a reduction mechanism, and a position closed-loop controller; the pitch actuator is a permanent magnet synchronous servo motor, the reduction mechanism is a planetary gear reducer, and the position closed-loop controller uses a PID algorithm to precisely control the motor speed and angle.

7. The adaptive angle adjustment system for floating offshore wind turbine blades according to claim 1, characterized in that: The status monitoring and feedback module includes an angle monitoring unit, a drive status monitoring unit, and a load feedback unit; the angle monitoring unit adopts a high-precision absolute encoder, the drive status monitoring unit includes a current sensor, a voltage sensor, and a temperature sensor, and the load feedback unit adopts a strain sensor.

Images