Adaptive anti-disturbance floating wind power foundation structure type and intelligent construction method

Abstract

The application discloses an adaptive anti-interference floating wind power foundation structure type and an intelligent construction method, and comprises the following steps: collecting multi-dimensional parameters such as wind, wave, flow load, structure geometry and mass distribution through an extreme sea state construction simulation platform; analyzing structure stress transmission and deformation characteristics by using a floating foundation multi-body coupling dynamic model, real-time regulating and controlling the space posture of a machine cabin, a blade and a tower by using a wind turbine unit posture anti-interference control model, and calculating and predicting construction errors such as positioning and docking by using an intelligent construction error compensation prediction algorithm; pre-rehearsing a construction process and optimizing parameters through the simulation platform, and completing the installation of the floating foundation, the hoisting of the wind turbine unit and the docking of the structure according to the optimized scheme. The application forms a collaborative regulation and control system of 'parameter collection-model analysis-error prediction-scheme optimization-construction execution', improves the construction accuracy and stability, and provides reliable technical support for deep-sea wind power structure construction.

Description

Technical Field

[0001] This invention relates to the field of intelligent construction technology for wind power structures, and in particular to an adaptive, disturbance-resistant floating wind power foundation structure and its intelligent construction method. Background Technology

[0002] As offshore wind power expands into deep-sea areas, the multi-field coupling effects of wind, waves, and currents caused by extreme sea conditions pose a severe challenge to the safety and accuracy of floating wind turbine construction. Deep-sea areas have complex seabed topography and drastic spatiotemporal variations in environmental loads, making traditional construction methods ill-suited to these dynamic and complex conditions. Floating wind turbine structures, consisting of floating foundations, wind turbine generators, and connectors, are prone to significant attitude shifts and structural deformations under extreme sea conditions (i.e., winds exceeding force 10 and waves exceeding 6 meters), directly impacting the continuity of the construction process and the precision of structural assembly. Simultaneously, the demands for efficiency and reliability in offshore wind power construction continue to rise, necessitating the development of a technical solution capable of coping with extreme sea state disturbances and achieving intelligent control of the construction process. This is crucial to addressing the prominent issues of poor environmental adaptability and difficulty in ensuring construction quality in deep-sea floating wind turbine construction.

[0003] The existing technology has two core drawbacks: First, it lacks a coordinated consideration of the multi-body coupled dynamic characteristics of the floating foundation and the attitude disturbance of the wind turbine. During construction, it fails to establish an integrated control mechanism that takes into account both multi-body force transmission and attitude disturbance resistance, resulting in a lag in structural attitude adjustment under extreme sea conditions. This makes it difficult to effectively offset the disturbance caused by environmental loads, leading to the accumulation of construction deviations. Second, the construction error compensation and scheme optimization lack dynamic adaptability. It has not formed an error prediction and parameter adjustment system based on real-time sea condition data and construction status feedback. It is impossible to predict construction risks and optimize processes in advance through simulation, making the construction scheme insufficiently adaptable to extreme sea conditions and difficult to achieve adaptive disturbance resistance control during the construction process. Summary of the Invention

[0004] In order to overcome the shortcomings and deficiencies of existing technologies, this invention provides an adaptive anti-disturbance floating wind power foundation structure and an intelligent construction method.

[0005] The technical solution adopted in this invention is an adaptive disturbance-resistant floating wind turbine foundation structure and intelligent construction method, including the following steps: S1, collecting wind load, wave load, current load, and seabed topography distribution data based on an extreme sea state construction simulation platform, constructing a sea state parameter database including spatiotemporal coupling characteristics, and simultaneously acquiring the floating foundation's geometric dimensions, wind turbine component mass distribution, and construction equipment operating parameters; S2, performing dynamic response analysis on the collected sea state parameters and structural parameters using a multi-body coupled dynamic model of the floating foundation to determine the force transmission path and deformation characteristics of the floating foundation and connecting parts; S3, using a wind turbine attitude disturbance-resistant control model to control the spatial attitude of the wind turbine nacelle, blades, and tower. The system performs real-time control of the state, offsetting the impact of sea state disturbances on the structural attitude by dynamically adjusting control parameters; S4, it uses an intelligent construction error compensation prediction algorithm to calculate and predict the foundation positioning deviation, structural docking deviation, and attitude adjustment deviation generated during construction in real time; S5, based on the model analysis results and error prediction data, it uses an extreme sea state construction simulation platform to perform construction process pre-run and parameter optimization, generating an adaptive anti-disturbance construction scheme; S6, according to the optimized construction scheme, it integrates the construction equipment actuators and control modules to complete the intelligent construction operation of floating foundation installation, wind turbine hoisting, and structural docking, using various models and platforms throughout the process for dynamic feedback and parameter adjustment of the construction state.

[0006] Furthermore, the expression for the multi-body coupled dynamic model of the floating foundation is as follows: , in, The mass matrix of the floating foundation multibody coupling is the same as the spatial coordinates of the floating foundation. Related; These are the acceleration vector, velocity vector, and displacement vector of the floating foundation coupled system, respectively. The damping matrix is ​​associated with the velocity vector and the ocean current velocity. This is the stiffness matrix, which is related to the displacement vector; This is the extreme sea state environment load vector, including time. Waves and flow angle The construction constraint load vector contains the coordinates of the constraint points. and constraint point velocity .

[0007] Furthermore, the expression for the wind turbine attitude disturbance rejection control model is as follows: , in, The estimated rate of change of attitude state over time; This is the wind turbine attitude state estimation vector; The state matrix, To control the input matrix, For attitude control input; The observer gain matrix; The attitude measurement output vector, This is the output matrix; The perturbation input matrix; The attitude disturbance load vector includes wind speed. Blade angular velocity and tower tilt angle .

[0008] Furthermore, the expression for the intelligent construction error compensation prediction algorithm is as follows: , in, for Predict the construction error vector at all times; These are the error weighting coefficients. For history Construction error vector at any given moment; For the algorithm iteration coefficients, For the objective function in parameters gradient at; Let covariance matrix be the variance matrix. This is the parameter correction amount; This is the disturbance compensation coefficient; This is a vector of error influencing factors, including positioning deviation. docking deviation and time delay .

[0009] Furthermore, the optimization model expression for the construction parameters of the extreme sea state construction simulation platform is as follows: , in, To optimize the objective function; These are the weighting coefficients; This is the actual displacement vector. Let the desired displacement vector be denoted as '('). To control the input amount; This is the construction error vector; This refers to the duration of the construction simulation. This is the terminal cost function, which is associated with the terminal displacement, control input, and construction error at the terminal time.

[0010] Furthermore, the dynamic adjustment model expression for the intelligent construction of the adaptive disturbance-resistant floating wind turbine structure is as follows: , in, The control input is adaptively adjusted; This is the initial control input; This is an adaptive gain matrix, relating displacement, velocity, and construction error; For actual environmental loads, To estimate environmental loads; This is the error compensation control quantity, associated with construction errors and error change rates.

