Floating offshore wind power multi-body coupling real-time monitoring system and method

Abstract

The present invention discloses a real-time monitoring system and method for multi-body coupling of floating offshore wind power plants, belonging to the field of offshore wind power monitoring technology. The system comprises: an information acquisition module for interactively acquiring information about the layout environment and device configuration of floating offshore wind power plants; a physical property extraction module for extracting the physical properties of multiple structures; a monitoring architecture acquisition module for acquiring a real-time monitoring architecture; a coupling model acquisition module for constructing a multi-body coupling model; a real-time information transmission module for collecting data from floating offshore wind power plants; a fault response output module for outputting real-time fault responses; and a fault prevention and maintenance module for performing fault prevention and maintenance on floating offshore wind power plants. This application solves the technical problems in the prior art of floating offshore wind power plants, such as the complex multi-body coupling structure, difficulty in real-time monitoring, and untimely fault prevention, which lead to high operational risks and low maintenance efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of offshore wind power monitoring, and in particular to a floating offshore wind power multi-body coupling real-time monitoring system and method. Background Art

[0002] Floating offshore wind power technology is an emerging technology developed to address the development of deep-sea wind resources and holds great potential. Because offshore wind power projects face complex environmental conditions in deepwater areas, such as strong winds, high waves, and currents, traditional fixed wind turbines are unsuitable for these conditions. This is why floating wind power technology has emerged. Floating wind power systems utilize floating platforms and mooring systems to deploy wind turbines in deepwater areas, harnessing wind energy for power generation. Their advantage lies in their ability to be deployed in deeper waters, further from shore, capturing more stable and powerful wind energy, thereby improving power generation efficiency.

[0003] Currently, monitoring methods for floating offshore wind turbines remain limited, relying primarily on traditional fixed sensor deployments that struggle to address the multi-body coupling characteristics and dynamic changes of floating platforms. Furthermore, existing monitoring systems primarily focus on single or localized monitoring, lacking a comprehensive, dynamic approach for coupled structures. This results in lags in fault warnings and operational decision-making, hindering timely response to complex marine environmental changes. Therefore, a new technical solution is urgently needed that can monitor the multi-body coupling status of floating wind turbines in real time, providing timely fault warnings and risk analysis to improve their safety and operational efficiency. Summary of the Invention

[0004] This application provides a real-time monitoring system and method for multi-body coupling of floating offshore wind power plants, aiming to solve the technical problems in the prior art of complex multi-body coupling structures of floating offshore wind power plants, difficulty in real-time monitoring, and untimely fault prevention, which lead to high operating risks and low maintenance efficiency.

[0005] In view of the above problems, the present application provides a floating offshore wind power multi-body coupling real-time monitoring system and method.

[0006] According to a first aspect disclosed herein, a real-time monitoring system for multi-body coupling of floating offshore wind turbines is provided. The system includes an information acquisition module for interactively acquiring deployment environment information and device configuration information of a floating offshore wind turbine; a physical property extraction module for extracting multiple physical properties of multiple coupled structures in the floating offshore wind turbine from the device configuration information; a monitoring architecture acquisition module for performing sensor scheduling configuration for the multiple coupled structures based on the multiple physical properties to obtain a real-time monitoring architecture; a coupling model acquisition module for constructing a multi-body coupling model based on the deployment environment information and device configuration information; a real-time information transmission module for transmitting real-time wind power information acquired by the real-time monitoring architecture from data acquisition of the floating offshore wind turbine to the multi-body coupling model via a distributed sensor network; a fault response output module for performing an associated operational risk analysis based on the multi-body coupling model and outputting a real-time fault response after the multi-body coupling model is dynamically updated according to the real-time wind power information; and a fault prevention and maintenance module for performing fault prevention and maintenance on the floating offshore wind turbine based on the real-time fault response.

[0007] Another aspect disclosed in the present application provides a real-time monitoring method for multi-body coupling of floating offshore wind power plants, the method comprising interactively obtaining layout environment information and device configuration information of a floating offshore wind power plant; extracting multiple structural physical properties of multiple coupled structures in the floating offshore wind power plant from the device configuration information; performing sensor scheduling configuration of the multiple coupled structures according to the multiple structural physical properties to obtain a real-time monitoring architecture; constructing a multi-body coupling model based on the layout environment information and device configuration information; transmitting real-time wind power information obtained by data collection from the floating offshore wind power plant by the real-time monitoring architecture to the multi-body coupling model via a distributed sensor network; after the multi-body coupling model performs dynamic operation updates based on the real-time wind power information, performing associated operation risk analysis based on the multi-body coupling model to output a real-time fault response; and performing fault prevention operation and maintenance on the floating offshore wind power plant based on the real-time fault response.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] By adopting a technical solution of interactively acquiring the layout environment information and device composition information of floating offshore wind turbines, extracting the physical properties of multiple coupled structures, scheduling and configuring sensors, real-time data acquisition, and dynamic updating of multi-body coupling models, the problems of complex multi-body coupling monitoring, poor data real-time performance, and difficulty in timely prevention of faults in traditional offshore wind turbines are solved. The technical effect of real-time monitoring of the operating status of floating offshore wind turbines, improving the speed and accuracy of fault response, and optimizing the fault prevention and operation and maintenance processes is achieved.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A structural schematic diagram of a floating offshore wind power multi-body coupling real-time monitoring system is provided for an embodiment of the present application.

