Digital twinborn intelligent sensing system and method applied to wind turbine generator, medium and equipment

Abstract

The invention relates to a digital twinborn intelligent sensing system and method applied to a wind turbine generator, a medium and equipment. The digital twinborn intelligent sensing system comprises an end side, a station side and a center side, the end side comprises a data sensing layer and a data acquisition and calculation layer; the data sensing layer comprises a plurality of sensing devices; the station side comprises a first-area data management module, a second-area data management module and a third-area data management application module; the center side comprises a digital twinborn simulation model building module, a virtual sensing module and an intelligent diagnosis module. According to the invention, standardized fusion of multi-source data and hierarchical storage of data can be realized, and virtual perception, intelligent diagnosis and early warning and digital twinborn simulation model functions are developed and deployed at the center side. According to the method, multi-source data standardized fusion and data hierarchical storage can be realized, virtual perception, intelligent diagnosis and early warning and digital twinborn simulation model functions are developed and deployed on the center side, and the problems of large data acquisition difficulty, low integrity, low accuracy and the like of the offshore wind turbine generator are effectively solved.

Description

Technical Field

[0001] The present invention relates to the field of wind turbines, and more specifically, to a digital twin intelligent sensing system, method, medium and equipment applied to wind turbines. Background Art

[0002] As installed capacity rapidly grows, wind turbine operation monitoring, a "software assurance" system, is also receiving increasing attention. Due to the remote locations and harsh environments of wind farms, wind turbine operation and maintenance costs are relatively high. With the rapid iteration of offshore wind power technology, measurement accuracy, communication speed, and computing power are constantly improving, and the volume and richness of data are growing exponentially. Communication speed and computing power guarantee the real-time and accuracy of digital twins, while measurement accuracy, data volume, and data richness support the high-fidelity, full-scale representation of digital twins. However, establishing digital twin models for complex structures like offshore wind turbines still faces challenges in measurement and sensing, such as difficulty in data acquisition, low data integrity, and low data accuracy. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to provide a digital twin intelligent perception system, method, medium and equipment applied to wind turbines in response to the problems existing in the prior art.

[0004] The technical solution adopted by the present invention to solve the technical problem is: constructing a digital twin intelligent perception system applied to wind turbines, including: terminal side, station side and center side;

[0005] The end side includes: a data perception layer and a data acquisition and calculation layer; the data perception layer includes multiple sensor devices, which are used to acquire and monitor multiple sensor data; the data acquisition and calculation layer is used to acquire, process, calculate and store raw data, and to acquire and process the multiple sensor data;

[0006] The station side includes: a zone 1 data management module, a zone 2 data management module, and a zone 3 data management application module; the zone 1 data management module is used to access the perception data and manage the perception data; the zone 2 data management module is used to cache the perception data and perform gate management on the perception data; the zone 3 data management application module is used to manage and apply the perception data and the original data;

[0007] The center side includes: a digital twin simulation model construction module, a virtual perception module and an intelligent diagnosis module; the digital twin simulation model construction module is used to construct a digital twin model of a wind turbine by combining finite element analysis and data correction; the virtual perception module is used to access the multiple perception data, real-time operation data and equipment status data; the intelligent diagnosis module is used to construct an equipment diagnosis model based on the multiple perception data, the real-time operation data, the equipment status data and the equipment failure mechanism, and perform fault warning diagnosis and life prediction based on the equipment diagnosis model.

[0008] In the digital twin intelligent perception system for wind turbines described in the present invention, the multiple sensing devices include: a first load sensor installed on the inner wall of the wind turbine blade, a second load sensor installed on the tower section, a nacelle-type laser wind measurement radar installed on the top of the nacelle, a vibration pickup installed on the tower section, a dynamic tilt monitoring sensor installed on the top of the tower, and a blade soundprint monitoring device installed on the surface of the wind turbine blade;

[0009] The data acquisition and computing layer includes: a standardized data acquisition module, an edge computing module, a data storage module, a controller, and a field bus for connecting the modules; the standardized data acquisition module is used to perform standardized acquisition and processing of the various perception data; the data storage module is used to store data; the controller is used to control and manage each module; the edge computing module is used to collect, calculate and store the original data.

[0010] In the digital twin intelligent perception system for wind turbines according to the present invention, the edge computing module includes:

[0011] An edge node device, configured to collect the raw data;

[0012] A data preprocessing module, which is used to filter, reduce noise and remove outliers from the raw data, and perform data format conversion and standardization;

[0013] A local storage module, wherein the local storage module is used to locally store the original data;

[0014] An edge computing submodule, configured to perform data analysis and calculations based on the end side;

[0015] A communication module, which uses network slicing technology to provide a connection between the edge node device and the cloud or other devices.

[0016] The digital twin intelligent perception system for wind turbines according to the present invention further includes: a data management service unit applied to the terminal side, the station side, and the center side;

[0017] The data management service unit includes: a terminal-side IoT layer;

[0018] The end-side IoT layer includes:

[0019] A data processing module, configured to process structured data, semi-structured data, or unstructured data collected by the terminal side;

[0020] A data coding model construction module, wherein the data coding model construction module is used to construct a standardized data coding module;

[0021] A user authority configuration module, which is used to support the station-side and center-side users in authority configuration;

[0022] A data storage policy configuration module is used to support data storage policy configuration.

