Deep sea wind turbine grounding grid state monitoring method based on digital twinning

Abstract

This invention relates to a digital twin-based method for monitoring the grounding grid status of deep-sea wind turbines. The method includes: deploying corresponding sensors at key locations of the grounding grid, in the sea area where the wind turbine is located, and in the soil to collect data; transmitting the collected data to both an offshore platform and a land-based control center for processing and analysis; the cloud computing platform at the land-based control center performing in-depth data mining to establish a grounding grid status assessment model and a fault prediction model; and using the digital twin model of the deep-sea wind turbine grounding grid to calculate the electrical parameters of the grounding grid in real time for a comprehensive real-time status assessment, combining historical data for trend analysis and prediction, and fault diagnosis and location. Compared with existing technologies, this invention has advantages such as timely detection of potential problems in the grounding grid of deep-sea wind turbines and improved accuracy and real-time performance of monitoring results.

Description

Technical Field

[0001] This invention relates to the field of monitoring technology for new energy power equipment, and in particular to a method for monitoring the status of grounding grids of deep-sea wind turbines based on digital twins. Background Technology

[0002] With the continuous advancement of energy transition and "carbon neutrality", offshore wind power has developed rapidly. However, the development and utilization of near-shore resources is approaching saturation, and the development of offshore wind power must be promoted to the deep sea.

[0003] In deep-sea environments, lightning strikes are a major cause of wind turbine failures. Deep-sea wind turbines are significantly larger than onshore and near-shore wind turbines and are situated in complex marine environments characterized by high salinity and humidity, making them far more vulnerable to lightning strikes than onshore and near-shore wind turbines. The grounding grid is a critical component of deep-sea wind turbines, responsible for rapidly dissipating lightning strikes and electrical fault currents, and is a core component ensuring the safety of wind turbine equipment and personnel.

[0004] Traditional methods for testing the grounding grid status of wind turbines, such as the three-level method for measuring grounding resistance and regular on-site inspections at sea, are problematic when applied to deep-sea wind power. These methods suffer from low efficiency, high time and labor costs, significant measurement errors, and long testing cycles. Furthermore, their real-time performance fails to meet the requirements for safe and stable operation of wind power systems.

[0005] A search revealed Chinese invention patent application publication number CN118504221A, which discloses a grounding grid corrosion monitoring system, method, device, and storage medium. The system includes: using a data modeling module to construct a three-dimensional model of the grounding grid based on preset static data of the grounding metal materials; using a data processing module to collect static data of the grounding metal materials, real-time dynamic corrosion data, and environmental data of the substation location; using the data processing module to preprocess the collected real-time dynamic corrosion data; using a digital twin modeling module to establish a corrosion digital twin model based on the static data of the metal materials, the environmental data of the substation location, and the three-dimensional model of the grounding grid; using a data synchronization module to synchronize the preprocessed real-time dynamic corrosion data to the corrosion digital twin model; and using a data monitoring and calculation module to monitor the corrosion degree of the grounding metal materials of the grounding grid based on the current preprocessed dynamic data from the corrosion digital twin model. This existing patent application has the problem that it only detects corrosion in the grounding grid and is not suitable for monitoring grounding grids in deep-sea environments.

[0006] How to achieve real-time and accurate detection of the grounding grid status of deep-sea wind turbines has become a technical problem that needs to be solved. Summary of the Invention

[0007] The purpose of this invention is to overcome the shortcomings of the existing technology by providing a digital twin-based method for monitoring the grounding grid status of deep-sea wind turbines. This method addresses the problems of low efficiency, poor accuracy, and insufficient real-time performance in the existing technology, enabling efficient, accurate, and real-time monitoring of the grounding grid status of deep-sea wind turbines and improving the safety and reliability of deep-sea wind power generation systems.

[0008] The objective of this invention can be achieved through the following technical solutions:

[0009] According to one aspect of the present invention, a method for monitoring the status of the grounding grid of a deep-sea wind turbine based on digital twin is provided, the method comprising:

[0010] A digital twin model of the grounding grid for deep-sea wind farms was constructed based on grounding grid design drawings, construction data, and material electrical characteristic parameters.

[0011] Sensors were deployed at key locations of the grounding grid of deep-sea wind turbines, in the sea area where the deep-sea wind turbines are located, and in the soil to collect raw data and environmental data.

