Offshore wind plant monitoring system based on digital twin and grid-connected architecture and design method thereof

Abstract

The invention discloses an offshore wind plant monitoring system based on a digital twin and grid-connected architecture and a design method thereof. The system comprises a field layer, an intermediate network communication layer and a station control and centralized control layer, the field layer comprises a fan monitoring subsystem, a booster station monitoring subsystem, a video monitoring subsystem, an environment monitoring subsystem, a power prediction subsystem and a submarine cable fault monitoring subsystem; the intermediate network communication layer comprises an SDH communication node and a longitudinal encryption device; the station control and centralized control layer comprises an integrated intelligent monitoring management platform and a digital twinborn model, the digital twinborn model is constructed based on collected data of the field layer and covers multi-dimensional information and functional sub-models of the wind power plant, and the integrated intelligent monitoring management platform stores a functional component library and can call the functional component library to realize monitoring and control functions; and the system can be tested and optimized. The system has the advantages of being high in integration level, intelligent and efficient in operation and maintenance, adaptive to different grid-connected frameworks, capable of fusing static design and dynamic operation and the like.

Description

Technical Field

[0001] This invention relates to the technical field of offshore wind farm monitoring, and in particular to an offshore wind farm monitoring system and its design method based on digital twin and grid-connected architecture. Background Technology

[0002] As the global energy structure shifts towards cleaner and lower-carbon energy, offshore wind farms, with their abundant resources, high power generation efficiency, and lack of land-based resource occupation, have become an important development direction in the new energy field. However, offshore wind farms are located in complex and harsh environments, with equipment distributed widely, and the requirements for grid connection are becoming increasingly stringent. Traditional monitoring and operation and maintenance management methods are no longer sufficient to meet the operational needs of large-scale, distributed offshore wind farms, and existing technologies face many problems that urgently need to be solved.

[0003] In terms of system integration, the existing monitoring system for offshore wind farms consists of multiple independent subsystems, such as the turbine monitoring subsystem, the substation monitoring subsystem, the video and environmental monitoring subsystem, the wind power prediction subsystem, and the submarine cable fault monitoring subsystem. These subsystems are typically developed by different manufacturers, using their own independent hardware, software platforms, and data formats, lacking a unified integration platform. For example, data from the turbine monitoring subsystem is mostly stored on local servers, while data from the substation monitoring subsystem is uploaded to a cloud database. Incompatible data access interfaces and communication protocols prevent efficient data sharing and collaborative analysis between the subsystems. This "information silo" phenomenon not only increases the costs of system development, deployment, and maintenance but also severely restricts the improvement of the overall operating efficiency of the wind farm, making it difficult to achieve a comprehensive understanding of the wind farm's operating status.

[0004] In terms of operation and maintenance management, current technologies still heavily rely on manual operation. Offshore wind farms are geographically remote, requiring maintenance personnel to travel by boat or helicopter to the site to conduct equipment inspections and troubleshooting. This is not only difficult and costly, but also exposes them to safety risks such as rough seas and extreme weather. Furthermore, the lack of intelligent and automated operation and maintenance methods prevents predictive maintenance of equipment status, often resulting in repairs only after equipment failure. This leads to long downtimes and significant power generation losses, making it difficult to meet the "unmanned, onshore centralized control" operation and maintenance goals of offshore wind farms.

[0005] Regarding grid connection adaptability, existing monitoring systems lack flexible adjustment capabilities, making it difficult to adapt to grid connection architectures in different regions and with varying grid requirements. When grid load fluctuates or grid dispatch instructions change, existing systems cannot quickly adjust the wind farm's output control strategy, leading to low power transmission efficiency and potentially causing grid voltage fluctuations and frequency instability. Furthermore, existing systems cannot effectively support advanced application functions such as Automatic Generation Control (AGC) and Automatic Voltage Control (AVC), limiting the deep integration of wind farms with the main grid and hindering the optimization of overall wind farm output and the safe and stable operation of the grid.

[0006] In terms of design and operation coordination, existing technologies lack an effective coupling mechanism between static design and dynamic operation scheduling. System design phases often rely on theoretical models and ideal operating conditions for parameter configuration. However, in actual operation, offshore wind farms are affected by environmental factors such as wind speed, waves, and temperature, as well as equipment aging and component wear, leading to significant deviations between the design and actual operating conditions. Due to the lack of real-time data feedback and iterative optimization mechanisms, designers cannot obtain operational data in a timely manner to correct design parameters, causing the system to operate in a suboptimal state for extended periods, making it difficult to guarantee operational efficiency and reliability.

[0007] Therefore, there is an urgent need for a highly integrated monitoring system and its design method that is intelligent and efficient in operation and maintenance, adaptable to different grid connection architectures, and can integrate static design and dynamic operation, in order to solve the shortcomings of existing technologies and promote the upgrading of offshore wind farm monitoring and operation and maintenance management technologies. Summary of the Invention

[0008] The purpose of this invention is to overcome the shortcomings of the prior art and provide an offshore wind farm monitoring system based on digital twin and grid-connected architecture. This system has the advantages of high integration, intelligent and efficient operation and maintenance, adaptability to different grid-connected architectures, and the ability to integrate static design and dynamic operation.