[0011] Further, S3 includes the following sub-steps: S31, collecting data on the center of gravity position of the wind turbine nacelle, the blade tip trajectory, and the tower bottom rotation angle through distributed attitude sensors, converting the collected data into an attitude parameter sequence in a unified coordinate system, and synchronously transmitting it to the control module; S32, based on the wind turbine attitude disturbance resistance control model, calculating the initial attitude control quantity according to the deviation between the attitude parameter sequence and the preset attitude reference value, and simultaneously introducing sea state disturbance observation values ​​to preliminarily correct the control quantity; S33, driving the nacelle yaw actuator, blade pitch mechanism, and tower vibration damping device through the control module to perform coordinated actions according to the corrected control quantity, adjusting the spatial attitude of each component of the wind turbine in real time, and maintaining structural attitude stability.

[0012] Further, S4 includes the following sub-steps: S41, collecting real-time data on the floating foundation positioning coordinates, structural docking surface gaps, and attitude adjustment amounts during construction, establishing an error data acquisition channel to ensure the continuity and synchronization of data transmission; S42, inputting the collected error data into an intelligent construction error compensation prediction algorithm, identifying the root causes of errors through the algorithm, and constructing an error development trend model by combining historical error data; S43, predicting the error change range in subsequent construction stages based on the error development trend model, generating corresponding error compensation amounts, and transmitting the compensation amounts to the construction execution system to provide data support for adjusting construction parameters.

[0013] Further, S5 includes the following sub-steps: S51, importing the dynamic response results of the floating foundation multi-body coupled dynamic model, the control effect data of the wind turbine attitude disturbance prevention control model, and the error data of the intelligent construction error compensation prediction algorithm into the extreme sea state construction simulation platform; S52, building a virtual simulation environment consistent with the actual construction scenario in the platform, and setting dynamic change boundary conditions for sea state parameters, structural parameters, and construction equipment parameters; S53, running the simulation platform to simulate the construction process, recording the structural stress, attitude changes, and construction error calibration data during the simulation, and analyzing the feasibility and rationality of the construction plan; S54, adjusting and optimizing the equipment operation parameters, control parameters, and error compensation strategies in the construction plan based on the simulation results, and generating an adaptive disturbance prevention construction plan adapted to extreme sea states.

[0014] An adaptive, disturbance-resistant floating wind turbine foundation structure and intelligent construction method are presented. This structure is implemented through different units, including: a multi-dimensional acquisition and processing unit for extreme sea state parameters, a multi-body coupled dynamics analysis unit for the floating foundation, a wind turbine attitude disturbance resistance collaborative control unit, an intelligent construction error prediction and compensation unit, an extreme sea state construction simulation and scheme optimization unit, and an adaptive disturbance-resistant construction execution and dynamic feedback unit. The multi-dimensional acquisition and processing unit for extreme sea state parameters communicates bidirectionally with the multi-body coupled dynamics analysis unit for the floating foundation, transmitting processed sea state and structural parameters to the analysis unit. After completing the dynamic response analysis using the multi-body coupled dynamics model of the floating foundation, the analysis unit synchronizes the results to the wind turbine attitude disturbance resistance collaborative control unit and the intelligent construction error prediction unit. The wind turbine attitude disturbance rejection collaborative control unit outputs attitude control signals based on the wind turbine attitude disturbance rejection control model. The intelligent construction error prediction and compensation unit generates error compensation data through the intelligent construction error compensation prediction algorithm. The output signals of both units are transmitted to the extreme sea state construction simulation and scheme optimization unit. The extreme sea state construction simulation and scheme optimization unit uses the extreme sea state construction simulation platform to optimize the construction scheme and sends the optimized construction instructions to the adaptive disturbance rejection construction execution and dynamic feedback unit. The adaptive disturbance rejection construction execution and dynamic feedback unit executes the construction operation and feeds back the real-time construction status data to each preceding unit to form a closed-loop control and carry out intelligent construction of the adaptive disturbance rejection floating wind power structure.

[0015] Beneficial Effects: This invention proposes an adaptive, disturbance-resistant floating wind turbine foundation structure and an intelligent construction method. It analyzes the force transmission path and deformation characteristics of the structure using a multi-body coupled dynamic model, and coordinates with an attitude disturbance-resistant control model to adjust the spatial attitude of the nacelle, blades, and tower in real time, forming a multi-dimensional collaborative control mechanism. This quickly offsets the effects of wind, wave, and current coupling disturbances under extreme sea conditions, avoiding attitude adjustment lag and the accumulation of construction deviations. Addressing the shortcomings of existing technologies in error compensation and dynamic adaptation for scheme optimization, this invention relies on an intelligent construction error compensation prediction algorithm to calculate and predict positioning, docking, and other construction errors in real time. Combined with an extreme sea condition construction simulation platform, it conducts construction process pre-runs and parameter optimization, forming a closed-loop control system of data acquisition, analysis and prediction, scheme optimization, and dynamic feedback, significantly improving the adaptability of the construction scheme to extreme sea conditions. Simultaneously, through the coordinated linkage of six functional units and the refined execution of each step, it achieves intelligent and precise control of the construction process, greatly improving the safety, stability, and assembly accuracy of deep-sea floating wind turbine structures, providing reliable technical support for the development of deep-sea wind power resources. Attached Figure Description

[0016] Figure 1 This is a flowchart of the method steps of the present invention; Figure 2This is a structural implementation unit composition diagram of the present invention. Detailed Implementation

[0017] It should be noted that, unless otherwise specified, the embodiments and features described in this application can be combined with each other. The application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0018] like Figure 1 As shown, the adaptive disturbance-resistant floating wind turbine foundation structure and intelligent construction method include the following steps: S1, based on the extreme sea state construction simulation platform, collects wind load, wave load, current load and seabed topography distribution data, constructs a sea state parameter database including spatiotemporal coupling characteristics, and simultaneously obtains floating foundation geometry, wind turbine component mass distribution and construction equipment operation parameters; Specifically, step S1 involves collecting multi-dimensional parameters through an extreme sea state construction simulation platform. The platform's wind speed sensor, wave sensor, current sensor, and topographic detection equipment continuously acquire data at a sampling frequency of 10 milliseconds. Wind load parameters include instantaneous wind speed, gust duration, and wind direction change angle, with a collection range of 0 to 70 meters per second for wind speed and 0 to 360 degrees for wind direction angle. Wave load parameters include wave height, period, and wave direction, covering wave heights of 0.5 to 15 meters and periods of 2 to 20 seconds. Current load parameters include current velocity and current direction, with a collection range of current velocity of 0.1 to 3 meters per second and current direction angle of 0 to 360 degrees. Seabed topographic distribution data is acquired using a multibeam echo sounder with a detection accuracy of 0.1 meters, covering topographic undulation data within a 500-meter radius of the construction area. Simultaneously, the structural parameter acquisition module records the geometric dimensions of the floating foundation, including length, width, height, and wall thickness, accurate to 0.01 meters. Mass distribution data for components such as the wind turbine nacelle, blades, and tower are also collected concurrently, with the mass measurement accuracy for each component controlled to 0.1 kg. Construction equipment operating parameters include the crane's rated lifting capacity, operating radius, and hoisting speed. The lifting capacity range is 10 to 1000 tons, the operating radius is 5 to 50 meters, and the hoisting speed is 0.1 to 1 meter per second. All collected data is transmitted to a data storage unit, constructing a database of sea state and structural parameters containing over 100,000 valid data points. This provides comprehensive and accurate basic data support for subsequent model analysis. This step requires ensuring that the sensor spacing does not exceed 10 meters and the data transmission delay does not exceed 50 milliseconds to guarantee the continuity and timeliness of parameter acquisition.