[0012] The collected raw data and environmental data are transmitted to the offshore platform and the land control center for processing and analysis, respectively; a grounding grid status assessment model and a fault prediction model are constructed; the grounding grid electrical parameters are calculated in real time using a digital twin model of the grounding grid of the deep-sea wind farm, and a real-time comprehensive assessment of the grounding grid status is conducted based on the grounding grid status assessment model; and fault diagnosis and location are performed on the grounding grid status based on the fault prediction model and historical data.

[0013] Preferably, the digital twin model of the grounding grid of the deep-sea wind power generation field includes a three-dimensional geometric model constructed based on the acquired grounding grid design drawings and construction data, and a physical model established according to the electrical characteristic parameters of the materials used in the grounding grid to simulate the distribution of current in the grounding grid;

[0014] The digital twin model of the grounding grid of the deep-sea wind farm is connected to the collected data in real time, and the parameters of the digital twin model of the grounding grid of the deep-sea wind farm are dynamically updated according to the data collected by the sensors.

[0015] More preferably, the three-dimensional geometric model is used to describe the shape, size, connection relationship of each component, and layout in space of the grounding grid, including the length, diameter, and burial depth of the grounding conductor, and the specifications and orientation of the connecting conductor.

[0016] Preferably, a four-wire resistance sensor is installed at each grounding electrode of the deep-sea wind turbine grounding grid in contact with the soil, an electrochemical corrosion sensor is installed at the joint of the connecting conductor, and an optical fiber temperature sensor is installed at the current concentration node that is prone to heat generation.

[0017] Preferably, in the sea area where the grounding grid of the deep-sea wind turbine is located, temperature and humidity sensors and salinity sensors are installed at a set distance from the grounding grid; and soil resistivity sensors are buried in the soil around the grounding grid of the deep-sea wind turbine.

[0018] Preferably, the method includes an offshore platform deployed in the deep sea and a land control center deployed on land, wherein the offshore platform is equipped with edge computing devices and the land control center is equipped with a data processing center of a cloud computing platform.

[0019] The offshore platform and the land-based control center transmit data via a satellite communication link;

[0020] The data collected by the sensors is transmitted to the data acquisition terminal on the offshore platform via submarine fiber optic cables.

[0021] More preferably, after receiving the data, the cloud computing platform preprocesses the raw data collected by the sensor;

[0022] The edge computing device runs an edge computing algorithm to perform preliminary analysis on the data, filter out abnormal data, and transmit the key information of the abnormal data to the cloud computing platform.

[0023] The cloud computing platform utilizes big data processing technology and machine learning algorithms to perform in-depth data mining and establish grounding grid status assessment models and fault prediction models.

[0024] Preferably, the input of the grounding grid status assessment model is a three-dimensional geometric model of the grounding grid, electrical parameters and environmental data, and the output is the grounding resistance of the grounding grid, the current distribution in the grounding body, the contact voltage and step voltage of the deep-sea wind turbine platform, the voltage difference between various devices of the deep-sea wind turbine platform and the degree of electrochemical corrosion of the grounding grid.

[0025] The inputs to the grounding grid fault prediction model are the three-dimensional geometric model of the grounding grid, electrical parameters, and environmental data. The outputs are the grounding resistance variation trend and risk prediction of the grounding grid, suspected fault points of the grounding grid, corrosion rate prediction of the grounding body, and fault causes.

[0026] Preferably, the process of real-time comprehensive status assessment includes:

[0027] The digital twin model of the grounding grid of the deep-sea wind farm calculates the electrical parameters of the grounding grid in real time, compares the calculation results with the preset standard values, and issues an early warning signal when the grounding resistance exceeds the set threshold of the standard value.

[0028] Taking into account parameters such as temperature and corrosion rate, the condition of the grounding grid is comprehensively evaluated in real time.

[0029] When an abnormality is detected in the grounding grid, the simulation results are compared with the actual monitoring data, and the fault diagnosis algorithm is used to determine the cause of the fault.

[0030] Preferably, the trend analysis and prediction based on historical data specifically involves: using time series analysis and deep learning models to analyze historical grounding resistance data and predict the changing trends of grounding resistance and grounding body corrosion rate within the next month; and modifying the fault prediction model based on changes in environmental parameters caused by seasonal variations.