[0023] In the digital twin intelligent perception system for wind turbines according to the present invention, the terminal-side IoT layer further includes:

[0024] A physical model definition and mapping module, configured to create a customized digital representation of the device in the end-side IoT layer, construct a physical model based on the digital representation, and map the physical properties and functions of the device to the physical model;

[0025] A physical model version update module, configured to incrementally update the physical model based on a preset update strategy after detecting a physical model version update;

[0026] A physical model sharing and collaboration module, which is used to support sharing and collaboration of physical models;

[0027] A visualization module is used to provide a graphical interface.

[0028] In the digital twin intelligent perception system for wind turbines according to the present invention, the digital twin simulation model construction module includes:

[0029] A wind speed model construction module, wherein the wind speed model construction module is used to construct a model based on wind-related parameters to obtain a wind speed model;

[0030] A blade model building module, wherein the blade model building module is used to perform finite element analysis modeling based on blade parameters to obtain a blade model;

[0031] A tower model building module, which is used to perform finite element analysis modeling on tower parameters to obtain a load model;

[0032] An electrical system model building module, wherein the electrical system model building module is used to perform model building based on device parameters to obtain an electrical system model and control strategy;

[0033] A simulation model construction module is used to construct a model based on the wind speed model, the blade model, the tower model, and the electrical system model and control strategy to obtain a digital twin model of the wind turbine.

[0034] In the digital twin intelligent perception system for wind turbines according to the present invention, the intelligent diagnosis module includes:

[0035] An early warning model construction module is used to construct a model based on the intelligent perception model to obtain an early warning model;

[0036] a diagnostic model construction module, configured to construct a model based on the multiple sensory data, the real-time operation data, the device status data, and the device failure mechanism to obtain the device diagnostic model;

[0037] A fault warning diagnosis module is used to perform fault warning diagnosis and life prediction based on the warning model and / or the equipment diagnosis model.

[0038] The present invention also provides a digital twin intelligent perception method for a wind turbine generator set, which is applied to the digital twin intelligent perception system for a wind turbine generator set described above, and includes the following steps:

[0039] Obtaining device-side perception data and device parameters;

[0040] Perform finite element analysis modeling based on the sensing data to obtain a wind speed model, a blade model, and a tower model;

[0041] Modeling is performed based on the equipment parameters to obtain an electrical system model and control strategy;

[0042] Combining the wind speed model, the blade model, the tower model, and the electrical system model with the control strategy to construct a model to obtain a digital twin model of the wind turbine;

[0043] Performing data correction on the digital twin model of the wind turbine generator set to obtain a target digital twin model;

[0044] Interoperate data between the digital twin model of the target and the cloud platform;

[0045] After data intercommunication, fault warning diagnosis and life prediction are performed based on the constructed equipment diagnosis model.

[0046] The present invention also provides a storage medium storing a computer program, which is suitable for loading by a processor to execute the steps of the digital twin intelligent perception method applied to wind turbines as described above.

[0047] The present invention also provides an electronic device comprising a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the steps of the digital twin intelligent perception method applied to a wind turbine as described above by calling the computer program stored in the memory.

[0048] The digital twin intelligent perception system, method, medium and equipment applied to wind turbines according to the present invention have the following beneficial effects: including: end side, station side and center side; the end side includes: data perception layer and data acquisition and calculation layer; the data perception layer includes a variety of sensing devices; the station side includes: zone one data management module, zone two data management module and zone three data management application module; the center side includes: digital twin simulation model construction module, virtual perception module and intelligent diagnosis module. The present invention can realize the standardized fusion of multi-source data and hierarchical data storage, and develop and deploy virtual perception, intelligent diagnosis and early warning, and digital twin simulation model functions on the center side. The present invention can realize the standardized fusion of multi-source data and hierarchical data storage, and develop and deploy virtual perception, intelligent diagnosis and early warning, and digital twin simulation model functions on the center side, effectively solving the problems of difficulty in acquiring data from offshore wind turbines, low integrity and low accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The present invention will be further described below with reference to the accompanying drawings and embodiments, in which:

[0050] Figure 1 This is a system architecture module diagram of an embodiment of a digital twin intelligent perception system for wind turbines provided by the present invention;

[0051] Figure 2 This is a flow chart of an embodiment of a digital twin intelligent perception method for wind turbines provided by the present invention;

[0052] Figure 3 This is a hardware structure diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0054] In a preferred embodiment, Figure 1 As shown, the digital twin intelligent perception system applied to wind turbines includes: terminal side, station side and center side.

[0055] The end side includes: a data perception layer and a data acquisition and computing layer; the data perception layer includes a variety of sensor devices, which are used to acquire monitoring and obtain a variety of perception data; the data acquisition and computing layer is used to collect, process, calculate and store raw data, as well as collect and process a variety of perception data.

[0056] In some embodiments, the multiple sensing devices include: a first load sensor mounted on the inner wall of a wind turbine blade; a second load sensor mounted on a tower section; a nacelle-mounted laser wind measurement radar mounted on the top of the nacelle; a vibration pickup mounted on the tower section; a dynamic tilt monitoring sensor mounted on the top of the tower; and a blade acoustic wave pattern monitoring device mounted on the surface of the wind turbine blade. Optionally, in this embodiment of the present invention, the sensing data includes, but is not limited to, blade root load monitoring data, blade acoustic wave pattern monitoring data, tower load monitoring data, laser radar wind measurement data, tower tilt monitoring data, and whole-machine vibration modal monitoring data.