[0009] To achieve the above objectives, the technical solution provided by this invention is as follows: The offshore wind farm monitoring system based on digital twin and grid-connected architecture includes a field layer, an intermediate network communication layer, and a station control and centralized control layer. The field layer includes a wind turbine monitoring subsystem, a booster station monitoring subsystem, a video monitoring subsystem, an environmental monitoring subsystem, a power prediction subsystem, and a submarine cable fault monitoring subsystem. Each subsystem is equipped with a standardized interface for collecting real-time data from the wind farm and transmitting it to the intermediate network communication layer. The intermediate network communication layer includes an SDH communication node and a vertical encryption device. The SDH communication node is used to receive data transmitted from the field layer, and the vertical encryption device is used to ensure data transmission security. The intermediate network communication layer also preprocesses the collected data. The station control and centralized control layer includes an integrated intelligent monitoring and management platform and a digital twin model. The digital twin model is built based on data collected from the field layer and covers multi-dimensional information and functional sub-models of the wind farm. The integrated intelligent monitoring and management platform stores a functional component library, which can call the functional component library to realize monitoring and control functions, and can test and optimize the system.

[0010] Furthermore, to achieve the above objectives, the present invention also provides a design method for the above-mentioned offshore wind farm monitoring system based on digital twin and grid-connected architecture, comprising: Data collection and integration: The offshore wind farm site layer deploys wind turbine monitoring subsystems, booster station monitoring subsystems, video monitoring subsystems, environmental monitoring subsystems, power prediction subsystems, and submarine cable fault monitoring subsystems. Each subsystem transmits real-time data to the SDH communication node in the intermediate network communication layer via a 35kV network, using standardized interfaces and communication protocols. Vertical encryption devices are used to ensure data transmission security. The collected data is formatted and preprocessed in the intermediate network communication layer to obtain standardized data. Model building: Based on digital twin technology and combined with the obtained standardized data, a digital twin model of an integrated digital twin monitoring system is constructed at the station control and centralized control layers. The digital twin model covers the wind turbine operating status of the wind farm, the electrical parameters of the substation, and environmental conditions, and includes sub-models for fault diagnosis and power prediction optimization. The digital twin model is trained using near-physical simulation technology and soft controller technology to make the model behavior match the physical system. System integration and adaptation: The digital twin system is integrated with the power system grid architecture, and digital twin subsystems are established on land and at sea respectively. Data interaction between subsystems is realized through SDH network. The functions of each subsystem mentioned in data acquisition and integration are modularly defined and encapsulated into a functional component library. Combined with soft controller technology, the monitoring subsystems work collaboratively, and the subsystems are seamlessly connected to the integrated intelligent monitoring and management platform of station control and centralized control layer. The digital twin model is the foundation of the digital twin system. Functionality and Application: The integrated intelligent monitoring and management platform calls upon the functional component library to monitor wind turbine speed, power, and temperature parameters in real time, view on-site videos of wind farms, and acquire meteorological and marine environmental data; it also remotely and intelligently controls equipment through soft controller technology, adjusts wind turbine operating parameters based on environmental data, and locates submarine cable faults based on the submarine cable fault monitoring subsystem. System testing and optimization: The test included assessing the accuracy, completeness, and timeliness of data acquisition from each subsystem at the data acquisition terminal; testing the stability and transmission efficiency of the communication link in the intermediate network communication layer; and testing the monitoring, analysis, and control functions of the integrated intelligent monitoring and management platform at the station control and centralized control layers. Based on the test results, the system parameters were adjusted, the model algorithm was optimized, and the user interface was improved, ultimately resulting in an offshore wind farm monitoring system based on digital twin and grid-connected architecture.

[0011] Furthermore, the real-time data includes wind turbine operating status data, substation electrical data, video data, environmental data, power prediction data, and submarine cable status data; The intermediate network communication layer preprocesses the collected data, including: Data cleaning: Remove abnormal data caused by sensor malfunctions or communication interference; Data completion: For data loss caused by brief communication interruptions, interpolation is used to complete the data. Standardized format: Heterogeneous data from different subsystems are converted into a standardized format and stored in a unified database, providing high-quality data support for subsequent model building and functional applications.

[0012] Furthermore, constructing a digital twin model includes: Build a framework for a digital twin model; Construct functional sub-models within the framework of the digital twin model; Training and calibration.

[0013] Furthermore, a framework for building a digital twin model is established, including: At the station control and centralized control layer, based on preprocessed standardized data and combined with the Unity and Digital Twin Hub digital twin platforms, a digital twin model is constructed. This model covers three core dimensions: Geometric Dimensions: Reconstructing the geographical layout and three-dimensional structure of wind farm equipment; the geographical layout includes the location of wind turbines, the coordinates of substations, and the route of submarine cables; the three-dimensional structure of equipment includes detailed geometric models of wind turbine blades, generators, and transformers. Physical dimension: Integrating the physical properties and operating laws of the equipment to achieve physical simulation of the equipment's operating state; among which, the physical properties of the equipment include material parameters, electrical characteristics, and mechanical properties; the operating laws include the power curve of the wind turbine and the loss model of the transformer; Information dimension: Real-time data, historical operation data, and fault record information collected by various subsystems during data acquisition and integration are used to form the data brain of the model.

[0014] Furthermore, the functional sub-models built within the digital twin model framework include: Fault diagnosis sub-model: Based on equipment vibration, temperature and current data, neural network and support vector machine algorithms are used to realize real-time diagnosis and early warning of wind turbine gearbox faults, substation switch faults and submarine cable insulation faults; Power prediction optimization sub-model: Combining real-time environmental data and historical power generation data, the power prediction algorithm is optimized to improve the accuracy of power prediction; real-time environmental data includes wind speed and wind direction. Life Prediction Sub-model: Based on equipment runtime, load changes, and maintenance record data, a remaining life prediction algorithm is used to predict the remaining service life of critical equipment, providing a basis for predictive maintenance.