[0031] Historical data includes electrical parameters, environmental parameters, and maintenance records.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. High efficiency: Through real-time monitoring and automated data processing and analysis, the system eliminates the need for frequent on-site inspections by personnel, greatly improving monitoring efficiency, enabling timely detection of potential problems in the grounding grid, reducing downtime, and improving the overall operating efficiency of the wind power generation system;

[0034] 2. Accuracy: The collaborative work of multiple types of sensors and the precise simulation of the digital twin model can comprehensively and accurately obtain the operating status information of the grounding grid, effectively overcoming the problems of traditional monitoring methods being greatly affected by environmental factors and having large measurement errors, thus improving the accuracy of monitoring results;

[0035] 3. Real-time performance: Based on a hybrid communication mode and a data processing approach combining edge computing and cloud computing, real-time monitoring and rapid response to the grounding grid status are achieved. Once an anomaly occurs in the grounding grid, an early warning signal can be issued immediately, along with accurate fault diagnosis and location information, ensuring timely maintenance and significantly improving the safety and reliability of deep-sea wind power generation systems. Attached Figure Description

[0036] Figure 1 This is a flowchart illustrating the grounding grid status monitoring method for deep-sea wind turbines in this invention.

[0037] Figure 2 This is a schematic diagram illustrating the construction process of the digital twin model of the grounding grid of the deep-sea wind turbine in this invention;

[0038] Figure 3 This is a schematic diagram of the sensor deployment structure in this invention;

[0039] Figure 4 This is a schematic diagram illustrating the principle of data transmission in this invention;

[0040] Figure 5 This is a schematic diagram of the data analysis process in this invention. Detailed Implementation

[0041] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0042] This embodiment relates to a method for monitoring the status of the grounding grid of a deep-sea wind turbine based on digital twins, taking a scenario of a deep-sea wind farm 60km offshore with 50 20MW deep-sea wind turbines as an example.

[0043] like Figure 1 As shown, the method includes the following steps:

[0044] S101: Construct a digital twin model of the grounding grid for deep-sea wind turbines.

[0045] S102: Deploy resistance sensors, corrosion sensors, and temperature sensors at key locations of the grounding grid of deep-sea wind turbines, and deploy temperature and humidity sensors, salinity sensors, and soil resistivity sensors in the sea area and soil where the deep-sea wind turbines are located.

[0046] S103: Data is transmitted using a hybrid communication mode that combines fiber optic communication and satellite communication. Data is preprocessed at the data processing center, including cleaning, noise reduction, and normalization. Edge computing is used to process the data initially on the offshore platform, and cloud computing platform is used for in-depth data analysis.

[0047] S104: Real-time status assessment of grounding grid electrical parameters is performed by using a digital twin model of the grounding grid of deep-sea wind farms, historical data is collected for trend analysis and prediction, and fault diagnosis and location are performed by combining the digital twin model and fault diagnosis algorithm.

[0048] In S101, the process of constructing a digital twin model of the grounding grid for deep-sea wind turbines includes the following steps, such as... Figure 2 As shown:

[0049] S1011: Constructing the Geometric Model: Collect the design drawings of the wind turbine grounding grid, including detailed information such as the number, location, and burial depth of the grounding conductors, and the specifications and orientation of the connecting conductors. Accurately construct a three-dimensional geometric model of the grounding grid based on the design drawings. This model precisely describes the shape, size, connection relationships of the components, and spatial layout of the grounding grid, including the length, diameter, and burial depth of the grounding conductors, and the specifications and orientation of the connecting conductors.

[0050] S1012: Establish a physical model: Consult the electrical characteristic parameters of the materials used in the grounding grid of the deep-sea wind turbine, such as the grounding conductor being made of galvanized steel, the resistivity of the seawater where the wind turbine is located, and the resistivity of the seabed soil. Input the geometric model of the deep-sea wind turbine grounding grid along with the aforementioned conductor, seawater, and soil parameters into electromagnetic simulation software based on the finite element method to establish a physical model of the grounding grid. In the model, the grounding grid is divided into several (e.g., 10,000) micro-units. By solving Maxwell's equations, the distribution of current in the grounding grid is simulated.