[0019] S2, by using a multi-body coupled dynamic model of the floating foundation to perform dynamic response analysis on the collected sea state parameters and structural parameters, the force transmission path and deformation characteristics of the floating foundation and connecting parts are determined. Specifically, step S2 utilizes a multi-body coupled dynamic model of the floating foundation to perform dynamic response analysis on the collected sea state and structural parameters. The model input data includes time-series data of wind, wave, and current loads collected in step S1, as well as structural parameters of the floating foundation and wind turbine. Numerical calculations are performed in 0.01-second time steps, focusing on analyzing the force transmission path of the floating foundation and connectors under multi-field coupling, clarifying the force transmission sequence from the bottom of the floating foundation to the bottom of the wind turbine tower, and calculating the tensile, compressive, and shear forces at each connection node. The force analysis range is 1000 to 1000000 Newtons. Simultaneously, the model outputs deformation characteristic data such as vertical displacement, horizontal displacement, and angular deformation of the floating foundation. The displacement analysis accuracy reaches 0.001 meters, and the angular accuracy reaches 0.01 degrees, determining the maximum peak value and variation law of structural deformation under different sea state combinations. During implementation, the data in the parameter database was first categorized according to sea state levels, into five different extreme sea state levels. Dynamic response calculations were then performed for each level, with at least 1000 iterations for each level to ensure the reliability of the analysis results. This step identifies the structural weaknesses and key deformation areas under extreme sea states, providing a targeted basis for subsequent attitude control and error compensation. During implementation, the convergence of the model calculations must be guaranteed, with the convergence error controlled within 0.0001, and the calculation time not exceeding 60 minutes.

[0020] S3 uses a wind turbine attitude disturbance rejection control model to adjust the spatial attitude of the wind turbine nacelle, blades and tower in real time, and offsets the impact of sea state disturbance on the structural attitude by dynamically adjusting the control parameters. Specifically, step S3 uses a wind turbine attitude disturbance rejection control model to perform real-time control of the spatial attitude of each component of the wind turbine. The controlled objects include the nacelle, blades, and tower. Attitude data is collected by a three-axis gyroscope installed on the top of the nacelle, strain sensors at the root of the blades, and tilt sensors in the middle of the tower. The sensor sampling frequency is 20 Hz. The data collected includes the yaw angle, pitch angle, and roll angle of the nacelle; the flapping angle, yaw angle, and torsion angle of the blades; and the tilt angle and bending angle of the tower. The angle acquisition range is -90 to 90 degrees, and the measurement accuracy is 0.01 degrees. The control model dynamically adjusts control parameters based on the deviation between the collected attitude data and the preset baseline attitude value. The nacelle yaw control parameters include yaw rate and yaw acceleration, with adjustment ranges of 0.1 to 1 degree per second and 0.01 to 0.1 degrees per square second, respectively. The blade pitch control parameter is the pitch rate, with an adjustment range of 0.5 to 5 degrees per second. The tower damping control parameter is the damper damping coefficient, with an adjustment range of 1000 to 10000 N / m. During implementation, the control model outputs control commands at 50-millisecond control cycles, driving the corresponding actuators. The nacelle yaw actuator, blade pitch mechanism, and tower damping device respond collaboratively, continuously adjusting to offset the impact of sea state disturbances on the structural attitude, maintaining the attitude deviation of each component within ±0.5 degrees. This step must ensure stable sensor data transmission, actuator response delays not exceeding 30 milliseconds, and smooth, abrupt control parameter adjustments to guarantee the real-time performance and accuracy of attitude control.

[0021] S4 utilizes an intelligent construction error compensation prediction algorithm to calculate and predict in real time the foundation positioning deviation, structural docking deviation, and attitude adjustment deviation generated during the construction process. Specifically, step S4 employs an intelligent construction error compensation and prediction algorithm to calculate and predict various deviations during the construction process in real time. The objects of error calculation and prediction include foundation positioning deviation, structural docking deviation, and attitude adjustment deviation. Real-time error data is collected using laser positioning devices, displacement sensors, and angle sensors installed on the construction equipment. The accuracy of the positioning deviation acquisition is 0.001 meters, the docking deviation acquisition accuracy is 0.01 millimeters, and the attitude adjustment deviation acquisition accuracy is 0.01 degrees. The sensor data update frequency is 10 Hz. The algorithm first smooths the collected real-time error data to eliminate random noise interference. Then, it constructs an error time series model based on 500 historical error data sets. By analyzing the error change trend through the model, it predicts the error development within the next 10 seconds, with prediction accuracy controlled within ±0.005 meters. During implementation, the algorithm outputs real-time error values ​​and predicted error values ​​at a calculation cycle of 20 milliseconds. The foundation positioning deviation calculation includes the positional deviations of the floating foundation in the x, y, and z directions; the structural docking deviation calculation includes the flatness deviation and coaxiality deviation of the docking surface; and the attitude adjustment deviation calculation involves the angular deviations of various components. Meanwhile, the algorithm divides the warning levels into three levels based on the magnitude of the error. When the error value exceeds 80% of the preset threshold, a level one warning is triggered; when it exceeds 90%, a level two warning is triggered; and when it exceeds 100%, a level three warning is triggered. This provides a clear basis for subsequent adjustments to construction parameters. This step must ensure the algorithm's computational efficiency, with a single calculation time not exceeding 10 milliseconds and an error prediction hit rate of not less than 95%.

[0022] S5, based on model analysis results and error prediction data, uses an extreme sea state construction simulation platform to perform construction process pre-simulation and parameter optimization, and generates an adaptive anti-disturbance construction scheme. Specifically, step S5, based on the aforementioned model analysis results and error prediction data, uses an extreme sea state construction simulation platform to conduct a pre-simulation of the construction process and parameter optimization. The virtual simulation environment built on the platform recreates the actual construction scenario at a 1:1 scale. The imported basic data includes the dynamic response results of step S2, the attitude control data of step S3, and the error data of step S4. The simulation time step is set to 0.1 seconds, and the simulation duration covers the entire construction process, not less than 1800 seconds. During the pre-simulation, key construction stages such as floating foundation installation, wind turbine hoisting, and structural docking are simulated. Key data such as structural stress, attitude changes, and construction errors are recorded in real time at an interval of 0.5 seconds, generating no less than 3600 sets of simulation data. Parameter optimization targets three core parameters: construction equipment operation parameters, attitude control parameters, and error compensation parameters. A multi-objective optimization strategy is adopted, with the optimization objectives being minimum structural stress, minimum construction error, and maximum construction efficiency. Weight coefficients are set for each objective, and the optimal parameter combination is obtained through 1000 iterations. The optimized construction plan clearly defines the equipment operation specifications, parameter value ranges, and time node requirements for each construction stage. The accuracy of equipment operation parameters reaches 0.01, the adjustment step size of control parameters is 0.001, and the time node error does not exceed 10 seconds. This step must ensure that the consistency error between the simulation environment and the actual scenario does not exceed 5%, and the validity verification pass rate of the optimized parameters is no less than 90%.

[0023] S6, following the optimized construction plan, integrates the construction equipment actuators and control modules to complete intelligent construction operations for floating foundation installation, wind turbine hoisting, and structural connection. Throughout the process, it utilizes various models and platforms for dynamic feedback and parameter adjustment of the construction status.