[0057] Specifically, blade root load monitoring data can be obtained by sensing a first load sensor (or multiple first load sensors) installed at a reasonable location on the root of the wind turbine blade. The first load sensor is fixed to the inner wall of the blade root. Optionally, blade root load monitoring data includes, but is not limited to, data on parameters such as blade flapping and pendulum vibration direction stress, strain, and bending moment. Blade soundprint monitoring data can be obtained by sensing a blade soundprint monitoring device (such as an intelligent sound acquisition device suitable for wind turbines) installed on the surface of the wind turbine blade. The blade soundprint monitoring device can collect the sound signals of the blade operation. Tower load monitoring data can be obtained by sensing a second load sensor (or multiple second load sensors) arranged at a reasonable cross-section of the tower. The second load sensor at each cross-section must simultaneously monitor strain in at least two directions. LiDAR wind measurement data can be obtained by sensing a nacelle-mounted laser wind measurement radar installed on the top of the nacelle. The nacelle-mounted laser wind measurement radar can monitor the actual wind conditions in front of the offshore wind turbine in real time. Tower inclination monitoring data can be obtained by sensing a dynamic inclination monitoring sensor installed on the top of the tower. Dynamic tilt monitoring sensors measure the tower's XY axis tilt angle and XY axis angular velocity relative to sea level. Vibration modal monitoring data for the entire tower can be obtained using multiple vibration pickups installed at appropriate locations across the tower. The lower frequency band limit of the pickups is no greater than 0.2 Hz, and the sampling frequency of the entire system is no less than 50 Hz, utilizing synchronous sampling technology.

[0058] The data acquisition and computing layer includes: a standardized data acquisition module, an edge computing module, a data storage module, a controller, and a field bus for connecting the modules; the standardized data acquisition module is used to collect and process a variety of sensory data in a standardized manner; the data storage module is used to store data; the controller is used to control and manage each module; the edge computing module is used to collect, calculate, and store the original data. Based on advanced sensor technology, the present invention adopts standardized data acquisition to build a flexible and elastic intelligent perception layer to realize the collection and edge computing of sensory data. For example, relevant advanced perception systems can be deployed on 5 typical units, including 2 nacelle-type laser wind measurement radars, and finally the modules are connected through a field bus to achieve efficient data transmission and communication.

[0059] In some embodiments, the standardized data acquisition module can provide data acquisition hardware equipment that meets industrial standards, including sensor interface modules, data conversion units, etc.; it can support plug-and-play modular functional design to facilitate rapid access to different types of sensors and devices; it can support standardized acquisition and processing of various sensory data, including but not limited to: environmental data, device status data, image and video data, etc.; it can support various sensor interfaces (including analog input, digital input, communication interfaces such as RS-485, CAN, etc.); provide standardized interface adapters to adapt to different types of sensors and data sources; realize real-time acquisition, conversion and preprocessing of sensor data; support real-time requirements for data acquisition, including data sampling rate, data accuracy, etc.; support industrial standard communication protocols (including Modbus TCP / RTU, OPC UA, Ethernet / IP, etc.), and support wireless AP standardized communication protocols when necessary; provide data upload and remote management functions, support network configuration and data transmission; provide modular hardware components, including data acquisition modules, data processing modules, communication modules, etc.

[0060] The edge computing module includes: edge node devices, which collect raw data; a data preprocessing module, which filters, reduces noise, removes outliers, and converts and standardizes the raw data; a monitoring and control module, which performs real-time control operations based on preset algorithms or rules and has the ability to trigger alarms and control device startup and shutdown; a local storage module, which stores raw data locally; an edge computing submodule, which performs end-to-end data analysis and computation; and a communication module, which uses network slicing technology to connect edge node devices to the cloud or other devices. Specifically, edge node devices collect raw data. Edge node devices include but are not limited to routers, switches, gateways, smart sensors, cameras, industrial controllers, and servers. The data preprocessing module performs preliminary filtering, noise reduction, and outlier removal on the collected raw data to improve data quality; it also converts and standardizes the data format for subsequent transmission and processing. The local storage module temporarily stores raw data locally to prevent data loss due to network failures or data transmission interruptions. The edge computing submodule can perform end-to-end data analysis and calculations using data aggregation or trend analysis, alleviating the computing pressure on central or station-side servers. The communication module enables communication and networking, communicating with upper-layer systems or cloud platforms via wired (including Ethernet, serial ports, fiber optics, etc.) or wireless (including WiFi, Bluetooth, cellular networks, etc.) methods to upload collected data. It supports multiple communication protocols (including Modbus, TCP / IP, MQTT, etc.) to ensure compatibility with different systems.