[0051] S1013: Develop a data interface program to achieve real-time connection between the digital twin model and sensor data, dynamically update the parameters of the digital twin model based on the sensor data, and realize the synchronous evolution of the virtual model and the physical entity.

[0052] In S102, corresponding sensors are deployed at key locations of the grounding grid of deep-sea wind turbines, in the sea area where the deep-sea wind turbines are located, and in the soil, such as... Figure 3 Specifically, it includes:

[0053] S1021: Four-wire resistance sensors are installed at each grounding electrode contact point with the soil in the grounding grid of deep-sea wind turbines, for a total of four sensors, to ensure comprehensive monitoring of grounding resistance changes. At the conductor joints, an electrochemical corrosion sensor is installed every 50 meters, for a total of four sensors, to monitor conductor corrosion in real time. At current-concentrated nodes prone to heat generation, fiber optic temperature sensors are installed, for a total of four sensors, to promptly detect temperature anomalies.

[0054] S1022: In the sea area where the grounding grid of the deep-sea wind turbine is located, four temperature and humidity sensors and four salinity sensors are installed at a set distance (e.g., 20 meters) from the grounding grid to monitor the ambient temperature, humidity, and seawater salinity in real time. In the soil surrounding the grounding grid of the deep-sea wind turbine, a soil resistivity sensor is buried every 200 meters, for a total of four sensors, to periodically measure soil resistivity. Grounding resistance is considered raw data, while conductor corrosion, temperature anomalies, ambient temperature and humidity, seawater salinity, and soil resistivity are considered environmental data.

[0055] In S103, a hybrid communication mode combining fiber optic communication and satellite communication is used to transmit data. The data collected by the sensors in S102 is then processed, such as... Figure 4 The process includes the following steps:

[0056] S1031: A submarine fiber optic cable is laid between the offshore platform and the sensors near the grounding grid of the deep-sea wind turbine to transmit the raw data collected by the sensors to the data acquisition terminal on the offshore platform. Environmental data is transmitted between the offshore platform and the land-based control center via a satellite communication link. The offshore platform is equipped with edge computing devices, and the land-based control center is equipped with a cloud computing platform data processing center.

[0057] S1032: At the data processing center of the land control center, the raw data collected by the sensors is first preprocessed, including data cleaning, denoising, and normalization. Specifically, data cleaning involves writing data cleaning algorithms to remove erroneous, duplicate, and outlier values ​​from the data; denoising uses digital signal processing techniques, such as filtering algorithms, to remove noise interference from the data; and normalization normalizes data collected by different types of sensors to give them uniform dimensions and value ranges, facilitating subsequent data analysis and model training.

[0058] S1033: On the edge computing equipment of the offshore platform, edge computing algorithms are run to perform preliminary data analysis, filter out abnormal data, and transmit key information to the cloud computing platform. The cloud computing platform utilizes big data processing technology and machine learning algorithms to perform in-depth data mining and establish a grounding grid status assessment model and a fault prediction model. The input parameters for the grounding grid status assessment model are the three-dimensional geometric model of the grounding grid, electrical parameters such as voltage and current, and environmental data. The output results are the grounding grid resistance, current distribution in the grounding body, contact voltage and step voltage of the deep-sea wind turbine platform, voltage difference between various devices on the deep-sea wind turbine platform, and the degree of electrochemical corrosion of the grounding grid, used to assess the health status of the deep-sea wind turbine grounding grid. The input parameters for the grounding grid fault prediction model are the three-dimensional geometric model of the grounding grid, electrical parameters such as voltage and current, and environmental data. The output results are the grounding grid resistance change trend and risk prediction, suspected fault points in the grounding grid, predicted corrosion rate of the grounding body, and possible causes of faults.

[0059] In S104, a digital twin model of the grounding grid of a deep-sea wind farm is used to calculate the electrical parameters of the grounding grid in real time for real-time status assessment. Historical data is collected for trend analysis and prediction. Fault diagnosis and location are then performed by combining the digital twin model with fault diagnosis algorithms. Figure 5 This includes the following steps:

[0060] S1041: Using a digital twin model, calculate electrical parameters of the grounding grid in real time, such as grounding resistance, step voltage, and contact voltage. Compare the calculated results with pre-set standard values. If the grounding resistance exceeds a set threshold (e.g., 40%), it is considered abnormal, and an early warning signal is issued. Simultaneously, a comprehensive assessment of the grounding grid's condition is performed, taking into account parameters such as temperature and corrosion rate. If any parameter is detected as abnormal, proceed to S1042; otherwise, proceed to S1043.