[0012] Figure 2 A flow chart of a method for real-time monitoring of floating offshore wind power multi-body coupling is provided for the embodiment of the present application;

[0013] Explanation of the accompanying symbols: information acquisition module 11, physical property extraction module 12, monitoring architecture acquisition module 13, coupling model acquisition module 14, real-time information transmission module 15, fault response output module 16, fault prevention and operation and maintenance module 17. DETAILED DESCRIPTION

[0014] The overall idea of ​​the technical solution provided by this application is as follows:

[0015] The present invention provides a real-time monitoring system and method for multi-body coupling in floating offshore wind turbines. This system interactively acquires information about the installation environment and configuration of floating offshore wind turbines, extracting the physical properties of multiple coupled structures. Based on this information, a real-time monitoring architecture is constructed through sensor scheduling and configuration, dynamically updated using a multi-body coupling model. This method utilizes real-time data collection and associated risk analysis to respond to and prevent wind turbine failures, aiming to improve operational safety and maintenance efficiency of wind turbine equipment.

[0016] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application will be specifically introduced in conjunction with the drawings in the specification.

[0017] Example 1, as Figure 1 As shown, the embodiment of the present application provides a floating offshore wind power multi-body coupling real-time monitoring system, which includes:

[0018] The information acquisition module 11 is used to interactively obtain the layout environment information and device configuration information of the floating offshore wind power device.

[0019] Specifically, a floating offshore wind turbine is an offshore wind turbine installed on a floating platform. It is adapted to deep-sea environments and stabilized by the floating structure's anchoring system. Deployment environment information refers to the external environmental conditions of the floating wind turbine. Device configuration information refers to the structure and design parameters of the floating wind turbine itself.

[0020] First, environmental information and equipment parameters are comprehensively collected through a variety of data sources and tools. When obtaining deployment environment information, meteorological monitoring systems (such as wind speed sensors, meteorological satellite data) are used to monitor meteorological data such as wind speed and wind direction in real time. At the same time, ocean monitoring systems (such as wave sensors, current meters) are combined to obtain ocean environmental data such as wave height, current direction and intensity. In addition, seabed topography data can be collected through sonar systems or seabed geological exploration tools (such as multi-beam echo sounders) to ensure the accuracy of seabed characteristics. Device composition information can be obtained through interaction with wind power equipment manufacturers and engineering design teams. Device composition information includes specific parameters of floating platforms and wind turbines.

[0021] This module ensures comprehensive and real-time collection of dynamic information about the wind turbine environment and its own structural parameters through the collaboration of multi-source sensor systems, data acquisition tools, and engineering design software, thus laying a solid foundation for subsequent monitoring and risk analysis.

[0022] The physical property extraction module 12 is configured to extract and obtain a plurality of structural physical properties of a plurality of coupled structures in the floating offshore wind turbine from the device configuration information.

[0023] Specifically, a coupled structure refers to the individual components or modules within a wind turbine, interconnected in a specific way to form a whole. Physical properties refer to the physical characteristics of each coupled structure, typically including size, shape, mass, material properties, and mechanical properties.

[0024] By analyzing design drawings or computer modeling data, the location, connection method and basic geometric characteristics of each coupled structure are determined. After these coupled structures are determined, their physical properties are further extracted.

[0025] Specifically, the design files automatically generated by 3D modeling software are used to obtain the geometric information of each structure, including its size, shape, and cross-sectional characteristics. Material properties are determined by consulting design documents or manufacturer-provided data sheets to determine the material properties of each coupled structure, including density, elastic modulus, Poisson's ratio, and other material properties. Mechanical analysis is performed on each coupled structure to calculate its strength, stiffness, stress-strain distribution, and other mechanical properties.

[0026] This module extracts the physical properties of the coupled structure from the device configuration information, which not only enables a comprehensive understanding of the specific structure and performance of the floating offshore wind turbine, but also provides accurate basic data for subsequent sensor deployment, dynamic analysis, and fault prediction.

[0027] The monitoring architecture acquisition module 13 is configured to perform sensor scheduling configuration of the plurality of coupled structures according to the physical properties of the plurality of structures to obtain a real-time monitoring architecture.

[0028] Specifically, sensor scheduling refers to the rational arrangement of sensor locations, types, and quantities based on the physical characteristics and monitoring requirements of each coupled structure to achieve real-time monitoring of key installation components. The real-time monitoring architecture, formed after sensor scheduling, is used to continuously collect operational status, external environmental data, and other key information from floating offshore wind turbines for real-time monitoring and analysis.

[0029] First, the physical properties of each coupled structure are analyzed to identify weak points or critical locations. By simulating the forces and deformations of each coupled structure under various environmental stresses, stress concentration areas, high-frequency vibrations, and critical fatigue nodes can be identified. For each coupled structure, key physical properties, such as the vibration characteristics of the wind turbine tower, the bending stresses of the blades, and the inclination and stability of the floating platform, determine the key locations for sensor placement.

[0030] Next, appropriate sensor types are selected based on the monitoring requirements of different locations. Specifically, accelerometers are suitable for monitoring wind turbine tower vibration, strain gauges are used to monitor blade stress and fatigue, inclination sensors are suitable for monitoring the platform's tilt angle, and pressure sensors can be used to measure the underwater pressure acting on the platform. Based on this, the sensor's performance, including accuracy, weather resistance, and response time, is determined to ensure it can adapt to the complex conditions of the marine environment.

[0031] Finally, a sensor deployment strategy is developed. Optimization simulation is performed using deployment strategy analysis tools to place sensors at the most critical monitoring nodes.

[0032] This module optimizes sensor configuration based on the physical properties of the structure, effectively improving monitoring accuracy and efficiency. By placing sensors at key locations on the structure, the resulting real-time monitoring architecture continuously monitors the operating status of floating wind turbines, promptly detecting potential faults and risks, minimizing downtime and extending their service life.

[0033] The coupling model obtaining module 14 is configured to construct and obtain a multi-body coupling model based on the layout environment information and the device configuration information.