[0015] Furthermore, system integration and adaptation include: Deeply integrate digital twin systems with the power system grid connection architecture: 1) Subsystem deployment: Digital twin subsystems are established in the onshore control center and the offshore wind farm respectively. The digital twin subsystem of the onshore control center focuses on operation and maintenance management and grid dispatch interaction, while the digital twin subsystem of the offshore wind farm focuses on real-time monitoring of field equipment. 2) Data Interaction: By optimizing data transmission bandwidth and routing configuration through the SDH network, and adapting to the data transmission rate and format requirements of different subsystems, real-time data interaction is achieved between the digital twin subsystem of the onshore control center and the digital twin subsystem of the offshore wind farm, ensuring that the data transmission latency is less than 100ms and the packet loss rate is less than 0.1%. Functional component integration: The functions of each monitoring subsystem in data acquisition and integration are modularized and encapsulated into a reusable functional component library. The component library includes wind turbine monitoring components, substation control components, video surveillance components, environmental monitoring subsystems, and submarine cable fault monitoring components. The functional component library is connected to the integrated intelligent monitoring and management platform of the station control and centralized control layers through standardized interfaces to achieve plug-and-play functionality for each component. The component collaborative control logic is written in conjunction with software controller technology to ensure that the wind turbine monitoring components, substation control components, video surveillance components, environmental monitoring subsystems, and submarine cable fault monitoring components work collaboratively. Compatibility and Adaptation: To meet the grid connection requirements of different regional power grids, an adaptation module is set up in the integrated intelligent monitoring and management platform to support flexible configuration of system parameters.

[0016] Furthermore, the implementation and application of functions include: Real-time panoramic monitoring: 1) Equipment monitoring: The fan speed, power and temperature parameters are displayed in real time through the fan monitoring component, and the bus voltage, current and switch status electrical data are displayed through the booster station control component. Detailed parameters and historical curves can be viewed by clicking on the equipment model. 2) Environmental monitoring: Through environmental monitoring components and video monitoring components, the platform interface displays real-time environmental data such as wind speed, wind direction, and wave height, as well as on-site video footage of the wind farm, supporting video playback and abnormal behavior recognition; 3) Fault monitoring: The fault diagnosis sub-model monitors the fault status of the equipment in real time. When a fault is detected, the platform automatically pops up an alarm window, showing the location of the faulty equipment, the fault type, and the fault level, and pushes it to the mobile APP of the operation and maintenance personnel. Remote intelligent control: 1) Output control: Receive AGC commands from the power grid dispatching agency and automatically adjust the wind turbine output through soft controller technology to ensure that the deviation between the total wind farm output and the dispatch command is less than 2%; according to voltage control requirements, automatically adjust the tap changer of the step-up substation through the AVC function to maintain the bus voltage stable within the allowable range; 2) Equipment control: Supports remote control of wind turbine start-up and shutdown, blade angle adjustment, and booster station switch operation. Operation commands are transmitted to field equipment through encrypted communication links to ensure the security and reliability of control commands; 3) Fault handling: When the submarine cable fault monitoring subsystem detects a submarine cable fault, the platform automatically generates a fault handling plan, including fault location, impact range analysis, and backup power switching instructions. Maintenance personnel can confirm and execute the plan with one click, shortening the fault handling time. Intelligent operation and maintenance management: 1) Predictive maintenance: Based on the life prediction sub-model, the platform automatically generates equipment maintenance plans and pushes maintenance reminders; combined with equipment operating status data, it provides early warnings of potential faults to avoid sudden downtime; 2) Data statistical analysis: The platform automatically calculates wind farm power generation, equipment failure rate, and operation and maintenance cost data, and generates daily, weekly, and monthly reports, which can be displayed in chart form to provide data support for operational decision-making; 3) Unmanned operation support: Operation and maintenance personnel can complete the comprehensive monitoring and management of the wind farm from the onshore control center, and only send personnel to the site when the equipment needs on-site maintenance, reducing operation and maintenance costs and safety risks.

[0017] Furthermore, system testing includes: 1) Data acquisition test: Check the accuracy, completeness and timeliness of data acquisition in each subsystem, and replace or optimize any sensors or communication links that do not meet the requirements; 2) Network performance testing: Test the transmission bandwidth, stability, and anti-interference capability of the intermediate network communication layer SDH network, simulate a strong electromagnetic interference environment at sea, and ensure that the data transmission packet loss rate is less than 0.1%; 3) Functional testing: Test the platform's real-time monitoring, remote control, fault diagnosis, AGC / AVC and other functions to verify the correctness and stability of the functions; Adaptability testing: Simulate different grid connection architecture requirements to test the flexibility and compatibility of system parameter configuration, ensuring that the system can quickly adapt to different grid requirements.

[0018] Furthermore, during system optimization, the system is iteratively optimized based on test results and actual operational feedback, including: 1) Parameter optimization: Adjust the parameters of the digital twin model and control parameters to improve the simulation accuracy and control effect of the model; the parameters of the digital twin model include the coefficients of the wind turbine power curve; the control parameters include the AGC response speed; 2) Algorithm optimization: Optimize the fault diagnosis algorithm and power prediction algorithm to improve the accuracy of fault diagnosis and the precision of power prediction; 3) Interface optimization: Based on the operating habits of maintenance personnel, optimize the platform user interface, simplify the operation process, and improve maintenance efficiency; 4) Functionality Improvement: Add new functions based on user needs to continuously improve the system's usability and intelligence.

