An intelligent vibration control system and control method for offshore wind turbines

Abstract

An offshore wind turbine intelligent vibration control system and control method belong to the technical field of wind turbine vibration control, the control system comprises: multi-field coupling modeling module, control module, adaptive control algorithm module, digital twin integrated platform module. The present application constructs a multi-field coupling modeling module, deploys an adaptive tuned mass damper (ATMD) and a fuzzy PID-LQR hybrid controller, combines a physical information neural network (PINN) for response prediction and parameter optimization, and realizes structure state visualization, remote control and strategy optimization through a digital twin platform. The present application realizes the perception, modeling, control and feedback loop of offshore wind power structure vibration, has the advantages of high modeling accuracy, fast control response and strong adaptive ability, and is suitable for the anti-vibration operation requirements of offshore wind turbines and complex structures.

Description

Technical Field

[0001] This invention belongs to the field of vibration reduction and control technology for wind turbines, specifically relating to an intelligent vibration control system and control method for offshore wind turbines. Background Technology

[0002] With the rapid development of deep-sea wind power, offshore wind turbines (hereinafter referred to as wind turbines) face a more complex coupled environment of wind, waves, and earthquakes, resulting in increasingly serious vibration problems that severely affect their service life and operational stability. Gradient changes in wind speed along the height direction, irregular wave impacts, and intense, complex vibrations triggered by earthquakes often lead to multimodal, high-frequency, and nonlinear dynamic responses in the structure. Long-period excitation can also induce resonance, further amplifying the stress on the tower and foundation, leading to structural fatigue and potential damage.

[0003] Existing wind turbine control technologies largely rely on fixed parameters or single-mode controllers, which struggle to cope with the uncertainties and rapid changes in loads under dynamic marine environments, especially posing a risk of control failure under extreme conditions (such as typhoons, strong waves, and large earthquakes). Meanwhile, traditional structural response prediction methods are computationally expensive and have poor adaptability, and efficient modeling tools for rapid regulation and control feedback have not yet been developed.

[0004] Furthermore, the large-scale deployment of wind farms places higher demands on intelligent operation and maintenance. However, current control systems generally lack remote diagnostics, strategy self-adjustment, and real-time structural status mapping capabilities, making it difficult to meet the "proactive perception - intelligent response - remote optimization" operation and maintenance trend of smart wind farms.

[0005] Therefore, there is an urgent need to develop a vibration control system for offshore wind turbines that integrates multiphysics modeling, adaptive control, and intelligent integration platforms to achieve perception, prediction, and active regulation of structural response under complex load conditions, thereby improving the operational resilience and service life of offshore wind power equipment. Summary of the Invention

[0006] This invention discloses an intelligent vibration control system and method for offshore wind turbines. The system and method integrate multi-source excitation modeling, adaptive control algorithm and digital twin system, and have functions such as rapid prediction of structural response, self-adjustment of control device, remote monitoring and optimization, which significantly improves the vibration control capability and operational resilience of offshore wind turbines in complex environments.

[0007] To achieve the above objectives, the technical solution of the present invention is as follows:

[0008] A smart vibration control system for offshore wind turbines includes: a multi-field coupling modeling module, a control module, an adaptive control algorithm module, and a digital twin integrated platform module;

[0009] The aforementioned multi-field coupling modeling module is used to construct a multi-field coupled dynamic model of an offshore wind turbine under the coupled effects of wind, waves, and earthquakes, in order to assess the impact of environmental load changes on structural vibration and provide input for the control module.

[0010] The control module is used to achieve multi-objective coordinated control of vibration reduction of offshore wind turbines under extreme typhoon, resonance, and large earthquake conditions.

[0011] The adaptive control algorithm module adaptively updates the control parameters based on real-time monitoring feedback data to ensure the stability and responsiveness of the system under different sea conditions.

[0012] The aforementioned digital twin integration platform module establishes a data interaction channel between the physical wind turbine and the digital twin model through real-time data mapping and dynamic simulation.