[0034] Specifically, a multi-body coupling model is a mathematical model formed by modeling the interaction between multiple coupled structures of a wind turbine (such as the floating platform, tower, blades, and anchoring system) and their surroundings. This model considers the interactions between these multiple structures and the influence of the external environment, dynamically reflecting the behavior of the wind turbine under different environmental conditions.

[0035] First, the coupled components of a floating offshore wind turbine are analyzed. By analyzing the device's configuration, the multiple coupled components within the wind turbine can be disassembled, such as the floating platform, wind turbine tower, blades, and anchoring system. Each component has its own physical properties (such as size, mass, stiffness, and material characteristics), which serve as input parameters in the model. Based on these physical parameters, individual component models are then constructed.

[0036] Next, based on the deployment environment information, the environmental conditions of the wind turbine are obtained, such as wind speed, wave characteristics, current direction, seabed characteristics, etc. This environmental information is used as external input conditions to influence the stress state of each coupled structure.

[0037] After obtaining the physical models and environmental data for each coupled structure, a multi-body coupling model is constructed. First, the connections between the structures are modeled to establish the dynamic equations between them. Then, based on the forces acting on the ocean environment, the mechanical equations acting on each structure are constructed. Finally, the entire multi-body coupling model is solved and simulated. This simulation process simulates the operating behavior of the wind turbine under different environmental conditions.

[0038] This module enables dynamic simulation and precise analysis of floating offshore wind turbines by constructing a multi-body coupling model based on the deployment environment and device configuration information.

[0039] The real-time information transmission module 15 is used for the real-time monitoring architecture to collect data from the floating offshore wind power device and transmit the real-time wind power information obtained to the multi-body coupling model through a distributed sensor network.

[0040] Specifically, real-time wind power information refers to data collected from various sensors within a wind turbine installation, reflecting the installation's real-time operating status, including wind speed, blade rotation speed, and platform inclination. A distributed sensor network (DSN) is a network of sensors installed at key locations within a wind turbine installation, enabling distributed data collection, processing, and transmission.

[0041] First, key components of a wind turbine installation utilize various types of sensors for data collection. For example, accelerometers monitor the vibration of the wind turbine tower and floating platform, strain gauges monitor the stress of the turbine blades, inclination sensors monitor the platform's tilt, and anemometers and wind vanes monitor wind speed and direction. These sensors, located at various locations throughout the installation, form a distributed sensor network covering the entire wind turbine installation. These sensors continuously collect data throughout the installation's operation, providing real-time wind power information such as wind speed fluctuations, tower vibration frequency, and platform tilt angle.

[0042] Once data collection is complete, it is transmitted to a central monitoring system via wireless transmission technology. Each sensor has an independent communication path within the distributed network, ensuring real-time data transmission and enabling data sharing and collaboration between devices through the Internet of Things (IoT).

[0043] Through real-time monitoring architecture and distributed sensor networks, this module can accurately monitor the operating status of floating offshore wind turbines in real time, and dynamically interact with multi-body coupling models through data transmission to achieve real-time analysis and prediction.

[0044] The fault response output module 16 is configured to perform an associated operation risk analysis based on the multi-body coupling model and output a real-time fault response after the multi-body coupling model is dynamically updated according to the real-time wind power information.

[0045] Specifically, correlated operational risk analysis involves analyzing the risks faced by wind turbines under current conditions based on a multi-body coupling model and assessing the impact of these risks on their operation. Real-time fault response involves the system taking immediate action when an abnormality or potential fault is detected through risk analysis. This can include issuing an alarm, adjusting turbine operating parameters, or recommending maintenance intervention.

[0046] First, when sensors on the wind turbines collect real-time data, this data is transferred to the model for dynamic updating of the multi-body coupled model. This update typically uses the operational data collected by the sensors as input to adjust the model parameters.

[0047] Next, a correlated operational risk analysis is performed based on the updated multi-body coupling model. The current operational risk of the device is assessed by analyzing the status of each coupled structure in the model. If the risk analysis indicates that the wind turbine device is facing a failure or anomaly, the system will output a real-time fault response based on the risk level.

[0048] This module significantly improves the safety and reliability of floating offshore wind turbines through real-time risk analysis and fault response based on multi-body coupling models.

[0049] The fault prevention operation and maintenance module 17 is configured to perform fault prevention operation and maintenance on the floating offshore wind turbine according to the real-time fault response.

[0050] Specifically, fault prevention operation and maintenance refers to predicting and analyzing the potential failure risks of the equipment, performing maintenance and management in advance, and avoiding equipment damage or downtime.

[0051] First, real-time fault response, through early risk analysis and diagnosis, has identified certain components of the floating offshore wind turbine installation that are on the verge of failure. For example, the system detects an increase in the tilt angle of the floating platform, abnormal tower vibration frequency, or excessive stress in the anchoring system. Based on these fault signals, the system issues an alarm through its built-in early warning mechanism and initiates preventive maintenance procedures.

[0052] Through real-time fault response and fault prevention operation and maintenance, floating offshore wind turbines can achieve more efficient and safe long-term operation, avoid significant losses caused by sudden failures, and reduce operating and maintenance costs.

[0053] In some embodiments, the sensor scheduling configuration of the multiple coupled structures is performed according to the physical properties of the multiple structures to obtain a real-time monitoring architecture, and the execution steps include:

[0054] A plurality of monomer mathematical models are constructed according to the physical properties of the plurality of structures; a sensor deployment analysis is performed based on the plurality of monomer mathematical models to obtain a plurality of sensor deployment strategies; and a sensor scheduling configuration of the plurality of coupled structures is performed with the plurality of sensor deployment strategies as constraints to obtain a real-time monitoring architecture.