[0024] Specifically, in the S6 construction process, the optimized specialized construction plan is strictly followed. High-precision construction equipment actuators are deeply integrated with intelligent control modules to construct an intelligent construction system with a closed-loop "perception-decision-execution" mechanism, enabling fully automated and precise construction operations. The entire construction process proceeds logically, covering three core stages: floating foundation installation, wind turbine hoisting, and structural connection. Each stage is linked in real-time through a collaborative communication link built by the control module, ensuring smooth construction flow without any interruptions. During the floating foundation installation stage, the construction team uses optimized 3D positioning parameters as the core benchmark and a dynamically adjustable mooring system to precisely calibrate the floating foundation's position. During positioning, laser positioning devices deployed at key parts of the foundation collect position data at millisecond-level frequencies and feed it back to the central control module in real time, forming a dynamic adjustment mechanism of "collection-analysis-correction." Based on the deviation between the feedback data and the preset benchmark value, the control module automatically calculates the adjustment amount and drives the traction mechanism of the mooring system to make minute adjustments until the positioning deviation of the floating foundation in the three directions of x-axis (horizontal transverse), y-axis (horizontal longitudinal), and z-axis (vertical height) is strictly controlled within 0.01 meters. To ensure the long-term stability of the foundation after installation, this stage of installation work lasts no less than 300 seconds, during which the horizontality, verticality, and overturning moment of the foundation are monitored simultaneously to ensure that all indicators meet the design specifications, laying a solid foundation for the subsequent hoisting of the wind turbine. During the wind turbine hoisting stage, a heavy-duty crane with optimized parameters is selected and operates precisely according to the three core parameters of preset lifting capacity, operating radius, and hoisting speed. The lifting capacity is strictly controlled within 80% to 90% of the crane's rated load to avoid overloading and maximize equipment efficiency. The operating radius is verified using both GPS positioning and laser ranging, with an error controlled within 0.1 meters to ensure precise alignment between the unit's landing point and the foundation installation location. The lifting speed adopts a uniform-gradient mode, with acceleration not exceeding 0.01 meters per second squared, minimizing inertial impact forces caused by sudden speed changes and protecting the unit's precision components from damage. High-precision attitude sensors are installed on the nacelle top and key blade nodes to capture real-time pitch, yaw, and roll angle data during lifting. The control module dynamically adjusts the crane boom angle and traction speed based on this attitude data, maintaining the unit's attitude deviation within ±0.3 degrees to ensure smooth and precise docking with the floating foundation. During the structural docking phase, the control module uses an optimized error compensation algorithm to automatically adjust the docking mechanism's operating parameters based on the initial positioning and lifting data. During the docking process, the bonding speed of the docking surfaces is strictly controlled within a low-speed range of 0.01 to 0.05 meters per second. The bonding gap of the docking surfaces is monitored in real time by an ultrasonic gap sensor with a detection accuracy of 0.001 millimeters, ensuring that the gap value never exceeds the allowable range of 0.1 millimeters.Once the mating surfaces are fully aligned and the gap meets requirements, the hydraulic fastening mechanism is automatically activated, applying a tightening torque of 1000 to 5000 Nm according to optimized preset parameters. The bolt tightening operation is completed in three stages (pre-tightening, intermediate tightening, and final tightening). The torque feedback value is monitored after each stage to ensure uniform and reliable tightening and avoid localized stress concentration. The entire construction process relies on deep collaboration between a digital twin model, a real-time data monitoring platform, and an intelligent control center to achieve full-dimensional dynamic feedback and adaptive parameter adjustment of the construction status. The control module collects and receives data from each sensor every 20 milliseconds. The edge computing unit quickly compares the data with the preset threshold. If any parameter deviation exceeds the standard (such as positioning deviation exceeding 0.01 meters, attitude deviation exceeding ±0.3 degrees, docking gap exceeding 0.1 mm, etc.), the system immediately starts a graded response parameter adjustment program. Level 1 deviation (slight deviation) is automatically corrected, Level 2 deviation (moderate deviation) triggers an early warning and strengthens the adjustment, and Level 3 deviation (severe deviation) immediately suspends construction and initiates the emergency response process. The response time of all adjustment actions does not exceed 50 milliseconds, ensuring that the entire construction process is in a precise and controllable closed-loop management state, and ultimately completing the intelligent construction task of the floating wind power structure efficiently and with high quality.

[0025] Preferably, the expression for the multibody coupled dynamic model of the floating foundation is: , in, The mass matrix of the floating foundation multibody coupling is the same as the spatial coordinates of the floating foundation. Related; These are the acceleration vector, velocity vector, and displacement vector of the floating foundation coupled system, respectively. The damping matrix is ​​associated with the velocity vector and the ocean current velocity. This is the stiffness matrix, which is related to the displacement vector; This is the extreme sea state environment load vector, including time. Waves and flow angle The construction constraint load vector contains the coordinates of the constraint points. and constraint point velocity .

[0026] Specifically, the floating foundation multibody coupled dynamic model is based on the coupling theory of multibody dynamics and fluid mechanics. First, by analyzing the rigid connection characteristics of the floating foundation and its connectors, and considering the mechanism of fluid action on the structure under extreme sea conditions, the floating foundation multibody system is decomposed into multiple rigid body elements. The force transmission and motion constraints between these elements are considered, and three core mechanical parameters—mass, damping, and stiffness—are introduced to construct the dynamic equilibrium equations. Simultaneously, addressing the time-varying characteristics of wind, waves, and currents in extreme sea conditions, environmental loads are treated as vectors varying with time and spatial angles, incorporating the position and velocity feedback of constraint points during construction to form a complete coupled dynamic model. This model is established because the forces and motions of the floating foundation multibody system are strongly coupled, requiring simultaneous consideration of both the structural mechanical properties and the influence of external environmental loads to accurately reflect the dynamic response laws. Regarding parameter values, the mass matrix is ​​calculated based on the floating foundation's geometric dimensions and material density, with a density range of 2500 to 2800. Geometric dimensional accuracy is controlled to 0.01. The damping matrix is ​​calibrated using dynamic experimental data from similar structures and empirical values ​​of fluid damping coefficients, with damping coefficients ranging from 1000 to 10000. The stiffness matrix is ​​obtained by fitting the results of structural finite element analysis, with stiffness coefficients ranging from 100000 to 10000000. The environmental load vector is based on statistical analysis from an extreme sea state parameter database, and the constraint load vector is set according to construction equipment operating parameters and structural installation requirements, with constraint force values ​​ranging from 1000 to 100000. This model quantifies the force transmission path and deformation characteristics of the floating foundation multibody system under extreme sea conditions, providing a mechanical basis for subsequent adjustments to construction parameters. The implementation method involves inputting the sea state parameters and structural parameters collected in step S1 into the model, performing numerical iterative calculations at a fixed time step of 0.01 seconds, with no less than 1000 iterations. The model accuracy is ensured by verifying the convergence of the calculation results, with the convergence error controlled within 0.0001. Finally, the stress data and structural deformation parameters of each connection node are output, providing data support for the optimization of the construction plan.