[0061] Furthermore, the edge computing module also includes: a model deployment and management module, a system self-diagnosis module, a security module, an authentication management module, and a remote management and configuration module. The model deployment and management module is based on the standardized model development and deployment framework for edge computing environments, offering flexible scalability and configuration capabilities. The system self-diagnosis module enables system self-diagnosis and self-recovery, monitoring its own operating status, including hardware status and network connectivity. In the event of a fault, it attempts automatic recovery or issues a fault alarm to facilitate timely maintenance. The security module encrypts collected data to ensure data security during transmission and storage. The authentication management module provides user authentication and permission management to prevent unauthorized access and manipulation. The remote management and configuration module supports remote management and configuration of the edge computing controller, including parameter settings, software updates, and task scheduling. The edge computing module is also adaptable to harsh environments, featuring features such as dust and water resistance, electromagnetic interference resistance, and salt spray resistance, enabling stable operation in harsh environments such as offshore wind power plants.

[0062] The station side includes: Zone 1 data management module, Zone 2 data management module and Zone 3 data management application module; Zone 1 data management module is used to access and manage perception data; Zone 2 data management module is used to cache perception data and manage perception data through gates; Zone 3 data management application module is used to manage and apply perception data and raw data.

[0063] Specifically, in some embodiments, the Zone 1 data management module is primarily used to access sensory data from various sources. Sensory data refers to data collected by various sensors (such as temperature sensors, humidity sensors, cameras, and sensors in the aforementioned sensor layer), which reflects the status of the station's internal or surrounding environment. The Zone 1 data management module is responsible for ensuring that this data is correctly received, initially processed (such as format conversion and data cleaning), and prepared for further analysis or use.

[0064] The Zone 2 data management module includes a sensor data cache module and a data penetration module. Since sensor data can come from multiple devices and be large in volume, a cache mechanism can be implemented to temporarily store this data to ensure system stability and responsiveness. This ensures that even in the event of a brief outage in the primary database or subsequent processing environment, important real-time data will not be lost. The data penetration module controls the process of transferring data from one security domain to another. Different application scenarios have different security requirements, and the data penetration module ensures that data is transmitted in accordance with established security policies and rules to prevent information leakage.

[0065] The three-zone data management application modules include: a data standardization module, a data storage module, a model management module, an inference platform, and a model computation module. Data from different sources often have different formats and standards. The data standardization module converts this heterogeneous data into a unified, standardized format to facilitate subsequent data processing and analysis. The data storage module is responsible for long-term storage of processed data, using various storage methods such as relational databases, NoSQL databases, and distributed file systems to meet different query and performance requirements. The model management module manages and maintains various models used for data analysis, including machine learning and deep learning models. It supports model version control and training status tracking. The inference platform performs operations such as prediction and classification on newly input data based on existing models. The inference platform is a key component for intelligent decision-making. The model computation module is responsible for executing model training tasks, adjusting model parameters based on historical data to improve model accuracy and efficiency. It may also support online learning, which means updating the model as new data is continuously received.

[0066] The entire station architecture design embodies a complete chain from data collection, preprocessing, storage, to analytical applications, aiming to build an efficient, secure, and scalable data processing and application platform. Such a platform plays a vital role in improving station operational efficiency, optimizing resource allocation, and enhancing safety.

[0067] The center side includes: digital twin simulation model, virtual perception module and intelligent diagnosis module; the digital twin simulation model is used to construct a digital twin model of the wind turbine by combining finite element analysis and data correction; the virtual perception module is used to access a variety of perception data, real-time operation data and equipment status data; the intelligent diagnosis module is used to build an equipment diagnosis model based on a variety of perception data, real-time operation data, equipment status data and equipment failure mechanism, and perform fault warning diagnosis and life prediction based on the equipment diagnosis model.

[0068] In some embodiments, the construction of the digital twin simulation model construction module adopts a combination of finite element analysis and data correction and is constructed on a Matlab or Simulink platform. Optionally, the digital twin simulation model includes: a wind speed model construction module, which is used to construct a model based on wind-related parameters to obtain a wind speed model; a blade model construction module, which is used to perform finite element analysis modeling based on blade parameters to obtain a blade model; a tower model construction module, which is used to perform finite element analysis modeling on tower parameters to obtain a load model; an electrical system model construction module, which is used to perform modeling based on equipment parameters to obtain an electrical system model and control strategy; a simulation model construction module, which is used to construct a model based on the wind speed model, blade model, tower model, and electrical system model and control strategy to obtain a digital twin model of the wind turbine.

[0069] Specifically, the wind speed model construction module obtains data such as wind speed, wind direction, turbulence intensity, vertical wind shear and horizontal wind shear through a nacelle-type laser wind measurement radar, and models the wind speed, wind direction, turbulence intensity, vertical wind shear and horizontal wind shear to obtain a wind speed model.