[0055] Specifically, a monomer mathematical model refers to a mathematical model established for a certain coupled structure, which describes its physical behavior and dynamic response characteristics under specific conditions, and is usually expressed through equations such as mechanics and structural mechanics.

[0056] First, a mathematical model of each coupled structure is constructed based on its physical properties. The purpose of each monomer mathematical model is to accurately describe the dynamic behavior of the structure in the marine environment.

[0057] Next, based on the mathematical model of the individual units, the sensor layout is analyzed. Sensor placement should be targeted at key locations within the structure, such as critical stress points, areas of frequent vibration, or locations of vulnerable components, to ensure that the data reflects the equipment's operating status. By analyzing each structure's stress concentration areas and dynamic response characteristics, the number, location, and type of sensors to be deployed are determined. Once the sensor deployment strategy is determined, the sensor scheduling is configured. Based on the dynamic response frequency of different structures, the sensor acquisition frequency and transmission priority are appropriately arranged. For example, some structures require high-frequency sampling, while others only require low-frequency monitoring. By properly configuring and scheduling, the system's energy consumption can be reduced and monitoring efficiency improved.

[0058] By constructing multiple single-unit mathematical models, formulating sensor deployment strategies, and performing reasonable sensor scheduling and configuration, floating offshore wind turbines can achieve an efficient and accurate real-time monitoring architecture, improving the safety and reliability of equipment operation.

[0059] In some embodiments, performing sensor deployment analysis based on the multiple monomer mathematical models to obtain multiple sensor deployment strategies includes:

[0060] A first structural physical property of a wind turbine in the floating offshore wind power device is extracted from the device configuration information, wherein the wind turbine is any one of the multiple coupled structures; multiple component structural information and multiple component behavior information of multiple key components are extracted based on the first structural physical property; after constructing multiple component structural models based on the multiple component structural information, the multiple component structural models are assembled to obtain a unit structural model; key monitoring nodes of the multiple key components are located based on the unit structural model and the multiple component behavior information to obtain a first sensor layout strategy; and so on, sensor layout analysis is performed based on the multiple monomer mathematical models to obtain the multiple sensor layout strategies.

[0061] Specifically, component structural information refers to detailed information about the geometry and material composition of key components. This information is used to build physical models and describe component behavior under different operating conditions. Component behavioral information refers to the mechanical performance of components during operation, such as stress, vibration, and temperature changes, reflecting their actual operating conditions.

[0062] First, the physical properties of the wind turbine are extracted from the device configuration information. The wind turbine is a key component of the coupled structure. Its physical properties include blade length and width, material strength, tower height, and the wave resistance of the base float. This data provides an accurate physical foundation for subsequent model construction.

[0063] Next, the physical properties of the wind turbine are used to further extract structural and behavioral information about its key components. Once this structural information is obtained, structural models of each key component are constructed. These models describe the stress and deformation of each component under different operating conditions using structural mechanics or finite element analysis. The component models are then assembled into a complete wind turbine structural model, ensuring that the interactions between the different components reflect realistic coupling relationships.

[0064] By analyzing the turbine structure model, we identify key monitoring nodes within the wind turbine. These nodes are typically areas of concentrated stress or frequent vibration, representing high-risk points for equipment failure. Based on these monitoring nodes, we develop a sensor placement strategy to ensure that sensors accurately capture data reflecting the health status of the equipment.

[0065] Similarly, multiple coupled structures are analyzed and sensor deployment strategies are derived. After analyzing the wind turbine, the same model construction and sensor deployment analysis are performed on other coupled structures. Each coupled structure has its own specific monitoring requirements, and the corresponding model analysis determines the sensor deployment strategy for each structure.

[0066] Through sensor deployment analysis based on multiple monomer mathematical models, an efficient and accurate real-time monitoring architecture can be established for floating offshore wind turbines, thereby improving the operational safety and maintenance efficiency of wind turbines.

[0067] In some embodiments, the key monitoring nodes of the plurality of key components are located based on the unit structure model and the behavior information of the plurality of components to obtain a first sensor deployment strategy, and the execution steps include:

[0068] The behavior information of the multiple components is fitted to the unit structure model to obtain a unit operation behavior model; based on the unit operation behavior model, the operation status data of the multiple key components are extracted to obtain multiple groups of operation status indicators; based on the multiple groups of operation status indicators, the key monitoring nodes of the multiple key components are located in the unit operation behavior model to obtain multiple groups of sensor layout nodes; the wind turbine, multiple key components and multiple groups of sensor layout nodes are associated and stored to constitute the first sensor layout strategy.

[0069] Specifically, the unit operation behavior model refers to a dynamic model generated by integrating the behavior information of components into the unit structure model. It can simulate the real-time operating status of the entire wind turbine under different environmental conditions. Operational status indicators refer to performance indicators derived from monitoring the behavioral data of key components, such as vibration frequency, temperature, stress amplitude, etc., which can reflect the health status and potential failure risks of components. Key monitoring nodes refer to areas that require intensive monitoring. These nodes are usually located in areas with concentrated stress or prone to damage, and are high-incidence points of failure. Sensor deployment nodes are sensor installation locations selected based on monitoring needs. The selection of these nodes directly affects the accuracy and effectiveness of monitoring data.

[0070] First, behavioral information extracted from key components (such as blade vibration characteristics, tower stress distribution, and gearbox temperature variations) is fitted into the structural model of the entire wind turbine. This actual component behavior information is coupled with the mathematical model of the overall turbine structure to form a turbine operational behavior model.

[0071] After developing the unit's operational behavior model, sensors are used to extract real-time operational status data from various components. This includes blade vibration frequency, gearbox temperature, and tower stress amplitude. This real-time data is then used to further calculate and extract operational status indicators, such as vibration amplitude, temperature change rate, and stress distribution.