[0019] Compared with existing technologies, the principles and advantages of this technical solution are as follows: 1. Improve system integration and reduce costs: By integrating multiple subsystems such as wind turbine monitoring and substation monitoring into an integrated digital twin platform, "information silos" are broken down, unified data management and sharing are achieved, and system development, deployment and maintenance costs are reduced. Practical application verification shows that system integration costs are reduced by more than 30% and maintenance costs are reduced by more than 25%.

[0020] 2. Enhance grid compatibility and improve flexibility: Adopting modular design and functional component encapsulation, it supports flexible system configuration according to different grid connection architecture requirements, adapts to the voltage level, dispatching protocol and control requirements of different regional power grids, shortens the system development cycle by more than 40%, and can quickly respond to changes in grid connection requirements.

[0021] 3. Achieve integration of design and operation to optimize system performance: Through a coupled model of static design and dynamic operation, combined with real-time data feedback, iterative optimization is achieved, so that the system is in the optimal operating state for a long time, improving the power generation efficiency of wind farms by 5%-8% and reducing equipment failure rate by 15%-20%.

[0022] 4. Promote intelligent operation and maintenance to reduce risks: realize unmanned operation of offshore wind farms and centralized control with fewer personnel on land. Operation and maintenance personnel do not need to frequently go to the offshore site, reducing operation and maintenance costs and safety risks. The workload of operation and maintenance personnel is reduced by more than 60%, and the fault handling time is shortened by more than 50%.

[0023] 5. Supports advanced application functions and ensures grid stability: Through AGC and AVC functions, the wind farm and the grid can be coordinated and dispatched. The deviation between the total output of the wind farm and the dispatch command is less than 2%, and the bus voltage control accuracy is improved to ±1%, ensuring the safe and stable operation of the grid and improving the grid friendliness of the wind farm. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the services required in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart illustrating the design method of the offshore wind farm monitoring system based on digital twin and grid-connected architecture according to the present invention. Detailed Implementation

[0026] The present invention will be further described below with reference to specific embodiments: The offshore wind farm monitoring system based on digital twin and grid-connected architecture described in this embodiment includes a field layer, an intermediate network communication layer, and a station control and centralized control layer.

[0027] The field layer includes a wind turbine monitoring subsystem, a booster station monitoring subsystem, a video monitoring subsystem, an environmental monitoring subsystem, a power prediction subsystem, and a submarine cable fault monitoring subsystem. Each subsystem is equipped with a standardized interface for collecting real-time data from the wind farm and transmitting it to the intermediate network communication layer. The intermediate network communication layer includes SDH (Synchronous Digital Hierarchy) communication nodes and vertical encryption devices. The SDH communication nodes are used to receive data transmitted from the field layer, and the vertical encryption devices are used to ensure data transmission security. The intermediate network communication layer also preprocesses the collected data. The station control and centralized control layer includes an integrated intelligent monitoring and management platform and a digital twin model. The digital twin model is built based on data collected from the field layer and covers multi-dimensional information and functional sub-models of the wind farm. The integrated intelligent monitoring and management platform stores a functional component library, which can call the functional component library to realize monitoring and control functions, and can test and optimize the system.

[0028] like Figure 1 As shown, the design method of an offshore wind farm monitoring system based on digital twin and grid-connected architecture includes the following steps: Data collection and integration: At the offshore wind farm site layer, a wind turbine monitoring subsystem, a booster station monitoring subsystem, a video monitoring subsystem, an environmental monitoring subsystem, a power prediction subsystem, and a submarine cable fault monitoring subsystem are deployed. Each subsystem transmits real-time data to the SDH communication node in the intermediate network communication layer via a 35kV network, using standardized interfaces and communication protocols such as IEC 61850 and Modbus. Vertical encryption devices are used to ensure data transmission security. At the intermediate network communication layer, the collected data undergoes format unification and preprocessing to obtain standardized data. Model building: Based on digital twin technology and combined with the obtained standardized data, a digital twin model of an integrated digital twin monitoring system is constructed at the station control and centralized control layers. The digital twin model covers the wind turbine operating status of the wind farm, the electrical parameters of the substation, and environmental conditions, and includes sub-models for fault diagnosis and power prediction optimization. The digital twin model is trained using near-physical simulation technology and soft controller technology to make the model behavior match the physical system. System integration and adaptation: The digital twin system is integrated with the power system grid architecture, and digital twin subsystems are established on land and at sea respectively. Data interaction between subsystems is realized through SDH network. The functions of each subsystem mentioned in data acquisition and integration are modularly defined and encapsulated into a functional component library. Combined with soft controller technology, the monitoring subsystems work collaboratively, and the subsystems are seamlessly connected to the integrated intelligent monitoring and management platform of station control and centralized control layer. The digital twin model is the foundation of the digital twin system. Functionality and Application: The integrated intelligent monitoring and management platform calls upon the functional component library to monitor wind turbine speed, power, and temperature parameters in real time, view on-site videos of wind farms, and acquire meteorological and marine environmental data; it also remotely and intelligently controls equipment through soft controller technology, adjusts wind turbine operating parameters based on environmental data, and locates submarine cable faults based on the submarine cable fault monitoring subsystem. System testing and optimization: The test included assessing the accuracy, completeness, and timeliness of data acquisition from each subsystem at the data acquisition terminal; testing the stability and transmission efficiency of the communication link in the intermediate network communication layer; and testing the monitoring, analysis, and control functions of the integrated intelligent monitoring and management platform at the station control and centralized control layers. Based on the test results, the system parameters were adjusted, the model algorithm was optimized, and the user interface was improved, ultimately resulting in an offshore wind farm monitoring system based on digital twin and grid-connected architecture.