[0070] The blade model construction module uses the first load sensor to obtain blade flapping stress, swing arm stress, strain, and bending moment. Based on these parameters, the blade element momentum method is used to divide the blade into multiple aerodynamic characteristic regions for finite element analysis (FEM) modeling to obtain the blade model. This method involves first dividing the entire blade into multiple segments along its length based on blade design parameters (such as blade length, shape, and angle of attack distribution). These segments are referred to as "blade elements." For each blade element, the aerodynamic forces (lift and drag) at that location are calculated using Blade Element Momentum Theory (BEM). BEM assumes that each blade element operates independently and accounts for the influence of tip effect and induced velocity. By integrating the aerodynamic forces across all blade elements, the total aerodynamic force for the entire blade, as well as important parameters such as power output, can be obtained. After obtaining the aerodynamic data provided by BEM, the next step is to create a three-dimensional blade model in FEA software. This model should reflect the actual blade geometry and material properties in as much detail as possible. The aerodynamic forces calculated using BEM are applied as external loads to the FEA model. This step requires converting the aerodynamic forces from the BEM blade element distribution into a load distribution suitable for the FEA (Finite Element Analysis) model. Static or dynamic analysis is performed to assess the blade's mechanical behavior, including stress, strain, and displacement, under different operating conditions. Modal analysis can also be performed to investigate the blade's vibration characteristics. Based on the analysis results, the blade design is optimized to ensure it meets strength, stiffness, and fatigue life requirements. Combining BEM with FEA: BEM provides information on the blade's aerodynamics, while FEA focuses on the blade's structural response. This combination of the two can achieve a comprehensive and in-depth understanding of wind turbine blades. In practical applications, BEM is often used to first calculate the aerodynamic forces on the blade under specific wind speed conditions. These forces are then imported as input loads into the FEA model for structural analysis. To improve analysis accuracy, it is sometimes necessary to iteratively adjust parameters in the BEM model (such as the angle of attack distribution) until the FEA results match experimental data or results from other advanced simulation tools.

[0071] The tower model construction module obtains the axial force along the center line of the tower, the lateral force perpendicular to the center line of the tower, the rotational torque acting on the tower, the bending moment acting on the tower section, and the tower vibration frequency and amplitude based on the second load sensor. Based on the axial force, lateral force, rotational torque, bending moment, vibration frequency and amplitude, and using the blade element dynamics method, the blade is divided into multiple aerodynamic characteristic regions for finite element analysis modeling to obtain the tower model.

[0072] The electrical system model building module is built using Matlab or Simulink platform combined with calculation software FAST for blade speed, generator speed, generator power, pitch angle, and yaw to obtain the electrical system model and control strategy.

[0073] The simulation model building module combines the wind speed model, blade model, tower model, and electrical system model with the control strategy to build a digital twin simulation model of the wind turbine in Matlab or Simulink to obtain a digital twin model of the wind turbine. This digital twin model is the initial model, and data correction is required to obtain the final digital twin model (i.e., the target digital twin model). The specific process for data correction of the initial model is as follows:

[0074] The blade model and tower model are modified. The initial mechanism model of the wind turbine is established using the equipment attribute parameters provided by the wind turbine manufacturer. The output of the initial mechanism model is processed using the frequency response method. By comparing the theoretical response characteristics given by the wind turbine manufacturer with the model response characteristics, the parameters of the blade model and tower model are modified until the constraints converge.

[0075] The control system structure and parameters are modified. Based on the modified model, a controller is added, taking into account the influence coefficients of environmental factors on the wind turbine, to form a closed-loop control system for the wind turbine. Real-time operating data is collected as input, and a full-operating closed-loop simulation of the digital twin simulation model is performed to obtain the dynamic characteristics of blade speed, generator speed, generator power, pitch angle, and yaw. The dynamic characteristics are compared with the actual operating data and deviation analysis is performed. Based on the analysis results, the control structure and control parameters in the digital twin simulation model are iteratively adjusted to obtain the final digital twin simulation model.

[0076] In this embodiment, the control system structure and parameters need to be appropriately adjusted based on the existing wind turbine control system model, taking into account issues encountered during actual operation (such as insufficient performance and poor stability), as well as new requirements or goals (such as improving power generation efficiency and extending equipment life). This step involves the selection of control algorithms, controller design, and parameter tuning. Incorporating environmental factors: Wind turbine operation is affected by a variety of environmental factors, including wind speed, wind direction, temperature, and humidity. Therefore, based on the revised model, it is necessary to further consider the impact of these environmental factors on the wind turbine, quantify these impacts as influence coefficients, and incorporate them into the model. This makes the model more realistic and improves its predictive accuracy. Adding a controller to form a closed-loop control system: After completing the above steps, the designed controller is combined with the revised wind turbine model to form a closed-loop control system. Closed-loop control means that the system output is fed back to the input, and the control strategy is adjusted by comparing the difference between the expected value and the actual value, thereby achieving more precise control. Full-operation closed-loop simulation: Utilizing digital twin technology, a closed-loop simulation of the wind turbine under all operating conditions is performed based on real-time operational data. Full operating conditions refer to all possible operating conditions encountered by the wind turbine, including varying wind speeds and directions. This approach allows for a comprehensive assessment of the wind turbine's performance under various conditions. Dynamic characteristic comparison and deviation analysis: The simulated dynamic characteristics, such as blade speed, generator speed, generator power, pitch angle, and yaw, are compared with actual operating data to analyze the deviations between the two. Deviation analysis helps identify model issues, such as unreasonable model assumptions or inaccurate parameter settings. Iterative adjustment of control structures and control parameters: Based on the results of the deviation analysis, the control structure and control parameters in the digital twin simulation model are iteratively adjusted. This process may be repeated multiple times until the deviation between the model's predicted results and the actual operating data falls within an acceptable range. Obtaining the final digital twin simulation model: After multiple rounds of iterative adjustments, when the model accurately reflects the actual operating conditions of the wind turbine, the final digital twin simulation model is obtained. This model can not only be used for design optimization of wind turbines, but also for fault diagnosis, performance prediction and other aspects.