[0072] Based on the multiple sets of operating status indicators extracted above, we analyze stress concentration areas or vulnerable areas of key components to determine sensor placement. These areas are typically where the equipment experiences significant stress or vibration during operation. Further analysis of the unit's operating behavior model helps locate these key monitoring nodes, ensuring that sensors are installed in the most effective locations to monitor the equipment's operating status.

[0073] After identifying key monitoring nodes, develop a sensor deployment strategy based on their locations. This includes sensor type (such as vibration sensors, temperature sensors, and stress sensors), number of sensors, and installation method. Ensure these sensors can collect critical operational data in real time.

[0074] After sensor deployment is complete, key components of the wind turbine, their corresponding operating status indicators, and monitoring nodes are associated and stored. This ensures traceability of monitoring data and system maintainability. Storing this associated information provides data support for subsequent fault diagnosis and equipment operation and maintenance.

[0075] In some embodiments, the multi-body coupling model is constructed based on the deployment environment information and the device configuration information, and the execution steps include:

[0076] The device composition information is disassembled to obtain multiple structural relationships and multiple structural boundary conditions of the multiple coupled structures; multiple external action information of the multiple coupled structures is extracted from the layout environment information; after obtaining multiple structural characteristics of the multiple coupled structures through an online search, dynamic equations are configured based on the multiple structural characteristics to obtain multiple interaction equations; after integrating the multiple monomer mathematical models into a pre-call framework, the multiple monomer mathematical models are coupled according to the multiple structural relationships and multiple interaction equations to obtain an initial coupling model; the layout environment information is merged with the initial coupling model as a boundary condition to obtain the multi-body coupling model.

[0077] Specifically, boundary conditions define the constraints on a structure's operating environment, such as fixed and free ends, and determine its response to external forces, such as force, displacement, and pressure. External action information refers to the environmental impact on the coupled structure, including natural forces such as wind, waves, and currents. Structural properties, coupled with the structure's physical and mechanical properties, such as material stiffness, mass distribution, and damping, determine its dynamic response.

[0078] First, the structural information of the floating offshore wind turbine was disassembled to extract the relationships between the various coupled structures. For example, the wind turbine is connected to the sea surface through a floating platform, and the mooring system secures the platform to the seabed.

[0079] Next, external force information such as wind, waves, and ocean currents is extracted from the actual environment in which the floating wind turbine is located. This external force information determines the force conditions of each coupled structure in the environment.

[0080] Then, the physical properties of each coupled structure are obtained by searching the database or the Internet. Based on these structural properties, the dynamic equations of each coupled structure are constructed, which describe their motion laws under external action.

[0081] The previously constructed monomer mathematical models were integrated into a pre-call framework and coupled based on the interrelationships and dynamic equations of the structures. Coupling means that the structures not only move independently but also influence each other.

[0082] Finally, the extracted deployment environment information (such as wind, wave, and current conditions) is integrated into the initial coupled model as boundary conditions to further optimize the model's accuracy and generate a multi-body coupled model that reflects the actual environment of the floating offshore wind turbine. This model can be used to simulate the dynamic response of the device in complex environments.

[0083] The multi-body coupling model can accurately simulate the motion of wind turbines under complex external forces such as wind, waves, and currents, improving the design and operational safety of wind turbines and enhancing the wind and wave resistance and operational stability of the entire device.

[0084] In some embodiments, after the multi-body coupling model is dynamically updated according to the real-time wind power information, performing associated operation risk analysis based on the multi-body coupling model and outputting a real-time fault response includes:

[0085] Interactively obtain multiple groups of sample operation data sets under multiple sample fault modes; construct and generate a fault state identification model based on the multiple groups of sample operation data sets; when the duration for the multi-body coupling model to dynamically update the operation according to the real-time wind power information reaches a preset duration constraint, extract associated operation data from the multi-body coupling model to obtain an associated operation data set; synchronize the associated operation data set to the fault state identification model for fault pattern matching to obtain a real-time fault mode and a real-time fault level; after setting a warning signal level according to the real-time fault level, output the real-time fault mode as a real-time fault response.

[0086] Specifically, the associated operational dataset refers to real-time data extracted from the multi-body coupled model, including operational information on wind turbines, floating platforms, and mooring systems in their current states. Fault pattern matching involves comparing real-time monitored operational data with historical fault patterns to identify whether the current equipment is in a fault state and the severity of that fault mode. Real-time fault response refers to the warning or prompt output when the system detects a fault, typically including the fault type, severity, and recommended action.

[0087] First, we collected operational data from floating offshore wind turbines under various fault modes using historical or experimental data. By analyzing this historical operational data, we obtained sensor stress data related to the tilt of the floating platform under high winds and waves, as well as the inclination angle of the floating platform and the stress conditions of the mooring system, which served as sample fault data.

[0088] By using machine learning algorithms (such as support vector machines, neural networks, etc.) or statistical analysis methods, a fault state recognition model is trained based on a sample data set. The goal is to establish a classification model that can distinguish between fault states and healthy states by learning from operating data under normal operation and different fault modes.

[0089] When the multi-body coupled model is dynamically updated based on real-time wind power information for a preset period (e.g., every 10 minutes or longer), the system extracts relevant operational data from the multi-body coupled model. This data includes wind turbine stress, floating platform inclination, and mooring system tension. This relevant operational data reflects the current system operating status.

[0090] The extracted, correlated operational data sets are transmitted in real time to the fault state recognition model. The model matches this data with previously trained fault patterns to determine whether the system is currently in a fault state and to identify the specific fault mode and level. For example, if the platform's inclination exceeds the safe range, it indicates a tilt fault.

[0091] By building a fault status identification model, the fault status of floating offshore wind power devices can be detected in real time, and fault responses can be output in a timely manner to improve the safety and stability of the system.