[0027] Preferably, the expression for the wind turbine attitude disturbance rejection control model is: , in, The estimated rate of change of attitude state over time; This is the wind turbine attitude state estimation vector; The state matrix, To control the input matrix, For attitude control input; The observer gain matrix; The attitude measurement output vector, This is the output matrix; The perturbation input matrix; The attitude disturbance load vector includes wind speed. Blade angular velocity and tower tilt angle .

[0028] Specifically, the wind turbine attitude disturbance rejection control model is based on linear state-space theory and combined with the principle of adaptive disturbance rejection control. It first decomposes the wind turbine's attitude motion into multiple state variables such as yaw angle, pitch angle, and roll angle. By analyzing the linear relationship between attitude changes and control inputs and disturbance loads, state equations and output equations are constructed. A disturbance observer module is introduced to estimate the impact of sea state disturbances on attitude in real time based on attitude measurement data. The disturbance term is incorporated as an additional input into the control model, forming a closed-loop disturbance rejection control structure. This model is established because the wind turbine's attitude is significantly affected by extreme sea state disturbances, and traditional control models struggle to respond quickly to time-varying disturbances. Therefore, the coordinated design of the observer and control law is necessary to achieve a balance between disturbance suppression and attitude adjustment. Regarding parameter values, the state matrix and output matrix are identified based on experimental data of the wind turbine's dynamic characteristics, with matrix element values ​​ranging from -10 to 10. The control input matrix is ​​determined in conjunction with the rated output parameters of the actuators, with element values ​​ranging from 0.1 to 10. The observer gain matrix is ​​designed using the pole placement method, with the real part of the poles ranging from -5 to -1. The disturbance input matrix is ​​set with reference to statistical data on the amplitude of sea state disturbances, with element values ​​ranging from 0.01 to 1. This model effectively counteracts the disturbances to the wind turbine's attitude caused by extreme sea states, maintaining structural attitude stability. The implementation involves collecting attitude data via attitude sensors at a sampling frequency of 20 Hz. After inputting the data into the model, the control output is calculated with a control cycle of 50 milliseconds, driving the nacelle yaw actuator, blade pitch mechanism, and other actuators. During the control process, the actual attitude is compared with the preset reference value in real time, and the model parameters are dynamically adjusted to maintain the attitude deviation within ±0.5 degrees, ensuring the real-time performance and accuracy of attitude control.

[0029] Preferably, the expression for the intelligent construction error compensation prediction algorithm is: , in, for Predict the construction error vector at all times; These are the error weighting coefficients. For history Construction error vector at any given moment; For the algorithm iteration coefficients, For the objective function in parameters gradient at; Let covariance matrix be the variance matrix. This is the parameter correction amount; This is the disturbance compensation coefficient; This is a vector of error influencing factors, including positioning deviation. docking deviation and time delay .

[0030] Specifically, the intelligent construction error compensation prediction algorithm is based on time-series data analysis and adaptive iteration theory. It first analyzes the time-series characteristics of various error data generated during construction, extracting the trend characteristics and periodic patterns of error changes, and constructing a correlation model between historical and future errors. Then, it introduces a gradient descent optimization mechanism, adjusting the algorithm weight coefficients by calculating the gradient of the objective function, and incorporating error influencing factor vectors to quantify the impact of factors such as positioning deviation and docking deviation, forming an algorithm model with both real-time calculation and prediction functions. This model is based on the fact that construction errors are cumulative and correlated, requiring the combination of historical data and real-time feedback to achieve accurate prediction. Traditional error compensation methods lack dynamic adaptability and are difficult to cope with sudden error changes under extreme sea conditions. Regarding parameter values, the error weight coefficient is obtained through training with 500 sets of historical error data, ranging from 0.01 to 0.99. The algorithm iteration coefficient is set from 0.001 to 0.1 according to the error convergence speed requirement. The initial value of the covariance matrix is ​​set as the identity matrix, and it is dynamically updated according to the number of iterations. The disturbance compensation coefficient is determined with reference to the error fluctuation amplitude under extreme sea conditions, ranging from 0.1 to 1. The time delay parameter ranges from 0.01 to 0.1. This algorithm predicts the trend of construction error changes in advance, providing data support for real-time error compensation. The implementation method is to collect real-time error data at a frequency of 10 Hz, input it into the algorithm, complete the error calculation and prediction in a calculation cycle of 20 milliseconds, and output the error prediction value within the next 10 seconds. At the same time, three warning levels are divided. When the error value exceeds 80%, 90%, and 100% of the preset threshold, the corresponding warning is triggered. The algorithm's single calculation time does not exceed 10 milliseconds, and the error prediction hit rate is not less than 95%, ensuring that it provides timely and reliable basis for construction adjustments.

[0031] Preferably, the construction parameter optimization model expression of the extreme sea state construction simulation platform is as follows: , in, To optimize the objective function; These are the weighting coefficients; This is the actual displacement vector. Let the desired displacement vector be denoted as '('). To control the input amount; This is the construction error vector; This refers to the duration of the construction simulation. This is the terminal cost function, which is associated with the terminal displacement, control input, and construction error at the terminal time.

[0032] Specifically, the parameter optimization model of the extreme sea state construction simulation platform is based on multi-objective optimization theory and construction process dynamics analysis. It first clarifies three major optimization objectives: minimizing structural stress, minimizing construction error, and maximizing construction efficiency. The priority of each objective is quantified through weighting coefficients. Floating foundation displacement deviation, control input energy consumption, and construction error are used as optimization variables to construct an integral objective function. A terminal cost function is incorporated to consider parameter stability at the end of construction, forming a complete multi-objective optimization model. This model is established because construction parameters under extreme sea conditions need to consider multiple objectives. Optimization of a single objective is insufficient to guarantee the overall construction effect; therefore, optimal balance of parameter configuration must be achieved through multi-objective collaborative optimization. Regarding parameter values, the three weighting coefficients are set according to construction priority, with values ​​ranging from 0.1 to 0.8, and their sum is 1. The construction simulation duration is determined to be 1800 to 3600 seconds based on the complete construction process. The terminal cost function coefficient ranges from 0.1 to 1. The quantification coefficients for displacement deviation, control input, and construction error are set with reference to industry construction standards and structural safety requirements, ranging from 1 to 100. This model optimizes construction parameters to suit extreme sea conditions through simulation, enhancing the scientific validity and feasibility of the construction plan. The implementation involves importing the preliminary model analysis results and error data into a simulation platform, constructing a virtual construction environment at a 1:1 scale, setting a simulation time step of 0.1 seconds, and obtaining the optimal parameter combination through 1000 to 2000 iterations. During the simulation, key data is recorded at 0.5-second intervals to verify the effectiveness of the optimized parameters, ensuring that the consistency error between the simulation environment and the actual scenario does not exceed 5%, and that the construction error is reduced by more than 30% after applying the optimized parameters.

[0033] Preferably, the dynamic adjustment model expression for the intelligent construction of the adaptive disturbance-resistant floating wind turbine structure is as follows: , in, The control input is adaptively adjusted; This is the initial control input; This is an adaptive gain matrix, relating displacement, velocity, and construction error; For actual environmental loads, To estimate environmental loads; This is the error compensation control quantity, associated with construction errors and error change rates.