[0077] The key to this entire process is effectively combining theoretical knowledge with practical experience to continuously optimize the model so that it reflects the behavior of wind turbines as realistically as possible. Furthermore, advanced methods such as machine learning can be used to assist in model building and optimization, further improving the accuracy and practicality of digital twin models.

[0078] In some embodiments, the intelligent diagnosis module includes: an early warning model construction module, which is used to construct a model based on the intelligent perception model to obtain an early warning model; a diagnosis model construction module, which is used to construct a model based on multiple perception data, real-time operation data, equipment status data and equipment failure mechanism to obtain an equipment diagnosis model; a fault early warning diagnosis module, which is used to perform fault early warning diagnosis and life prediction based on the early warning model and / or equipment diagnosis model.

[0079] Specifically, the early warning model construction module, based on intelligent perception models and data analysis algorithms, enables early warning and accurate diagnosis of wind turbine faults. The system should be able to predict the type of fault that may occur based on the changing trends and characteristic information of monitoring data, and issue early warning signals. The diagnostic model construction module, using collected perception data, real-time operating data, and equipment status data, constructs diagnostic models tailored to specific equipment failure mechanisms. The fault early warning and diagnosis module, based on the early warning and / or diagnostic models, rapidly locates the fault location and analyzes the cause. By learning and analyzing historical fault data, it builds a fault diagnosis knowledge base, continuously improving the accuracy and efficiency of fault diagnosis. It also provides detailed fault diagnosis reports. These reports include a description of the fault, the scope of impact, and recommended repair measures, providing strong technical support for maintenance personnel. The virtual perception model construction constructs a data model based on the environment, operating conditions, and perceived loads, forming a standardized model for the pilot turbine model. This supports load inversion and load linkage for the fleet, enabling accurate simulation.

[0080] Furthermore, the digital twin intelligent perception system for wind turbines also includes a data management service unit for the terminal, station, and center sides. This data management service unit integrates IoT configuration, data collection, and data storage.

[0081] Optionally, in some embodiments, the data management service unit includes: an end-side IoT layer; the end-side IoT layer includes: a data processing module, the data processing module is used to process structured data, semi-structured data or unstructured data collected on the end side (including but not limited to data cleaning, denoising, format conversion, removal of abnormal data and noise interference). A data coding model construction module, the data coding model construction module is used to build a standardized data coding module. A user authority configuration module, the user authority configuration module is used to support the authority configuration of users on the station side and the center side. A data storage policy configuration module, the data storage policy configuration module is used to support data storage policy configuration, including data storage duration, data storage structure, data storage type, etc. under different management architectures.

[0082] Furthermore, the end-side IoT layer also includes: a physical model definition and mapping module, which is used to customize the digital representation of the devices in the end-side IoT layer and build a physical model based on the digital representation, and map the physical properties and functions of the device to the physical model. A physical model version update module, which is used to incrementally update the physical model based on a preset update strategy after detecting a physical model version update. A physical model sharing and collaboration module, which is used to support the sharing and collaboration of physical models. A visualization module, which is used to provide a graphical interface to support the configuration and expansion of new devices and the definition of device properties and behaviors.

[0083] Based on the needs of perception data management, the present invention constructs a data management service that integrates IoT configuration, data collection, data storage, and data services: it supports all software functions required by the end-side IoT layer, including object model definition mapping, IoT protocol configuration (supporting common industrial standardized protocols, including OPCUA, Modbus, MQTT, etc.), version management, user management, etc.; it supports open source IoT protocol management and configuration; the data management service function supports data interface service encapsulation modes including RESTful API, and supports user interface encapsulation and publishing; it supports user applications on the site and center sides, and provides convenient user authority configuration; it supports the deployment and upgrade of data coding models, and realizes standardized storage based on data coding models before data collection is stored in the database; it supports the configuration of data storage strategies, including functional configurations such as data storage duration, data storage structure, and data storage type under different management architectures; it supports common data governance methods, and provides common data cleaning, data preprocessing, data reduction, and data quality evaluation method configuration according to data characteristics, including diagnosis of data anomaly problems such as constant value data, abnormal data, over-limit data, and null value data, and quality evaluation methods such as data integrity rate and data availability rate. The data storage solution provides multimodal data storage based on the characteristics of perception data, supports structured, semi-structured, and unstructured data storage, selects databases based on different types of data, and forms a standardized data storage solution.

[0084] In the embodiments of this application, a customized offshore wind power intelligent perception system integrating edge computing, data management, and digital twin applications is developed through standardized data acquisition technology, sensing technology, and Internet of Things technology. The system includes research on various advanced sensing technologies, data acquisition technology based on standardized data acquisition modules that can be expanded, and edge computing technology. In addition, the system can also complete multi-source data fusion and data layered storage on the site side, complete data management and application based on IoT data standardization, and develop and deploy virtual perception, intelligent diagnosis and warning, digital twin simulation models, and other functions on the center side. These functions can be flexibly adjusted according to the system deployment location.

[0085] refer to Figure 2 The present invention also provides a digital twin intelligent perception method for wind turbines. The digital twin intelligent perception method for wind turbines is applied to the aforementioned digital twin intelligent perception system for wind turbines.