[0029] Specifically, in this embodiment, the real-time data includes wind turbine operating status data, substation electrical data, video data, environmental data, power prediction data, and submarine cable status data; The intermediate network communication layer preprocesses the collected data, including: Data cleaning: Remove abnormal data caused by sensor malfunctions or communication interference (such as values ​​outside the reasonable range or duplicate data). Data completion: For data loss caused by brief communication interruptions, interpolation methods (such as linear interpolation and cubic spline interpolation) are used to complete the data. Unified format: Heterogeneous data from different subsystems (such as numerical, character, and image data) are converted into standardized formats (such as JSON and XML) and stored in a unified database to provide high-quality data support for subsequent model building and functional applications.

[0030] Specifically, in this embodiment, constructing a digital twin model includes: Building a digital twin model framework includes: At the station control and centralized control layer, based on preprocessed standardized data and combined with the Unity and Digital Twin Hub digital twin platforms, a digital twin model is constructed. This model covers three core dimensions: Geometric Dimensions: Reconstructing the geographical layout and three-dimensional structure of wind farm equipment; the geographical layout includes the location of wind turbines, the coordinates of substations, and the route of submarine cables; the three-dimensional structure of equipment includes detailed geometric models of wind turbine blades, generators, and transformers. Physical dimension: Integrating the physical properties and operating laws of the equipment to achieve physical simulation of the equipment's operating state; among which, the physical properties of the equipment include material parameters, electrical characteristics, and mechanical properties; the operating laws include the power curve of the wind turbine and the loss model of the transformer; Information dimension: Real-time data, historical operation data, and fault record information collected by various subsystems during data acquisition and integration are used to form the data brain of the model.

[0031] Construct functional sub-models within the digital twin model framework, including: Fault diagnosis sub-model: Based on equipment vibration, temperature and current data, neural network and support vector machine algorithms are used to realize real-time diagnosis and early warning of wind turbine gearbox faults, substation switch faults and submarine cable insulation faults; Power prediction optimization sub-model: Combining real-time environmental data and historical power generation data, the power prediction algorithm (such as an improved LSTM neural network) is optimized to improve the accuracy of power prediction; real-time environmental data includes wind speed and wind direction; Life Prediction Sub-model: Based on equipment runtime, load changes, and maintenance record data, the remaining life prediction algorithm (such as the Weibull distribution model) is used to predict the remaining service life of key equipment (such as wind turbine main shafts and generators), providing a basis for predictive maintenance.

[0032] Model Training and Calibration: Near-physical simulation technology is used to simulate different operating conditions of wind farms (such as rated wind speed, extreme wind and waves, equipment failure, etc.). A virtual control environment is built using soft controller technology to train and calibrate the digital twin model. The simulation results are compared with the actual operating data of the physical system. Algorithms such as gradient descent and particle swarm optimization are used to correct the model parameters until the simulation error is less than a preset threshold (such as power prediction error less than 5% and fault diagnosis accuracy greater than 95%), ensuring that the model can accurately reflect the operating state of the physical system.

[0033] Specifically, in this embodiment, system integration and adaptation includes: Deeply integrate digital twin systems with the power system grid connection architecture: 1) Subsystem deployment: Digital twin subsystems are established in the onshore control center and the offshore wind farm respectively. The digital twin subsystem of the onshore control center focuses on operation and maintenance management and grid dispatch interaction, while the digital twin subsystem of the offshore wind farm focuses on real-time monitoring of field equipment. 2) Data Interaction: By optimizing data transmission bandwidth and routing configuration through the SDH network, the data transmission rate (e.g., wind turbine data transmission rate 1s / time, environmental data transmission rate 5s / time) and format requirements of different subsystems (such as wind turbine monitoring and power prediction) are adapted to achieve real-time data interaction between the digital twin subsystem of the onshore control center and the digital twin subsystem of the offshore wind farm, ensuring that the data transmission latency is less than 100ms and the packet loss rate is less than 0.1%. Functional component integration: The functions of each monitoring subsystem in data acquisition and integration are modularized and encapsulated into a reusable functional component library. The component library includes wind turbine monitoring components, substation control components, video surveillance components, environmental monitoring subsystems, and submarine cable fault monitoring components. The functional component library is connected to the integrated intelligent monitoring and management platform of the station control and centralized control layers through standardized interfaces to achieve plug-and-play functionality for each component. The component collaborative control logic is written in conjunction with software controller technology to ensure that the wind turbine monitoring components, substation control components, video surveillance components, environmental monitoring subsystems, and submarine cable fault monitoring components work collaboratively. Compatibility and Adaptation: To address the grid connection requirements of different regional power grids (such as different voltage levels and dispatch protocols), an adaptation module is set up in the integrated intelligent monitoring and management platform to support flexible configuration of system parameters (such as voltage control range and AGC response speed). For example, for a 220kV power grid, the voltage control range of the substation bus is set to 220±5kV; for power grid dispatch systems using the IEC 61970 protocol, corresponding communication interfaces are configured to ensure that the system can achieve data interaction and command reception with the power grid dispatching agency.