[0034] Specifically, the adaptive disturbance-resistant construction dynamic adjustment model is based on feedback control theory and disturbance compensation principle. It first uses the initial control input as a foundation, then constructs an adaptive gain matrix by combining the floating foundation displacement, velocity, and construction errors to quantify the influence of each state parameter on the control output. The difference between the actual and estimated environmental loads is introduced as a disturbance compensation term, and error and error change rate are incorporated to construct the error compensation control quantity, forming a three-layer control structure of "initial control + disturbance compensation + error correction." This model is established because environmental loads and construction conditions under extreme sea conditions are highly time-varying, and fixed control parameters are difficult to adapt to dynamic changes. Adaptive adjustment is needed to achieve real-time matching between the control input and the actual working conditions. Regarding parameter values, the initial control input is set according to the initial construction plan and equipment rated parameters, with a value range of 10 to 1000. The adaptive gain matrix elements are determined based on state parameter sensitivity analysis, with a value range of 0.01 to 10. The proportional coefficient and differential coefficient of the error compensation control quantity range from 0.1 to 10 and 0.01 to 1, respectively. The quantization coefficient of the environmental load estimation error ranges from 1 to 10. This model enables dynamic adaptive adjustment of construction control parameters, enhancing resilience to extreme sea conditions. The implementation involves collecting structural displacement, velocity, construction error, and environmental load data at 20-millisecond intervals. This data is then input into the model to calculate the adaptively adjusted control input, driving the actuators of the construction equipment. The control module receives feedback data every 50 milliseconds, dynamically updating the model parameters to ensure that the control input adjustment response time does not exceed 30 milliseconds. This keeps the structural attitude deviation and construction error under extreme sea conditions within acceptable limits, guaranteeing the stability and accuracy of the construction process.

[0035] Preferably, step S3 includes the following sub-steps: S31, collecting data on the center of gravity position of the wind turbine nacelle, the blade tip trajectory, and the bottom rotation angle of the tower using distributed attitude sensors, converting the collected data into an attitude parameter sequence in a unified coordinate system, and synchronously transmitting it to the control module; S32, based on the wind turbine attitude disturbance resistance control model, calculating the initial attitude control quantity according to the deviation between the attitude parameter sequence and the preset attitude reference value, and simultaneously introducing sea state disturbance observation values ​​to preliminarily correct the control quantity; S33, driving the nacelle yaw actuator, blade pitch mechanism, and tower vibration damping device through the control module to perform coordinated actions according to the corrected control quantity, adjusting the spatial attitude of each component of the wind turbine in real time, and maintaining structural attitude stability.

[0036] Specifically, during the implementation of S31, distributed attitude sensors are installed on the top of the nacelle, at the blade roots, and in the middle of the tower, with the sensor spacing controlled between 5 and 8 meters. Data is continuously collected at a sampling frequency of 20 Hz, including the three-dimensional spatial coordinates of the nacelle's center of gravity, the real-time position of the blade tip trajectory, and the angle change at the bottom of the tower. After the data is collected, the output data from different sensors is uniformly converted to the geodetic coordinate system through a data conversion module to form a standardized sequence of attitude parameters. Data transmission is carried out via wired transmission, with the transmission delay controlled within 30 milliseconds to ensure that the data is synchronized to the central control module in real time. During the implementation of S32, the control module calls the wind turbine attitude disturbance rejection control model. First, it compares the attitude parameter sequence obtained in S31 with the preset attitude reference value point by point and calculates the deviation between the two. The deviation calculation accuracy reaches 0.01 degrees. Then, based on the magnitude of the deviation, it initially generates the initial control quantities for nacelle yaw, blade pitch, and tower vibration reduction. At the same time, it collects real-time sea state disturbance data through environmental sensors and incorporates the disturbance observation value as a correction factor into the initial control quantity to complete the first dynamic correction of the control quantity. During the implementation of S33, the control module sends corrected control values ​​to the nacelle yaw actuator, blade pitch mechanism, and tower damping device at a 50-millisecond command cycle. The three actuators respond in concert: the yaw actuator adjusts the nacelle direction at an angular velocity of 0.1 to 1 degree per second, the pitch mechanism adjusts the blade angle at a velocity of 0.5 to 5 degrees per second, and the damping device adjusts the damping force according to the dynamic damping coefficient. The attitude changes of each component are monitored in real time throughout the process, and the control parameters are continuously fine-tuned through closed-loop feedback to keep the attitude deviation of the nacelle, blades, and tower within ±0.5 degrees. This step, through precise step-by-step operation, enables rapid cancellation of extreme sea state disturbances, ensures the attitude stability of the wind turbine, and lays the foundation for subsequent construction phases.

[0037] Preferably, step S4 includes the following sub-steps: S41, collecting real-time data on the floating foundation positioning coordinates, structural docking surface gaps, and attitude adjustment amounts during construction, establishing an error data acquisition channel to ensure the continuity and synchronization of data transmission; S42, inputting the collected error data into an intelligent construction error compensation prediction algorithm, identifying the root causes of errors through the algorithm, and constructing an error development trend model by combining historical error data; S43, predicting the error change range in subsequent construction stages based on the error development trend model, generating corresponding error compensation amounts, and transmitting the compensation amounts to the construction execution system to provide data support for adjusting construction parameters.

[0038] Specifically, during the implementation of S41, laser positioning devices, displacement sensors, and angle sensors are installed on the floating foundation positioning device, structural docking mechanism, and attitude adjustment equipment. The sensor measurement accuracy reaches 0.001 meters, 0.01 millimeters, and 0.01 degrees, respectively. Data is collected at a frequency of 10 Hz, specifically including the positioning coordinate deviation of the floating foundation in the x, y, and z directions, the gap size of the structural docking surface, and the angular deviation of the attitude adjustment of each component. Data is transmitted through a dedicated data acquisition channel with a bandwidth of 100 Mbps to ensure the continuity and synchronization of data transmission without packet loss. During the implementation of S42, the real-time error data collected in S41 is input into the intelligent construction error compensation prediction algorithm. First, random noise interference is eliminated through smoothing filtering, with the filtering window size set to 50 data points. Then, the processed data is subjected to root cause identification to analyze the causes of positioning deviation, docking deviation, and attitude deviation. At the same time, 500 sets of similar construction error data stored in the historical database are called up to construct an error development trend model. The model is trained and iterated no less than 800 times to ensure that the model fit is above 0.95. When S43 is implemented, the error change range within the next 10 seconds is predicted based on a trend model with a prediction step size of 0.1 seconds. The corresponding error compensation amount is generated with a calculation accuracy of 0.0001 meters. The compensation amount is then transmitted to the construction execution system via a data bus with a transmission delay of no more than 20 milliseconds, providing accurate data support for the parameter adjustment of construction equipment. This step, through step-by-step progression, enables real-time monitoring, accurate analysis, and advance prediction of errors, effectively avoiding error accumulation and improving construction accuracy and reliability.

[0039] Preferably, step S5 includes the following sub-steps: S51, importing the dynamic response results of the floating foundation multi-body coupled dynamic model, the control effect data of the wind turbine attitude disturbance prevention control model, and the error data of the intelligent construction error compensation prediction algorithm into the extreme sea state construction simulation platform; S52, building a virtual simulation environment consistent with the actual construction scenario in the platform, and setting dynamic change boundary conditions for sea state parameters, structural parameters, and construction equipment parameters; S53, running the simulation platform to simulate the construction process, recording the structural stress, attitude changes, and construction error calibration data during the simulation, and analyzing the feasibility and rationality of the construction plan; S54, adjusting and optimizing the equipment operation parameters, control parameters, and error compensation strategies in the construction plan based on the simulation results, and generating an adaptive disturbance prevention construction plan adapted to extreme sea states.