[0092] In some embodiments, the steps of constructing and generating a fault state recognition model based on the plurality of sample operation data sets include:

[0093] From the multiple groups of sample operation data sets, a first group of sample operation data sets corresponding to a first sample fault mode is called and obtained, wherein the first sample fault mode is any one of the multiple sample fault modes; the first group of sample operation data sets is split based on the fault level to obtain K sample operation data sets; the first sample operation data set corresponding to the first fault level is called from the K sample operation data sets; the first group of sample operation data sets is split based on the multiple coupling structures to obtain multiple sample operation data combinations; fault feature aggregation is performed on the multiple sample operation data combinations to obtain a first group of fault deviation windows of the first sample fault mode at the first fault level; and so on, K groups of fault deviation windows of the first sample fault mode at K fault levels are obtained; the first sample fault mode, K fault levels and K groups of fault deviation windows are stored in association to obtain a first fault mode identification branch; and so on, multiple fault mode identification branches of the multiple sample fault modes are constructed; and the multiple fault mode identification branches are connected in parallel to obtain the fault state identification model.

[0094] Specifically, the fault level refers to the classification of fault modes according to the severity of the fault, which is usually divided into minor, moderate and severe levels. Each level corresponds to different maintenance needs and risks. The fault deviation window refers to the difference between the normal operating state and the fault state. By analyzing the abnormalities of the equipment operation data, the window area where it deviates from the normal operating range is determined to determine the occurrence of the fault. The fault mode recognition branch refers to the recognition model branch constructed for a specific fault mode and different fault levels, which is used to identify and classify specific fault modes and levels.

[0095] First, select a dataset related to a specific fault mode from multiple stored sample run datasets. Split the first sample run dataset by fault level, for example, into K sample run datasets classified by minor, moderate, and severe levels. Each dataset corresponds to a fault condition of varying severity, enabling more accurate identification of different fault stages.

[0096] From the K split sample operation data sets, select the sample operation data set corresponding to the first fault level (e.g., a minor fault) for subsequent analysis and modeling. This sample operation data set is further split according to the different coupling structures of the equipment to obtain multiple sample operation data combinations.

[0097] The split operating data is combined to analyze and extract the key fault characteristics of each component under the current failure mode. These characteristics include deviations from normal operating values ​​for stress, displacement, temperature, etc. of each component, forming a fault deviation window.

[0098] Based on the fault severity level, a fault deviation window is calculated for each level. For example, a minor fault may only show slight stress anomalies, while a major fault may show significant stress and vibration anomalies. These deviation windows can be used for subsequent real-time fault detection.

[0099] For each sample fault mode and its various fault levels, multiple fault pattern recognition branches are constructed. Each branch is used to identify fault characteristics of different levels under a specific fault mode. When multiple fault pattern recognition branches are connected in parallel, a complete fault state recognition model is formed.

[0100] By building multiple fault mode recognition branches, the system can accurately identify the type and severity of faults based on different fault levels and the specific operating conditions of the equipment structure, thereby improving the accuracy of fault detection.

[0101] In summary, the floating offshore wind power multi-body coupling real-time monitoring system provided by the embodiments of the present application has the following technical effects:

[0102] 1. By building a multi-body coupled real-time monitoring model for floating offshore wind turbines, we can comprehensively monitor the operating status of all components in the device. Coupled analysis based on real-time data enhances comprehensive control over device operation in complex dynamic environments, significantly improving the stability and safety of wind turbines.

[0103] 2. Through the rational deployment and scheduling of sensors, an effective real-time monitoring architecture is formed. The sensor deployment strategy based on the single-unit mathematical model ensures accurate monitoring of key nodes, helps improve the accuracy of data collection and the overall efficiency of the monitoring system, and reduces blind spots.

[0104] 3. By combining the device's structural information and the deployment environment, a multi-body coupling model is constructed to enable coupling analysis between complex structures. This model can dynamically respond to environmental changes, improving the adaptability and operational stability of offshore wind turbines in different environments.

[0105] The second embodiment is based on the same inventive concept as the floating offshore wind power multi-body coupling real-time monitoring system in the above embodiment. Figure 2 As shown, the embodiment of the present application provides a real-time monitoring method for multi-body coupling of floating offshore wind power, the method comprising:

[0106] Step S100: interactively obtaining deployment environment information and device configuration information of a floating offshore wind turbine;

[0107] Step S200: extracting and obtaining a plurality of structural physical properties of a plurality of coupled structures in the floating offshore wind turbine from the device configuration information;

[0108] Step S300: performing sensor scheduling configuration of the plurality of coupled structures according to the physical properties of the plurality of structures to obtain a real-time monitoring architecture;

[0109] Step S400: constructing a multi-body coupling model based on the deployment environment information and device configuration information;

[0110] Step S500: the real-time monitoring architecture collects data from the floating offshore wind turbine and transmits the real-time wind power information obtained to the multi-body coupling model via a distributed sensor network;

[0111] Step S600: After the multi-body coupling model is dynamically updated according to the real-time wind power information, an associated operation risk analysis is performed based on the multi-body coupling model, and a real-time fault response is output;

[0112] Step S700: performing fault prevention operation and maintenance on the floating offshore wind turbine according to the real-time fault response.

[0113] Furthermore, the sensors of the multiple coupled structures are scheduled and configured according to the physical properties of the multiple structures to obtain a real-time monitoring architecture, including: constructing multiple monomer mathematical models according to the physical properties of the multiple structures; performing sensor layout analysis based on the multiple monomer mathematical models to obtain multiple sensor layout strategies; and scheduling and configuring the sensors of the multiple coupled structures with the multiple sensor layout strategies as constraints to obtain a real-time monitoring architecture.