[0013] Preferably, the multi-field coupling modeling module uses the Kaimal wind speed spectrum to describe wind shear characteristics, the Pierson-Moskowitz wave spectrum to represent random wave energy distribution, and the improved Kanai-Tajimi ground motion spectrum to represent seismic characteristics. It comprehensively considers the spatiotemporal evolution characteristics and correlations of wind-wave-earthquake excitation, analyzes the probability distribution characteristics of environmental loads through the Copula function, and outputs multimodal dynamic response simulation data of the wind turbine structure based on stochastic differential equations.

[0014] Preferably, the control module includes: an adaptive tuned mass damper integrated at the top of the wind turbine tower or a key stress-bearing part; the adaptive tuned mass damper is equipped with a vibration energy acquisition module and has self-powering capability; a fuzzy PID-LQR hybrid controller is designed based on Lyapunov stability theory to optimize the control of the adaptive tuned mass damper; and a multi-objective genetic algorithm is used to optimize the control parameters to achieve multi-objective coordinated control under extreme typhoon, resonance, and large earthquake conditions.

[0015] Preferably, the adaptive control algorithm module includes: introducing a physical information deep neural network, integrating traditional control theory with deep learning methods, and realizing real-time prediction and analysis of complex excitations and structural dynamic responses to wind-wave-earthquake under the constraints of physical laws.

[0016] Preferably, the digital twin integration platform module is used to construct a real-time virtual mapping system for structure-controller-environment interaction, integrate sensor networks and edge computing methods deployed on the wind turbine, and establish a data interaction channel between the physical wind turbine and the digital twin model through real-time data mapping and dynamic simulation, so as to realize real-time monitoring of structural response, simulation optimization of control strategy, remote diagnosis and active control decision-making.

[0017] A control method for an intelligent vibration control system for offshore wind turbines includes the following steps: (1) collecting environmental excitation and structural response data based on a sensor network; (2) simulating the structural response through a multi-field coupling modeling module; (3) predicting the structural state and optimizing control parameters using an adaptive control algorithm module; (4) actively controlling the system through control commands; and (5) completing remote optimization and control feedback closed loop through a digital twin integrated platform module.

[0018] The beneficial effects of the intelligent vibration control system and control method for offshore wind turbines of the present invention are as follows:

[0019] 1. Multiphysics joint modeling: accurately describes the dynamic characteristics of complex marine environmental loads and structural responses, improving the accuracy of vibration prediction.

[0020] 2. Adaptive Active Control: Employing a self-powered active control device and advanced control algorithms significantly improves the adaptability and responsiveness of the control strategy.

[0021] 3. Intelligent operation and maintenance management: The combination of digital twin technology and edge computing enables real-time status monitoring, remote diagnosis, and dynamic optimization of control strategies.

[0022] 4. Strong generalization ability: It is applicable to different working conditions and different types of offshore wind turbine structures, and has broad prospects for engineering promotion. Attached Figure Description

[0023] Figure 1 This invention includes a flowchart illustrating its input-output working principle.

[0024] Figure 2 : Flowchart of wind-wave-earthquake joint modeling, including load spectrum selection, computational fluid dynamics (CFD) modeling, and joint distributed simulation structure.

[0025] Figure 3 The control strategy structure diagram shows the coupling structure of ATMD and LQR fuzzy control, as well as the simulation control effect results.

[0026] Figure 4 : PINN assisted adaptive control framework diagram, showing data flow and parameter adjustment logic.

[0027] Figure 5 : Digital twin and control platform integrated structure diagram, illustrating the simulation model—sensor data—remote control closed loop. Detailed Implementation

[0028] The following description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

[0029] The following embodiments can be understood as illustrating a part of the structure or method of the present invention individually, or as combining the embodiments to explain the broader structure or method of the present invention.

[0030] Example 1

[0031] A smart vibration control system for offshore wind turbines, such as Figure 1-5 As shown, it includes: a multi-field coupling modeling module, a control module, an adaptive control algorithm module, and a digital twin integration platform module;

[0032] The aforementioned multi-field coupling modeling module is used to construct a multi-field coupled dynamic model of offshore wind turbines under the coupled action of wind, waves, and earthquakes, breaking through the limitations of traditional single load assumptions, in order to evaluate the impact of environmental load changes on structural vibration and provide input for the control module;

[0033] The control module is used to achieve multi-objective coordinated control of vibration reduction of offshore wind turbines under extreme typhoon, resonance, and large earthquake conditions.