[0040] Specifically, during the implementation of S51, the dynamic response data output from the floating foundation multi-body coupled dynamic model, the control effect data output from the wind turbine attitude disturbance rejection control model, and the error data output from the intelligent construction error compensation prediction algorithm were all imported into the extreme sea state construction simulation platform via data interfaces. The data import format adopted a standardized data exchange format, with an import rate of no less than 10MB per second, ensuring that all key data were imported completely without any missing or distorted data. During the implementation of S52, a virtual construction scene was built on the simulation platform at a 1:1 scale, recreating the three-dimensional models of the floating foundation, wind turbine, and construction equipment. The model detail accuracy reached 0.01 meters. Dynamically changing boundary conditions were set, including the time-varying laws of wind loads, wave loads, and current loads, the undulating characteristics of the seabed topography, and the dynamic adjustment range of structural parameters. The boundary condition update frequency was consistent with the actual sea state change frequency, ensuring the realism of the simulation. During S53 implementation, the simulation platform is launched to simulate the construction process. The simulation time step is set to 0.1 seconds, and the simulation duration covers the entire construction process for no less than 1800 seconds. During the simulation, key data such as structural stress, attitude changes, and construction errors are recorded at 0.5-second intervals, generating no less than 3600 sets of simulation data. Simultaneously, data anomalies are monitored in real time, with the anomaly detection threshold set at ±15% of the normal range. During S54 implementation, the simulation data recorded in S53 is analyzed to evaluate the feasibility and rationality of the construction plan. If problems such as excessive structural stress, excessive construction errors, or low construction efficiency exist, the operating parameters of the construction equipment, attitude control parameters, and error compensation strategies are adjusted and optimized. The optimization iterations are no less than 1000 times, ultimately generating an adaptive anti-disturbance construction plan suitable for extreme sea conditions. This step, through step-by-step simulation and optimization, anticipates construction risks in advance, improves the scientific nature and adaptability of the construction plan, and ensures the smooth progress of actual construction.

[0041] like Figure 2As shown, the adaptive disturbance-resistant floating wind turbine foundation structure and intelligent construction method are illustrated. This structure is implemented through different units, including: a multi-dimensional acquisition and processing unit for extreme sea state parameters, a multi-body coupled dynamic analysis unit for the floating foundation, a wind turbine attitude disturbance resistance collaborative control unit, an intelligent construction error prediction and compensation unit, an extreme sea state construction simulation and scheme optimization unit, and an adaptive disturbance-resistant construction execution and dynamic feedback unit. The multi-dimensional acquisition and processing unit for extreme sea state parameters communicates bidirectionally with the multi-body coupled dynamic analysis unit for the floating foundation, transmitting the processed sea state parameters and structural parameters to the analysis unit. After completing the dynamic response analysis using the multi-body coupled dynamic model of the floating foundation, the analysis unit synchronizes the results to the wind turbine attitude disturbance resistance collaborative control unit and the intelligent construction error prediction and compensation unit. The prediction and compensation unit and the wind turbine attitude disturbance rejection collaborative control unit output attitude control signals based on the wind turbine attitude disturbance rejection control model. The intelligent construction error prediction and compensation unit generates error compensation data through the intelligent construction error compensation prediction algorithm. The output signals of both are transmitted to the extreme sea state construction simulation and scheme optimization unit. The extreme sea state construction simulation and scheme optimization unit uses the extreme sea state construction simulation platform to optimize the construction scheme and sends the optimized construction instructions to the adaptive disturbance rejection construction execution and dynamic feedback unit. The adaptive disturbance rejection construction execution and dynamic feedback unit executes the construction operation and feeds back the real-time construction status data to each preceding unit to form a closed-loop control and carry out intelligent construction of the adaptive disturbance rejection floating wind power structure.

[0042] The adaptive, disturbance-resistant floating wind turbine foundation structure and intelligent construction method address the lack of coordinated consideration of multi-body coupling and attitude disturbance resistance. Based on a multi-body coupled dynamic model of the floating foundation, it deeply analyzes the structural force transmission law and deformation characteristics. Simultaneously, it incorporates a wind turbine attitude disturbance resistance control model to real-time adjust the spatial attitude of the nacelle, blades, and tower, constructing a multi-dimensional collaborative control mechanism. This mechanism can quickly respond to coupled disturbances from wind, waves, and currents under extreme sea conditions, completely resolving the problems of attitude adjustment lag and construction deviation accumulation. Addressing the deficiencies in error compensation and dynamic adaptation of scheme optimization, it utilizes an intelligent construction error compensation prediction algorithm to calculate and predict trends of construction errors such as positioning deviation and docking deviation in real time. Combined with an extreme sea condition construction simulation platform, it conducts full-process construction pre-runs and parameter optimization, forming a closed-loop control mode of "data acquisition - analysis and prediction - scheme optimization - dynamic feedback," significantly improving the adaptability of the construction scheme to extreme sea conditions.

[0043] This method boasts multiple significant advantages, comprehensively ensuring the quality and efficiency of deep-sea construction: Firstly, it features a high degree of technical system integration, organically combining multi-body coupled dynamic analysis, attitude disturbance control, error prediction compensation, and simulation optimization platforms to form an intelligent control system covering the entire construction process. This eliminates the need for additional auxiliary technical modules to achieve multi-objective management. Secondly, it offers precise and efficient control response. Through the collaborative linkage of various models and platforms, it achieves real-time linkage of sea state disturbance identification, structural attitude adjustment, and construction error compensation, significantly reducing the interference of extreme sea conditions on the construction process. Thirdly, it has a wide range of applicability. Relying on dynamic parameter adjustment mechanisms and simulation optimization functions, it can adapt to different terrain conditions and extreme sea state characteristics in deep-sea areas without requiring significant technical modifications for specific scenarios. Fourthly, it offers strong construction controllability. Through the closed-loop collaboration of six functional units and the refined execution of each step, it achieves full traceability and controllability of the construction process, effectively improving structural assembly accuracy and construction safety, and providing stable and reliable technical support for the large-scale development of deep-sea wind power resources.