[0034] Specifically, in this embodiment, the functional implementation and application include: Real-time panoramic monitoring: 1) Equipment monitoring: The fan speed, power and temperature parameters are displayed in real time through the fan monitoring component, and the bus voltage, current and switch status electrical data are displayed through the booster station control component. Detailed parameters and historical curves can be viewed by clicking on the equipment model. 2) Environmental monitoring: Through environmental monitoring components and video monitoring components, the platform interface displays real-time environmental data such as wind speed, wind direction, and wave height, as well as on-site video footage of the wind farm. It supports video playback and abnormal behavior recognition (such as personnel accidentally entering dangerous areas). 3) Fault monitoring: The fault diagnosis sub-model monitors the fault status of the equipment in real time. When a fault is detected, the platform automatically pops up an alarm window, showing the location of the faulty equipment, the fault type, and the fault level, and pushes it to the mobile APP of the operation and maintenance personnel. Remote intelligent control: 1) Output control: Receive AGC commands from the power grid dispatching agency and automatically adjust the wind turbine output through soft controller technology to ensure that the deviation between the total wind farm output and the dispatch command is less than 2%; according to voltage control requirements, automatically adjust the tap changer of the step-up substation through the AVC function to maintain the bus voltage stable within the allowable range; 2) Equipment control: Supports remote control of wind turbine start-up and shutdown, blade angle adjustment, and booster station switch operation. Operation commands are transmitted to field equipment through encrypted communication links to ensure the security and reliability of control commands; 3) Fault handling: When the submarine cable fault monitoring subsystem detects a submarine cable fault, the platform automatically generates a fault handling plan, including fault location, impact range analysis, and backup power switching instructions. Maintenance personnel can confirm and execute the plan with one click, shortening the fault handling time. Intelligent operation and maintenance management: 1) Predictive maintenance: Based on the life prediction sub-model, the platform automatically generates equipment maintenance plans and pushes maintenance reminders; combined with equipment operating status data, it provides early warnings of potential faults to avoid sudden downtime; 2) Data statistical analysis: The platform automatically calculates wind farm power generation, equipment failure rate, and operation and maintenance cost data, and generates daily, weekly, and monthly reports, which can be displayed in chart form to provide data support for operational decision-making; 3) Unmanned operation support: Operation and maintenance personnel can complete the comprehensive monitoring and management of the wind farm from the onshore control center, and only send personnel to the site when the equipment needs on-site maintenance, reducing operation and maintenance costs and safety risks.

[0035] Specifically, in this embodiment, the system test includes: 1) Data acquisition test: Check the accuracy, completeness and timeliness of data acquisition in each subsystem, and replace or optimize any sensors or communication links that do not meet the requirements; 2) Network performance testing: Test the transmission bandwidth, stability, and anti-interference capability of the intermediate network communication layer SDH network, simulate a strong electromagnetic interference environment at sea, and ensure that the data transmission packet loss rate is less than 0.1%; 3) Functional testing: Test the platform's real-time monitoring, remote control, fault diagnosis, AGC / AVC and other functions to verify the correctness and stability of the functions; Adaptability testing: Simulate different grid connection architecture requirements to test the flexibility and compatibility of system parameter configuration, ensuring that the system can quickly adapt to different grid requirements.

[0036] Specifically, in this embodiment, during system optimization, the system is iteratively optimized based on test results and actual operational feedback, including: 1) Parameter optimization: Adjust the parameters of the digital twin model and control parameters to improve the simulation accuracy and control effect of the model; the parameters of the digital twin model include the coefficients of the wind turbine power curve; the control parameters include the AGC response speed; 2) Algorithm optimization: Optimize the fault diagnosis algorithm and power prediction algorithm to improve the accuracy of fault diagnosis and the precision of power prediction; 3) Interface optimization: Based on the operating habits of maintenance personnel, optimize the platform user interface, simplify the operation process, and improve maintenance efficiency; 4) Functionality Improvement: Add new functions based on user needs to continuously improve the system's usability and intelligence.

[0037] The above-described embodiments are merely preferred embodiments of the present invention and are not intended to limit the scope of the present invention. Therefore, any changes made in accordance with the shape and principle of the present invention should be covered within the protection scope of the present invention.

Claims

1. A monitoring system for offshore wind farms based on digital twin and grid-connected architecture, characterized in that, It includes the field layer, intermediate network communication layer, and station control and centralized control layer; The field layer includes a wind turbine monitoring subsystem, a booster station monitoring subsystem, a video monitoring subsystem, an environmental monitoring subsystem, a power prediction subsystem, and a submarine cable fault monitoring subsystem. Each subsystem is equipped with a standardized interface for collecting real-time data from the wind farm and transmitting it to the intermediate network communication layer. The intermediate network communication layer includes an SDH communication node and a vertical encryption device. The SDH communication node is used to receive data transmitted from the field layer, and the vertical encryption device is used to ensure data transmission security. The intermediate network communication layer also preprocesses the collected data. The station control and centralized control layer includes an integrated intelligent monitoring and management platform and a digital twin model. The digital twin model is built based on data collected from the field layer and covers multi-dimensional information and functional sub-models of the wind farm. The integrated intelligent monitoring and management platform stores a functional component library, which can call the functional component library to realize monitoring and control functions, and can test and optimize the system.