[0034] The adaptive control algorithm module adaptively updates the control parameters based on real-time monitoring feedback data to ensure the stability and responsiveness of the system under different sea conditions.

[0035] The aforementioned digital twin integration platform module establishes a data interaction channel between the physical wind turbine and the digital twin model through real-time data mapping and dynamic simulation.

[0036] Example 2

[0037] Based on Example 1, this example discloses: Figure 2 As shown, the multi-field coupling modeling module uses the Kaimal wind speed spectrum to describe wind shear characteristics, the Pierson-Moskowitz wave spectrum to represent random wave energy distribution, and the improved Kanai-Tajimi ground motion spectrum to represent earthquake characteristics. It comprehensively considers the spatiotemporal evolution characteristics and correlations of wind-wave-earthquake excitation, analyzes the probability distribution characteristics of environmental loads through the Copula function, and outputs multimodal dynamic response simulation data of the wind turbine structure based on stochastic differential equations.

[0038] Example 3

[0039] Based on Example 1, this example discloses: Figure 3As shown, the control module includes: an adaptive tuned mass damper (ATMD) integrated at the top of the wind turbine tower or a key stress-bearing part (the area of ​​maximum shear force and bending moment variation in the tower) to facilitate active or semi-active control strategies for offshore wind turbines. The ATMD is equipped with a vibration energy acquisition module and has self-powering capabilities, converting structural vibration energy into control energy using a self-powering principle, thus enhancing the system's independence and sustainability. Based on Lyapunov stability theory, a fuzzy PID-LQR hybrid controller is designed, and a multi-objective genetic algorithm (NSGA-II) is used to optimize the control parameters for optimized control of the ATMD, achieving multi-objective coordinated control under extreme typhoon, resonance, and large earthquake conditions. The main power source for the ATMD control system of this invention is the electrical energy generated by the offshore wind turbine itself, ensuring the stable operation of the controller and actuators. Based on this, the ATMD device integrates an energy harvesting module to collect mechanical energy from structural vibrations (such as through piezoelectric elements), which is then processed by the energy management circuit to provide backup power to the controller when the main power supply fails, thereby maintaining basic monitoring and emergency vibration reduction functions under low power consumption conditions.

[0040] Example 4

[0041] Based on Example 1, this example discloses: Figure 4 As shown, the adaptive control algorithm module includes: to enhance the adaptive capability of the control system to uncertain marine environments, a Physics-Informed Neural Network (PINN) is introduced, integrating traditional control theory with deep learning methods to achieve real-time prediction and analysis of complex excitations and structural dynamic responses under the constraints of physical laws. The adaptive control algorithm module constructs a PINN model with wind speed, waves, earthquakes, structural acceleration, and sensor data as inputs, and outputs predicted future structural responses and optimal controller parameters. This model is trained and updated online, enhancing the controller's adaptability to vibration responses in complex marine environments.

[0042] Example 5

[0043] Based on Example 1, this example discloses: Figure 5As shown, the digital twin integration platform module is used to construct a real-time virtual mapping system for structure-controller-environment interaction. It integrates a sensor network and edge computing methods deployed on the wind turbine. Through real-time data mapping and dynamic simulation, it establishes a data interaction channel between the physical wind turbine and the digital twin model, enabling real-time monitoring of structural response, simulation optimization of control strategies, remote diagnosis, and proactive control decision-making. The sensor network consists of three layers of sensors deployed on the wind turbine's tower top, tower body, and foundation, including accelerometers, strain gauges, displacement gauges, and environmental wind, wave, and seismic sensors. It also integrates a LoRa wireless network and edge computing nodes. The edge nodes perform real-time fusion and preprocessing of vibration and environmental data. The integration and functional deployment of the digital twin integration platform module comprises a virtual wind turbine modeling module, a structural state mapping module, and a control strategy simulation module. It receives sensor network data in real time, drives the virtual model, simulates structural responses under different control strategies, and assists in remote decision optimization.