[0044] In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, the terms "set," "install," "connect," "link," and "fix" 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 communication between two components. Those skilled in the art will understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0045] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. An adaptive, disturbance-resistant floating wind turbine foundation structure and intelligent construction method, characterized in that, Includes the following steps: S1. Based on the extreme sea state construction simulation platform, wind load, wave load, current load, and seabed topography distribution data are collected to construct a sea state parameter database including spatiotemporal coupling characteristics. Simultaneously, the geometric dimensions of the floating foundation, the mass distribution of wind turbine components, and the operating parameters of the construction equipment are acquired. S2. Through a multi-body coupled dynamic model of the floating foundation, dynamic response analysis is performed on the collected sea state and structural parameters to determine the force transmission path and deformation characteristics of the floating foundation and connecting components. S3. A wind turbine attitude disturbance rejection control model is used to real-time regulate the spatial attitude of the wind turbine nacelle, blades, and tower, dynamically adjusting control parameters to counteract sea state disturbances. The impact of disturbances on structural attitude; S4, using an intelligent construction error compensation prediction algorithm to calculate and predict in real time the foundation positioning deviation, structural docking deviation, and attitude adjustment deviation generated during construction; S5, based on model analysis results and error prediction data, using an extreme sea state construction simulation platform to perform construction process pre-playing and parameter optimization, generating an adaptive anti-disturbance construction scheme; S6, according to the optimized construction scheme, integrating construction equipment actuators and control modules to complete intelligent construction operations for floating foundation installation, wind turbine hoisting, and structural docking, using various models and platforms throughout the process for dynamic feedback and parameter adjustment of construction status; The expression for the multibody coupled dynamic model of the floating foundation is: ， in, The mass matrix of the floating foundation multibody coupling is the same as the spatial coordinates of the floating foundation. Related; These are the acceleration vector, velocity vector, and displacement vector of the floating foundation coupled system, respectively. The damping matrix is ​​associated with the velocity vector and the ocean current velocity. This is the stiffness matrix, which is related to the displacement vector; This is the extreme sea state environment load vector, including time. Waves and flow angle The construction constraint load vector contains the coordinates of the constraint points. and constraint point velocity ; The expression for the wind turbine attitude disturbance rejection control model is: ， in, The estimated rate of change of attitude state over time; This is the wind turbine attitude state estimation vector; The state matrix, To control the input matrix, For attitude control input; The observer gain matrix; The attitude measurement output vector, This is the output matrix; The perturbation input matrix; The attitude disturbance load vector includes wind speed. Blade angular velocity and tower tilt angle .

2. The adaptive disturbance-resistant floating wind power foundation structure and intelligent construction method according to claim 1, characterized in that, The expression for the intelligent construction error compensation prediction algorithm is as follows: ， in, for Predict the construction error vector at all times; These are the error weighting coefficients. For history Construction error vector at any given moment; For the algorithm iteration coefficients, For the objective function in parameters gradient at; Let covariance matrix be the variance matrix. This is the parameter correction amount; This is the disturbance compensation coefficient; This is a vector of error influencing factors, including positioning deviation. docking deviation and time delay .

3. The adaptive disturbance-resistant floating wind power foundation structure and intelligent construction method according to claim 1, characterized in that, The construction parameter optimization model expression of the extreme sea state construction simulation platform is as follows: ， in, To optimize the objective function; These are the weighting coefficients; This is the actual displacement vector. Let the desired displacement vector be denoted as '('). To control the input amount; This is the construction error vector; This refers to the duration of the construction simulation. This is the terminal cost function, which is associated with the terminal displacement, control input, and construction error at the terminal time.

4. The adaptive disturbance-resistant floating wind power foundation structure and intelligent construction method according to claim 1, characterized in that, The dynamic adjustment model expression for the intelligent construction of the adaptive disturbance-resistant floating wind turbine structure is as follows: ， in, The control input is adaptively adjusted; This is the initial control input; This is an adaptive gain matrix, relating displacement, velocity, and construction error; For actual environmental loads, To estimate environmental loads; This is the error compensation control quantity, associated with construction errors and error change rates.

5. The adaptive anti-disturbance floating wind power foundation structure and intelligent construction method according to claim 1, characterized in that, S3 includes the following steps: S31, collecting data on the center of gravity position of the wind turbine nacelle, the blade tip trajectory, and the bottom rotation angle of the tower through distributed attitude sensors, converting the collected data into an attitude parameter sequence in a unified coordinate system, and synchronously transmitting it to the control module; S32, based on the wind turbine attitude disturbance resistance control model, calculating the initial attitude control quantity according to the deviation between the attitude parameter sequence and the preset attitude reference value, and simultaneously introducing sea state disturbance observation values ​​to preliminarily correct the control quantity; S33, driving the nacelle yaw actuator, blade pitch mechanism, and tower vibration damping device through the control module to perform coordinated actions according to the corrected control quantity, adjusting the spatial attitude of each component of the wind turbine in real time, and maintaining structural attitude stability.

6. The adaptive disturbance-resistant floating wind power foundation structure and intelligent construction method according to claim 1, characterized in that, S4 includes the following sub-steps: S41, collecting real-time data on the floating foundation positioning coordinates, structural docking surface gaps, and attitude adjustment amounts during construction, establishing an error data acquisition channel to ensure the continuity and synchronization of data transmission; S42, inputting the collected error data into an intelligent construction error compensation prediction algorithm, identifying the root causes of errors through the algorithm, and constructing an error development trend model by combining historical error data; S43, predicting the error change range in subsequent construction stages based on the error development trend model, generating corresponding error compensation amounts, and transmitting the compensation amounts to the construction execution system to provide data support for adjusting construction parameters.

7. The adaptive disturbance-resistant floating wind power foundation structure and intelligent construction method according to claim 1, characterized in that, S5 includes the following sub-steps: S51, importing the dynamic response results of the floating foundation multi-body coupled dynamic model, the control effect data of the wind turbine attitude disturbance prevention control model, and the error data of the intelligent construction error compensation prediction algorithm into the extreme sea state construction simulation platform; S52, building a virtual simulation environment consistent with the actual construction scenario in the platform, and setting dynamic change boundary conditions for sea state parameters, structural parameters, and construction equipment parameters; S53, running the simulation platform to simulate the construction process, recording the structural stress, attitude changes, and construction error calibration data during the simulation, and analyzing the feasibility and rationality of the construction plan; S54, adjusting and optimizing the equipment operation parameters, control parameters, and error compensation strategies in the construction plan based on the simulation results, and generating an adaptive disturbance prevention construction plan adapted to extreme sea states.

8. The adaptive disturbance-resistant floating wind turbine foundation structure and intelligent construction method according to any one of claims 1-7, characterized in that, This structural design is implemented through different units, including: a multi-dimensional acquisition and processing unit for extreme sea state parameters, a multi-body coupled dynamics analysis unit for the floating foundation, a wind turbine attitude disturbance rejection collaborative control unit, an intelligent construction error prediction and compensation unit, an extreme sea state construction simulation and scheme optimization unit, and an adaptive disturbance rejection construction execution and dynamic feedback unit. The multi-dimensional acquisition and processing unit for extreme sea state parameters communicates bidirectionally with the multi-body coupled dynamics analysis unit for the floating foundation, transmitting processed sea state and structural parameters to this unit. This unit then performs dynamic response analysis using the multi-body coupled dynamics model of the floating foundation and synchronizes the results to the wind turbine attitude disturbance rejection collaborative control unit and the intelligent construction error prediction and compensation unit. The wind turbine attitude disturbance rejection collaborative control unit outputs attitude control signals based on the wind turbine attitude disturbance rejection control model. The intelligent construction error prediction and compensation unit generates error compensation data through the intelligent construction error compensation prediction algorithm. The output signals of both are transmitted to the extreme sea state construction simulation and scheme optimization unit. The extreme sea state construction simulation and scheme optimization unit uses the extreme sea state construction simulation platform to optimize the construction scheme and sends the optimized construction instructions to the adaptive disturbance rejection construction execution and dynamic feedback unit. The adaptive disturbance rejection construction execution and dynamic feedback unit executes the construction operation and feeds back the real-time construction status data to each preceding unit to form a closed-loop control and carry out intelligent construction of the adaptive disturbance rejection floating wind power structure.

Images