2. A design method for an offshore wind farm monitoring system based on digital twin and grid-connected architecture as described in claim 1, characterized in that, include: Data collection and integration: The offshore wind farm site layer deploys wind turbine monitoring subsystems, booster station monitoring subsystems, video monitoring subsystems, environmental monitoring subsystems, power prediction subsystems, and submarine cable fault monitoring subsystems. Each subsystem transmits real-time data to the SDH communication node in the intermediate network communication layer via a 35kV network, using standardized interfaces and communication protocols. Vertical encryption devices are used to ensure data transmission security. The collected data is formatted and preprocessed in the intermediate network communication layer to obtain standardized data. Model building: Based on digital twin technology and combined with the obtained standardized data, a digital twin model of an integrated digital twin monitoring system is constructed at the station control and centralized control layers. The digital twin model covers the wind turbine operating status of the wind farm, the electrical parameters of the substation, and environmental conditions, and includes sub-models for fault diagnosis and power prediction optimization. The digital twin model is trained using near-physical simulation technology and soft controller technology to make the model behavior match the physical system. System integration and adaptation: The digital twin system is integrated with the power system grid architecture, and digital twin subsystems are established on land and at sea respectively. Data interaction between subsystems is realized through SDH network. The functions of each subsystem mentioned in data acquisition and integration are modularly defined and encapsulated into a functional component library. Combined with soft controller technology, the monitoring subsystems work together, and the subsystems are seamlessly connected with the integrated intelligent monitoring and management platform of station control and centralized control layer. The digital twin model is the foundation of the digital twin system; Functionality and Application: The integrated intelligent monitoring and management platform calls upon the functional component library to monitor wind turbine speed, power, and temperature parameters in real time, view on-site videos of wind farms, and acquire meteorological and marine environmental data; it also remotely and intelligently controls equipment through soft controller technology, adjusts wind turbine operating parameters based on environmental data, and locates submarine cable faults based on the submarine cable fault monitoring subsystem. System testing and optimization: The test included assessing the accuracy, completeness, and timeliness of data acquisition from each subsystem at the data acquisition terminal; testing the stability and transmission efficiency of the communication link in the intermediate network communication layer; and testing the monitoring, analysis, and control functions of the integrated intelligent monitoring and management platform at the station control and centralized control layers. Based on the test results, system parameters were adjusted, model algorithms were optimized, and the user interface was improved, ultimately resulting in an offshore wind farm monitoring system based on digital twin and grid-connected architecture.

3. The design method of the offshore wind farm monitoring system based on digital twin and grid-connected architecture according to claim 2, characterized in that, The real-time data includes wind turbine operating status data, substation electrical data, video data, environmental data, power prediction data, and submarine cable status data; The intermediate network communication layer preprocesses the collected data, including: Data cleaning: Remove abnormal data caused by sensor malfunctions or communication interference; Data completion: For data loss caused by brief communication interruptions, interpolation is used to complete the data. Standardized format: Heterogeneous data from different subsystems are converted into a standardized format and stored in a unified database, providing high-quality data support for subsequent model building and functional applications.

4. The design method of the offshore wind farm monitoring system based on digital twin and grid-connected architecture according to claim 2, characterized in that, Building a digital twin model includes: Build a framework for a digital twin model; Construct functional sub-models within the framework of the digital twin model; Training and calibration.

5. The design method of the offshore wind farm monitoring system based on digital twin and grid-connected architecture according to claim 4, characterized in that, Building a digital twin model framework includes: At the station control and centralized control layer, based on preprocessed standardized data and combined with the Unity and Digital Twin Hub digital twin platforms, a digital twin model is constructed. This model covers three core dimensions: Geometric Dimensions: Reconstructing the geographical layout and three-dimensional structure of wind farm equipment; the geographical layout includes the location of wind turbines, the coordinates of substations, and the route of submarine cables; the three-dimensional structure of equipment includes detailed geometric models of wind turbine blades, generators, and transformers. Physical dimension: Integrating the physical properties and operating laws of the equipment to achieve physical simulation of the equipment's operating state; among which, the physical properties of the equipment include material parameters, electrical characteristics, and mechanical properties; the operating laws include the power curve of the fan and the loss model of the transformer; Information dimension: Real-time data, historical operation data, and fault record information collected by various subsystems during data acquisition and integration are used to form the data brain of the model.

6. The design method of the offshore wind farm monitoring system based on digital twin and grid-connected architecture according to claim 4, characterized in that, The functional sub-models built within the digital twin model framework include: Fault diagnosis sub-model: Based on equipment vibration, temperature and current data, neural network and support vector machine algorithms are used to realize real-time diagnosis and early warning of wind turbine gearbox faults, substation switch faults and submarine cable insulation faults; Power prediction optimization sub-model: Combining real-time environmental data and historical power generation data, the power prediction algorithm is optimized to improve the accuracy of power prediction; real-time environmental data includes wind speed and wind direction. Life Prediction Sub-model: Based on equipment runtime, load changes, and maintenance record data, a remaining life prediction algorithm is used to predict the remaining service life of critical equipment, providing a basis for predictive maintenance.