[0044] Example 6

[0045] Based on Examples 1-5, this example discloses:

[0046] A control method for an intelligent vibration control system for offshore wind turbines, such as Figure 1-5 As shown, the process includes the following steps: (1) collecting environmental excitation and structural response data based on a sensor network; (2) simulating the structural response through a multi-field coupling modeling module; (3) predicting the structural state and optimizing control parameters using an adaptive control algorithm module; (4) actively controlling the system through control commands; and (5) completing the remote optimization and control feedback loop through a digital twin integration platform module.

[0047] The simulation verification and working condition assessment of this invention are based on a multi-field coupled modeling module. 10,000 sets of structural vibration simulations under different wind, wave and earthquake combinations are carried out to evaluate the vibration suppression effect, energy consumption and stability of the control module under different working conditions (normal operation, strong wind, long-period ground motion) and verify the robustness of the system.

[0048] The closed-loop operation process and application demonstration of this invention are implemented by deploying a complete system in a prototype wind turbine tower, achieving closed-loop operation of data acquisition, predictive analysis, control optimization, and execution feedback. The system collects real-time data through sensors, dynamically adjusts the control strategy after edge processing and PINN analysis, and implements vibration reduction control by the control module. A digital twin platform displays the wind turbine status in real time and records historical control data, providing support for system maintenance and parameter tuning.

[0049] Working principle of the invention:

[0050] This invention is based on the five-in-one intelligent control closed-loop principle of "sensing-modeling-prediction-control-feedback," and achieves real-time monitoring, prediction, and active control of the structural vibration of offshore wind turbines in complex marine environments through multi-module collaboration. The system workflow is as follows:

[0051] First, a sensor network is deployed at key parts of the wind turbine structure (the area where the tower experiences the greatest changes in shear force and bending moment) to collect structural response (such as acceleration, displacement, and strain) and environmental excitation information (such as wind speed, waves, and earthquakes) in real time. The data is then transmitted to the digital twin integration platform module via wireless communication.

[0052] In the modeling phase, a wind-wave-earthquake excitation model was jointly constructed using the Kaimal wind speed spectrum, PM wave spectrum, and improved Kanai-Tajimi ground motion spectrum simulations. Combined with structural finite element analysis, this generated nonlinear coupled dynamic response simulation data. Simultaneously, an intelligent prediction model combining PINN and DNN was employed to achieve online prediction of structural response trends and assist in determining the optimization direction of control strategies.

[0053] The control decision module constructs a fuzzy PID-LQR hybrid controller based on Lyapunov stability theory, dynamically adjusting control parameters according to simulation feedback and real-time prediction results. The control device is a self-powered ATMD, which effectively reduces the dynamic response of the tower structure through control force output.

[0054] Ultimately, all monitoring data and control behaviors form a virtual mapping of structure, control, and environment in the digital twin integration platform module. The platform is used for control strategy simulation verification, remote status visualization, and intelligent diagnosis, realizing vibration suppression and operation optimization throughout the entire life cycle of the wind turbine.

[0055] Application prospects of this invention:

[0056] This invention addresses the reliability requirements of offshore wind turbines, possesses advanced technology and broad engineering application potential, and its application prospects are mainly reflected in the following aspects:

[0057] 1. Applicable to vibration-resistant design of deep-sea wind farm structures: As wind farms expand into deeper waters, the vibration problem of wind turbine structures becomes increasingly prominent. This invention can provide customized intelligent control solutions for high-tower, large-capacity wind turbines, significantly improving structural safety and lifespan.

[0058] 2. Can be integrated into the construction of smart wind farms: This invention is highly compatible with digital twin platforms and edge computing architectures, supports intelligent monitoring, remote control and adaptive optimization of wind farms, and is a key technological foundation for realizing a smart wind power operation and maintenance system.