[0086] like Figure 2 As shown, in a preferred embodiment, the digital twin intelligent perception method applied to a wind turbine generator system includes the following steps:

[0087] Step S201: Acquire terminal-side perception data and device parameters.

[0088] Specifically, blade parameters (such as the aforementioned blade flapping direction stress, swing arm direction stress, strain, bending moment and other parameters), tower parameters (such as the aforementioned axial force, lateral force, rotational torque, bending moment, vibration frequency and amplitude), wind-related parameters (such as the aforementioned wind speed, wind direction, turbulence intensity, vertical wind shear and horizontal wind shear, etc.), and related equipment parameters (such as blade speed, generator speed, generator power, pitch angle, yaw, etc.) can be obtained based on the perception data obtained by the data perception layer.

[0089] Step S202: Perform finite element analysis modeling based on the sensing data to obtain a wind speed model, a blade model, and a tower model.

[0090] Step S203: Modeling is performed based on the equipment parameters to obtain an electrical system model and control strategy.

[0091] Step S204: construct a model by combining the wind speed model, blade model, tower model, electrical system model and control strategy to obtain a digital twin model of the wind turbine.

[0092] Step S205: perform data correction on the digital twin model of the wind turbine to obtain the target digital twin model.

[0093] Step S206: Communicate data between the target digital twin model and the cloud platform.

[0094] Specifically, a cloud platform, server, operating system, and database are built, and the local IDE calls the communication space to realize data exchange between the digital twin simulation model and the cloud platform.

[0095] Step S207: After data communication, fault warning diagnosis and life prediction are performed based on the constructed equipment diagnosis model.

[0096] Specifically, after data intercommunication, the cloud platform will be redeveloped to realize the functions of operation status detection, visualization, fault warning and diagnosis, and service life prediction.

[0097] In addition, an electronic device of the present invention includes a memory and a processor; the memory is used to store a computer program; the processor is used to execute the computer program to implement a digital twin intelligent perception method for a wind turbine as described in any one of the above. Specifically, according to an embodiment of the present invention, the process described with reference to the flowchart above can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed by an electronic device and, when executed, performs the above functions defined in the method of the embodiment of the present invention. The electronic device in the present invention may be a terminal such as a notebook, desktop, tablet computer, smart phone, or a similar computing device, or may be a server. Taking running on a mobile terminal as an example, such as Figure 3 As shown, the mobile terminal may include one or more ( Figure 1 Only one is shown) a processor 302 (the processor 302 may include a processing device such as a microprocessor MCU or a programmable logic device FPGA) and a memory 304 for storing data. The mobile terminal may also include a transmission device 306 and an input / output device 308 for communication functions. It will be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the mobile terminal. Figure 1 More or fewer components than shown, or with Figure 1 Different configurations shown.

[0098] The memory 304 can be used to store computer programs, such as software programs and modules of application software, such as a computer program corresponding to a data information security protection method in an embodiment of the present invention. The processor 302 executes the computer program stored in the memory 304 to execute various functional applications and data processing, thereby implementing the above-mentioned method. The memory 304 may include a high-speed random access memory and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 304 may further include a memory remotely located relative to the processor 302, and these remote memories may be connected to the mobile terminal via a network. Examples of the above-mentioned network include the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0099] Transmission device 306 is used to receive or transmit data via a network. A specific example of the aforementioned network may include a wireless network provided by the mobile terminal's communications provider. In one embodiment, transmission device 306 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, transmission device 306 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0100] In addition, the present invention provides a storage medium having a computer program stored thereon, which, when executed by a processor, implements any of the above-mentioned digital twin intelligent perception methods for wind turbines. Specifically, it should be noted that the storage medium of the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. Computer-readable storage media may be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or components, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present invention, a computer-readable signal medium may include a data signal transmitted in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wires, optical cables, RF (radio frequency), or any suitable combination thereof.

[0101] The computer-readable medium may be included in the electronic device, or may exist independently without being incorporated into the electronic device.

[0102] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0103] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the above description has generally described the components and steps of each example according to their functions. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0104] The steps of the methods or algorithms described in conjunction with the embodiments disclosed herein may be implemented directly using hardware, a software module executed by a processor, or a combination of the two. The software module may be placed in a random access memory (RAM), internal memory, read-only memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0105] The above embodiments are intended only to illustrate the technical concepts and features of the present invention. Their purpose is to enable those skilled in the art to understand the present invention and implement it accordingly. They are not intended to limit the scope of protection of the present invention. All equivalent variations and modifications within the scope of the claims of the present invention are intended to be covered by the claims of the present invention.

Claims

1. A digital twin intelligent perception system applied to wind turbines, characterized in that: include: Terminal side, station side and center side; The end side includes: a data perception layer and a data acquisition and calculation layer; the data perception layer includes multiple sensor devices, which are used to acquire and monitor multiple sensor data; the data acquisition and calculation layer is used to acquire, process, calculate and store raw data, and to acquire and process the sensor data; The station side includes: a zone 1 data management module, a zone 2 data management module, and a zone 3 data management application module; the zone 1 data management module is used to access the perception data and manage the perception data; the zone 2 data management module is used to cache the perception data and perform gate management on the perception data; the zone 3 data management application module is used to manage and apply the perception data and the original data; The center side includes: a digital twin simulation model construction module, a virtual perception module and an intelligent diagnosis module; the digital twin simulation model construction module is used to construct a digital twin model of a wind turbine by combining finite element analysis and data correction; the virtual perception module is used to access the multiple perception data, real-time operation data and equipment status data; the intelligent diagnosis module is used to construct an equipment diagnosis model based on the multiple perception data, the real-time operation data, the equipment status data and the equipment failure mechanism, and perform fault warning diagnosis and life prediction based on the equipment diagnosis model.