7. The design method of the offshore wind farm monitoring system based on digital twin and grid-connected architecture according to claim 2, characterized in that, System integration and adaptation, including: Deeply integrate digital twin systems with the power system grid connection architecture: 1) Subsystem deployment: Digital twin subsystems are established in the onshore control center and the offshore wind farm respectively. The digital twin subsystem of the onshore control center focuses on operation and maintenance management and grid dispatch interaction, while the digital twin subsystem of the offshore wind farm focuses on real-time monitoring of field equipment. 2) Data Interaction: By optimizing data transmission bandwidth and routing configuration through the SDH network, and adapting to the data transmission rate and format requirements of different subsystems, real-time data interaction is achieved between the digital twin subsystem of the onshore control center and the digital twin subsystem of the offshore wind farm, ensuring that the data transmission latency is less than 100ms and the packet loss rate is less than 0.1%. Functional component integration: The functions of each monitoring subsystem in data acquisition and integration are modularized and encapsulated into a reusable functional component library. The component library includes wind turbine monitoring components, substation control components, video surveillance components, environmental monitoring subsystems, and submarine cable fault monitoring components. The functional component library is connected to the integrated intelligent monitoring and management platform of the station control and centralized control layers through standardized interfaces to achieve plug-and-play functionality for each component. The component collaborative control logic is written in conjunction with software controller technology to ensure that the wind turbine monitoring components, substation control components, video surveillance components, environmental monitoring subsystems, and submarine cable fault monitoring components work collaboratively. Compatibility and Adaptation: To meet the grid connection requirements of different regional power grids, an adaptation module is set up in the integrated intelligent monitoring and management platform to support flexible configuration of system parameters.

8. The design method of the offshore wind farm monitoring system based on digital twin and grid-connected architecture according to claim 6, characterized in that, Functionality implementation and application, including: Real-time panoramic monitoring: 1) Equipment monitoring: The fan speed, power and temperature parameters are displayed in real time through the fan monitoring component, and the bus voltage, current and switch status electrical data are displayed through the booster station control component. Detailed parameters and historical curves can be viewed by clicking on the equipment model. 2) Environmental monitoring: Through environmental monitoring components and video monitoring components, the platform interface displays real-time environmental data such as wind speed, wind direction, and wave height, as well as on-site video footage of the wind farm, supporting video playback and abnormal behavior recognition; 3) Fault monitoring: The fault diagnosis sub-model monitors the fault status of the equipment in real time. When a fault is detected, the platform automatically pops up an alarm window, showing the location of the faulty equipment, the fault type, and the fault level, and pushes it to the mobile APP of the operation and maintenance personnel. Remote intelligent control: 1) Output control: Receive AGC commands from the power grid dispatching agency and automatically adjust the wind turbine output through soft controller technology to ensure that the deviation between the total wind farm output and the dispatch command is less than 2%; according to voltage control requirements, automatically adjust the tap changer of the step-up substation through the AVC function to maintain the bus voltage stable within the allowable range; 2) Equipment control: Supports remote control of wind turbine start-up and shutdown, blade angle adjustment, and booster station switch operation. Operation commands are transmitted to field equipment through encrypted communication links to ensure the security and reliability of control commands; 3) Fault handling: When the submarine cable fault monitoring subsystem detects a submarine cable fault, the platform automatically generates a fault handling plan, including fault location, impact range analysis, and backup power switching instructions. Maintenance personnel can confirm and execute the plan with one click, shortening the fault handling time. Intelligent operation and maintenance management: 1) Predictive maintenance: Based on the life prediction sub-model, the platform automatically generates equipment maintenance plans and pushes maintenance reminders; combined with equipment operating status data, it provides early warnings of potential faults to avoid sudden downtime; 2) Data statistical analysis: The platform automatically calculates wind farm power generation, equipment failure rate, and operation and maintenance cost data, and generates daily, weekly, and monthly reports, which can be displayed in chart form to provide data support for operational decision-making; 3) Unmanned operation support: Operation and maintenance personnel can complete the comprehensive monitoring and management of the wind farm from the onshore control center, and only send personnel to the site when the equipment needs on-site maintenance, reducing operation and maintenance costs and safety risks.

9. The design method of the offshore wind farm monitoring system based on digital twin and grid-connected architecture according to claim 2, characterized in that, System testing includes: 1) Data acquisition test: Check the accuracy, completeness and timeliness of data acquisition in each subsystem, and replace or optimize any sensors or communication links that do not meet the requirements; 2) Network performance testing: Test the transmission bandwidth, stability, and anti-interference capability of the intermediate network communication layer SDH network, simulate a strong electromagnetic interference environment at sea, and ensure that the data transmission packet loss rate is less than 0.1%; 3) Functional testing: Test the platform's real-time monitoring, remote control, fault diagnosis, AGC / AVC and other functions to verify the correctness and stability of the functions; Adaptability testing: Simulate different grid connection architecture requirements to test the flexibility and compatibility of system parameter configuration, ensuring that the system can quickly adapt to different grid requirements.

10. The design method of the offshore wind farm monitoring system based on digital twin and grid-connected architecture according to claim 2, characterized in that, During system optimization, the system is iteratively optimized based on test results and actual operational feedback, including: 1) Parameter optimization: Adjust the parameters of the digital twin model and control parameters to improve the simulation accuracy and control effect of the model; the parameters of the digital twin model include the coefficients of the wind turbine power curve; the control parameters include the AGC response speed; 2) Algorithm optimization: Optimize the fault diagnosis algorithm and power prediction algorithm to improve the accuracy of fault diagnosis and the precision of power prediction; 3) Interface optimization: Based on the operating habits of maintenance personnel, optimize the platform user interface, simplify the operation process, and improve maintenance efficiency; 4) Functionality Improvement: Add new functions based on user needs to continuously improve the system's usability and intelligence.

Images