[0114] Furthermore, a sensor layout analysis is performed based on the multiple monomer mathematical models to obtain multiple sensor layout strategies, including: extracting the first structural physical properties of the wind turbine group in the floating offshore wind power device from the device composition information, wherein the wind turbine group is any one of the multiple coupled structures; extracting multiple component structure information and multiple component behavior information of multiple key components based on the first structural physical properties; constructing multiple component structure models based on the multiple component structure information, assembling the multiple component structure models to obtain a unit structure model; locating the key monitoring nodes of the multiple key components based on the unit structure model and the multiple component behavior information to obtain a first sensor layout strategy; and so on, performing sensor layout analysis based on the multiple monomer mathematical models to obtain the multiple sensor layout strategies.

[0115] Furthermore, the key monitoring nodes of the multiple key components are located according to the unit structure model and the behavior information of the multiple components to obtain a first sensor deployment strategy, including: fitting the behavior information of the multiple components to the unit structure model to obtain a unit operation behavior model; extracting the operation status data of the multiple key components based on the unit operation behavior model to obtain multiple groups of operation status indicators; locating the key monitoring nodes of the multiple key components in the unit operation behavior model based on the multiple groups of operation status indicators to obtain multiple groups of sensor deployment nodes; and associating and storing the wind turbine, multiple key components and multiple groups of sensor deployment nodes to constitute the first sensor deployment strategy.

[0116] Furthermore, a multi-body coupling model is constructed based on the layout environment information and the device composition information, including: disassembling the device composition information to obtain multiple structural relationships and multiple structural boundary conditions of the multiple coupled structures; extracting multiple external action information of the multiple coupled structures from the layout environment information; after obtaining multiple structural characteristics of the multiple coupled structures through an online search, configuring dynamic equations based on the multiple structural characteristics to obtain multiple interaction equations; after integrating the multiple monomer mathematical models into the pre-call framework, coupling the multiple monomer mathematical models according to the multiple structural relationships and multiple interaction equations to obtain an initial coupling model; fusing the layout environment information as a boundary condition with the initial coupling model to obtain the multi-body coupling model.

[0117] Furthermore, after the multi-body coupling model is dynamically updated according to the real-time wind power information, an associated operation risk analysis is performed based on the multi-body coupling model, and a real-time fault response is output, including: interactively obtaining multiple groups of sample operation data sets under multiple sample fault modes; constructing a fault state identification model based on the multiple groups of sample operation data sets; when the duration of the multi-body coupling model's dynamic operation update according to the real-time wind power information reaches a preset duration constraint, extracting associated operation data from the multi-body coupling model to obtain an associated operation data set; synchronizing the associated operation data set to the fault state identification model for fault pattern matching to obtain a real-time fault mode and a real-time fault level; after setting a warning signal level according to the real-time fault level, outputting the real-time fault mode as a real-time fault response.

[0118] Furthermore, a fault state identification model is constructed based on the multiple groups of sample operation data sets, including: calling and obtaining a first group of sample operation data sets corresponding to a first sample fault mode from the multiple groups of sample operation data sets, wherein the first sample fault mode is any one of the multiple sample fault modes; splitting the first group of sample operation data sets based on the fault level to obtain K sample operation data sets; calling a first sample operation data set corresponding to the first fault level from the K sample operation data sets; splitting the first group of sample operation data sets based on the multiple coupling structures to obtain multiple sample operation data combinations; performing fault feature aggregation on the multiple sample operation data combinations to obtain a first group of fault deviation windows of the first sample fault mode at the first fault level; and so on, obtaining K groups of fault deviation windows of the first sample fault mode at K fault levels; associating and storing the first sample fault mode, K fault levels and K groups of fault deviation windows to obtain a first fault mode identification branch; and so on, constructing multiple fault mode identification branches of the multiple sample fault modes; and connecting the multiple fault mode identification branches in parallel to obtain the fault state identification model.

[0119] Any step of the method described above can be stored as a computer instruction or program in an unlimited computer memory, and can be called and recognized by an unlimited computer processor to implement any method in the embodiments of the present application, without any unnecessary restrictions.

[0120] Furthermore, the terms "first" or "second" as described above may not only represent an order relationship but may also represent a specific concept and / or refer to the selection of multiple elements individually or collectively. Obviously, those skilled in the art may make various modifications and variations to this application without departing from the scope of this application. Thus, if such modifications and variations fall within the scope of this application and its equivalents, this application is intended to include such modifications and variations.

Claims

1. Floating offshore wind power multi-body coupling real-time monitoring system, characterized by: The system comprises: An information acquisition module, for interactively acquiring layout environment information and device composition information of a floating offshore wind power device; a physical property extraction module, configured to extract and obtain a plurality of structural physical properties of a plurality of coupled structures in the floating offshore wind turbine from the device configuration information; A monitoring architecture acquisition module, configured to perform sensor scheduling configuration of the plurality of coupled structures according to the physical properties of the plurality of structures to obtain a real-time monitoring architecture; A coupling model acquisition module, configured to construct and acquire a multi-body coupling model based on the deployment environment information and the device configuration information; A real-time information transmission module, configured to transmit the real-time wind power information acquired by the real-time monitoring architecture through data collection on the floating offshore wind power device to the multi-body coupling model via a distributed sensor network; a fault response output module, configured to perform an associated operation risk analysis based on the multi-body coupling model and output a real-time fault response after the multi-body coupling model is dynamically updated according to the real-time wind power information; a fault prevention operation and maintenance module, configured to perform fault prevention operation and maintenance on the floating offshore wind turbine according to the real-time fault response; After the multi-body coupling model is dynamically updated according to the real-time wind power information, an associated operation risk analysis is performed based on the multi-body coupling model to output a real-time fault response, including: Interactively obtain multiple sets of sample operation data sets under various sample failure modes; Constructing and generating a fault state recognition model based on the plurality of sample operation data sets; When the duration of the dynamic update of the multi-body coupling model according to the real-time wind power information reaches a preset duration constraint, extracting associated operation data of the multi-body coupling model to obtain an associated operation data set; Synchronizing the associated operation data set to the fault state identification model to perform fault pattern matching to obtain a real-time fault mode and a real-time fault level; After setting the warning signal level according to the real-time fault level, the real-time fault mode is output as a real-time fault response.