2. The digital twin intelligent perception system for wind turbines according to claim 1 is characterized in that: The multiple sensing devices include: a first load sensor installed on the inner wall of the wind turbine blade, a second load sensor installed on the tower section, a nacelle-type laser wind measurement radar installed on the top of the nacelle, a vibration pickup installed on the tower section, a dynamic tilt monitoring sensor installed on the top of the tower, and a blade soundprint monitoring device installed on the surface of the wind turbine blade; The data acquisition and computing layer includes: a standardized data acquisition module, an edge computing module, a data storage module, a controller, and a field bus for connecting the modules; the standardized data acquisition module is used to perform standardized acquisition and processing of the various perception data; the data storage module is used to store data; the controller is used to control and manage each module; the edge computing module is used to collect, calculate and store the original data.

3. The digital twin intelligent perception system for wind turbines according to claim 2 is characterized in that: The edge computing module includes: An edge node device, configured to collect the raw data; A data preprocessing module, which is used to filter, reduce noise and remove outliers from the raw data, and perform data format conversion and standardization; A local storage module, wherein the local storage module is used to locally store the original data; An edge computing submodule, configured to perform data analysis and calculations based on the end side; A communication module, which uses network slicing technology to provide a connection between the edge node device and the cloud or other devices.

4. The digital twin intelligent perception system for wind turbines according to any one of claims 1 to 3, characterized in that: Also includes: A data management service unit applied to the terminal side, the station side, and the center side; The data management service unit includes: a terminal-side IoT layer; The end-side IoT layer includes: A data processing module, configured to process structured data, semi-structured data, or unstructured data collected by the terminal side; A data coding model construction module, wherein the data coding model construction module is used to construct a standardized data coding module; A user authority configuration module, which is used to support the station-side and center-side users in authority configuration; A data storage policy configuration module is used to support data storage policy configuration.

5. The digital twin intelligent perception system for wind turbines according to claim 4 is characterized in that: The end-side IoT layer further includes: A physical model definition and mapping module, configured to create a customized digital representation of the device in the end-side IoT layer, construct a physical model based on the digital representation, and map the physical properties and functions of the device to the physical model; A physical model version update module, configured to incrementally update the physical model based on a preset update strategy after detecting a physical model version update; A physical model sharing and collaboration module, which is used to support sharing and collaboration of physical models; A visualization module is used to provide a graphical interface.

6. The digital twin intelligent perception system for wind turbines according to claim 1 is characterized in that: The digital twin simulation model construction module includes: A wind speed model construction module, wherein the wind speed model construction module is used to construct a model based on wind-related parameters to obtain a wind speed model; A blade model building module, wherein the blade model building module is used to perform finite element analysis modeling based on blade parameters to obtain a blade model; A tower model building module, which is used to perform finite element analysis modeling on tower parameters to obtain a load model; An electrical system model building module, wherein the electrical system model building module is used to perform model building based on device parameters to obtain an electrical system model and control strategy; A simulation model construction module is used to construct a model based on the wind speed model, the blade model, the tower model, and the electrical system model and control strategy to obtain a digital twin model of the wind turbine.

7. The digital twin intelligent perception system for wind turbines according to claim 1 is characterized in that: The intelligent diagnosis module includes: An early warning model construction module is used to construct a model based on the intelligent perception model to obtain an early warning model; a diagnostic model building module, configured to build a model based on the multiple sensory data, the real-time operation data, the device status data, and the device failure mechanism to obtain the device diagnostic model; A fault warning diagnosis module is used to perform fault warning diagnosis and life prediction based on the warning model and / or the equipment diagnosis model.

8. A digital twin intelligent perception method for a wind turbine generator system, applied to the digital twin intelligent perception system for a wind turbine generator system according to any one of claims 1 to 7, characterized in that: The following steps are involved: Obtaining device-side perception data and device parameters; Perform finite element analysis modeling based on the sensing data to obtain a wind speed model, a blade model, and a tower model; Modeling is performed based on the equipment parameters to obtain an electrical system model and control strategy; Combining the wind speed model, the blade model, the tower model, and the electrical system model with the control strategy to construct a model to obtain a digital twin model of the wind turbine; Performing data correction on the digital twin model of the wind turbine generator set to obtain a target digital twin model; Interoperate data between the digital twin model of the target and the cloud platform; After data intercommunication, fault warning diagnosis and life prediction are performed based on the constructed equipment diagnosis model.

9. A storage medium, characterized in that: The storage medium stores a computer program, which is suitable for being loaded by a processor to execute the steps of the digital twin intelligent perception method applied to a wind turbine as claimed in claim 8.

10. An electronic device, characterized in that: It includes a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the steps of the digital twin intelligent perception method applied to a wind turbine as claimed in claim 8 by calling the computer program stored in the memory.

Images