[0059] 3. It can be extended to other marine or tall structure scenarios: such as offshore platforms, port pile foundation structures, marine photovoltaic foundations, long-span bridge towers and other complex engineering structures with multi-source excitation characteristics. The intelligent vibration control framework proposed in this invention can also be applied after appropriate modification.

[0060] This invention has significant economic and environmental benefits: by reducing structural fatigue damage, reducing the frequency of operation and maintenance, and extending the life of wind turbines, this invention helps to reduce the cost of wind power and improve the efficiency of clean energy utilization, and has good green and low-carbon demonstration value.

[0061] In summary, this invention has comprehensive advantages such as advanced structural mechanism, intelligent control algorithm, flexible platform integration, and strong engineering adaptability, and has broad application prospects and promotion value in the next generation of high-performance, highly intelligent, and sustainable offshore wind power systems.

Claims

1. An intelligent vibration control system for offshore wind turbines, characterized by: include: Multi-field coupling modeling module, control module, adaptive control algorithm module, and digital twin integration platform module; The aforementioned multi-field coupling modeling module is used to construct a multi-field coupled dynamic model of an offshore wind turbine under the coupled effects of wind, waves, and earthquakes, in order to assess the impact of environmental load changes on structural vibration and provide input for the control module. The control module is used to achieve multi-objective coordinated control of vibration reduction of offshore wind turbines under extreme typhoon, resonance, and large earthquake conditions. The adaptive control algorithm module adaptively updates the control parameters based on real-time monitoring feedback data to ensure the stability and responsiveness of the system under different sea conditions. The aforementioned digital twin integration platform module establishes a data interaction channel between the physical wind turbine and the digital twin model through real-time data mapping and dynamic simulation; The multi-field coupling modeling module uses the Kaimal wind speed spectrum to describe wind shear characteristics, the Pierson-Moskowitz wave spectrum to represent random wave energy distribution, and the improved Kanai-Tajimi ground motion spectrum to represent seismic characteristics. It comprehensively considers the spatiotemporal evolution characteristics and correlations of wind-wave-seismic excitation, analyzes the probability distribution characteristics of environmental loads through the Copula function, and outputs multimodal dynamic response simulation data of the wind turbine structure based on stochastic differential equations.

2. The intelligent vibration control system for offshore wind turbines as described in claim 1, characterized in that: The control module includes: an adaptive tuned mass damper integrated at the top of the wind turbine tower or a key stress-bearing part; the adaptive tuned mass damper is equipped with a vibration energy acquisition module and has self-powering capability; based on Lyapunov stability theory, a fuzzy PID-LQR hybrid controller is designed to optimize the control of the adaptive tuned mass damper; and a multi-objective genetic algorithm is used to optimize the control parameters to achieve multi-objective coordinated control under extreme typhoon, resonance, and large earthquake conditions.

3. The intelligent vibration control system for offshore wind turbines as described in claim 2, characterized in that: The adaptive control algorithm module includes: introducing a physical information deep neural network, integrating traditional control theory with deep learning methods, and realizing real-time prediction and analysis of complex excitations and structural dynamic responses to wind-wave-earthquake under the constraints of physical laws.

4. The intelligent vibration control system for offshore wind turbines as described in claim 3, characterized in that: The aforementioned digital twin integration platform module is used to construct a real-time virtual mapping system for structure-controller-environment interaction. It integrates sensor networks and edge computing methods deployed on the wind turbine, and establishes a data interaction channel between the physical wind turbine and the digital twin model through real-time data mapping and dynamic simulation, thereby realizing real-time monitoring of structural response, simulation optimization of control strategies, remote diagnosis, and active control decision-making.

5. A control method, characterized in that, The control method described is the control method of the intelligent vibration control system for offshore wind turbines as described in claim 4, which includes the following steps: (1) collecting environmental excitation and structural response data based on a sensor network; (2) simulating the structural response through a multi-field coupling modeling module; (3) predicting the structural state and optimizing the control parameters using an adaptive control algorithm module; (4) actively controlling the system through control commands; and (5) completing remote optimization and control feedback closed loop through a digital twin integration platform module.

Images