2. The floating offshore wind power multi-body coupling real-time monitoring system according to claim 1, characterized in that: Performing sensor scheduling configuration of the multiple coupled structures according to the physical properties of the multiple structures to obtain a real-time monitoring architecture includes: constructing a plurality of monomer mathematical models according to the physical properties of the plurality of structures; Performing sensor deployment analysis based on the multiple monomer mathematical models to obtain multiple sensor deployment strategies; The multiple sensor deployment strategies are used as constraints to perform sensor scheduling configuration of the multiple coupled structures to obtain a real-time monitoring architecture.

3. The floating offshore wind power multi-body coupling real-time monitoring system according to claim 2, characterized in that: Performing sensor deployment analysis based on the multiple monomer mathematical models to obtain multiple sensor deployment strategies includes: Extracting and obtaining a first structural physical property of a wind turbine in the floating offshore wind turbine from the device configuration information, wherein the wind turbine is any one of the multiple coupled structures; Extracting and obtaining a plurality of component structure information and a plurality of component behavior information of a plurality of key components according to the physical properties of the first structure; After constructing a plurality of component structure models according to the plurality of component structure information, assembling the plurality of component structure models to obtain a unit structure model; Positioning key monitoring nodes of the multiple key components according to the unit structure model and the behavior information of the multiple components to obtain a first sensor deployment strategy; Similarly, the sensor layout analysis is performed based on the multiple monomer mathematical models to obtain the multiple sensor layout strategies.

4. The floating offshore wind power multi-body coupling real-time monitoring system according to claim 3, characterized in that: Positioning key monitoring nodes of the multiple key components according to the unit structure model and the behavior information of the multiple components to obtain a first sensor deployment strategy includes: Fitting the plurality of component behavior information to the unit structure model to obtain a unit operation behavior model; Extracting the operating status data of the plurality of key components based on the unit operating behavior model to obtain a plurality of groups of operating status indicators; Positioning key monitoring nodes of the multiple key components in the unit operation behavior model based on the multiple groups of operation status indicators to obtain multiple groups of sensor deployment nodes; The wind turbine generator set, multiple key components and multiple groups of sensor deployment nodes are stored in association to form the first sensor deployment strategy.

5. The floating offshore wind power multi-body coupling real-time monitoring system according to claim 2, characterized in that: Constructing a multi-body coupling model based on the layout environment information and the device composition information includes: disassembling the device configuration information to obtain a plurality of structural relationships and a plurality of structural boundary conditions of the plurality of coupled structures; Extracting and obtaining a plurality of external action information of the plurality of coupling structures from the layout environment information; After obtaining a plurality of structural characteristics of the plurality of coupled structures through network search, configuring dynamic equations based on the plurality of structural characteristics to obtain a plurality of interaction equations; After integrating the multiple monomer mathematical models into the pre-call framework, the multiple monomer mathematical models are coupled according to the multiple structural relationships and the multiple interaction equations to obtain an initial coupled model; The layout environment information is used as a boundary condition and integrated with the initial coupling model to obtain the multi-body coupling model.

6. The floating offshore wind power multi-body coupling real-time monitoring system according to claim 1, characterized in that: Constructing and generating a fault state recognition model based on the plurality of sample operation data sets includes: Calling and obtaining a first set of sample operation data sets corresponding to a first sample failure mode from the multiple sets of sample operation data sets, wherein the first sample failure mode is any one of the multiple sample failure modes; Splitting the first group of sample operation data sets based on the fault level to obtain K sample operation data sets; Calling a first sample operation data set corresponding to a first fault level from the K sample operation data sets; splitting the first set of sample operation data sets based on the multiple coupled structures to obtain multiple sample operation data combinations; Performing fault feature aggregation on the plurality of sample operation data combinations to obtain a first group of fault deviation windows of the first sample fault mode at a first fault level; Similarly, K groups of fault deviation windows of the first sample fault mode at K fault levels are obtained; Associatively storing the first sample fault mode, K fault levels, and K groups of fault deviation windows to obtain a first fault mode identification branch; Similarly, multiple failure mode identification branches of the multiple sample failure modes are constructed; The multiple fault mode identification branches are connected in parallel to obtain the fault state identification model.

7. A real-time monitoring method for multi-body coupling of floating offshore wind power, characterized in that: The method is applied to the floating offshore wind power multi-body coupling real-time monitoring system according to any one of claims 1 to 6, and the method comprises: Interactively obtain the layout environment information and device composition information of the floating offshore wind power device; Extracting and obtaining a plurality of structural physical properties of a plurality of coupled structures in the floating offshore wind turbine from the device configuration information; Performing sensor scheduling configuration of the multiple coupled structures according to the physical properties of the multiple structures to obtain a real-time monitoring architecture; Constructing a multi-body coupling model based on the layout environment information and the device composition information; The real-time monitoring architecture collects data from the floating offshore wind power device and transmits the real-time wind power information obtained to the multi-body coupling model through a distributed sensor network; After the multi-body coupling model is dynamically updated according to the real-time wind power information, an associated operation risk analysis is performed based on the multi-body coupling model, and a real-time fault response is output; Fault prevention operation and maintenance are performed on the floating offshore wind power device according to the real-time fault response.

Images