[0061] S1042: Collect historical data of the grounding grid over the past year, including electrical parameters, environmental parameters, and maintenance records. Utilize time series analysis and deep learning models to analyze historical grounding resistance data and predict the trends in grounding resistance and grounding electrode corrosion rate over the next month. Incorporate seasonal variations in environmental parameters to refine the fault prediction model and improve prediction accuracy.

[0062] S1043: When an abnormality is detected in the grounding grid, such as a sudden increase in grounding resistance and temperature rise, fault scenarios such as conductor corrosion and connection point breakage are simulated in the digital twin model. The simulation results are compared with the actual monitoring data, and the fault diagnosis algorithm is used to determine the cause of the fault. The visualization function of the digital twin model is used to display the location of the fault in a three-dimensional graphical format, providing maintenance personnel with accurate fault location information.

[0063] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in the present invention, and these modifications or substitutions should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for monitoring the status of grounding grids of deep-sea wind turbines based on digital twins, characterized in that, The method includes: A digital twin model of the grounding grid for deep-sea wind farms was constructed based on grounding grid design drawings, construction data, and material electrical characteristic parameters. Sensors were deployed at key locations of the grounding grid of deep-sea wind turbines, in the sea area where the deep-sea wind turbines are located, and in the soil to collect raw data and environmental data. The collected raw data and environmental data are transmitted to the offshore platform and the land control center for processing and analysis, respectively; a grounding grid status assessment model and a fault prediction model are constructed. The electrical parameters of the grounding grid are calculated in real time using a digital twin model of the grounding grid of a deep-sea wind farm. The grounding grid status is comprehensively assessed in real time based on the grounding grid status assessment model. Based on the fault prediction model and historical data, fault diagnosis and location are performed on the grounding grid status.

2. The method for monitoring the grounding grid status of deep-sea wind turbines based on digital twins according to claim 1, characterized in that, The digital twin model of the grounding grid of the deep-sea wind farm includes a three-dimensional geometric model built based on the acquired grounding grid design drawings and construction data, and a physical model established based on the electrical characteristic parameters of the materials used in the grounding grid to simulate the distribution of current in the grounding grid. The digital twin model of the grounding grid of the deep-sea wind farm is connected to the collected data in real time, and the parameters of the digital twin model of the grounding grid of the deep-sea wind farm are dynamically updated according to the data collected by the sensors.

3. The method for monitoring the grounding grid status of deep-sea wind turbines based on digital twins according to claim 2, characterized in that, The three-dimensional geometric model is used to describe the shape, size, connection relationship of each component, and layout in space of the grounding grid, including the length, diameter, and burial depth of the grounding conductor, as well as the specifications and orientation of the connecting conductors.

4. The method for monitoring the grounding grid status of deep-sea wind turbines based on digital twins according to claim 1, characterized in that, Four-wire resistance sensors are installed at each grounding electrode of the deep-sea wind turbine grounding grid in contact with the soil, electrochemical corrosion sensors are installed at the joints of the connecting conductors, and fiber optic temperature sensors are installed at the current concentration nodes that are prone to overheating.

5. The method for monitoring the grounding grid status of deep-sea wind turbines based on digital twins according to claim 1, characterized in that, Temperature and humidity sensors and salinity sensors are installed at a set distance from the grounding grid of the deep-sea wind turbine in the sea area where the grounding grid is located; soil resistivity sensors are buried in the soil around the grounding grid of the deep-sea wind turbine.

6. The method for monitoring the grounding grid status of deep-sea wind turbines based on digital twins according to claim 1, characterized in that, The method includes an offshore platform deployed in the deep sea and a land control center deployed on land. The offshore platform is equipped with edge computing devices, and the land control center is equipped with a data processing center of a cloud computing platform. The offshore platform and the land-based control center transmit data via a satellite communication link; The raw data collected by the sensors is transmitted to the data acquisition terminal on the offshore platform via submarine fiber optic cables.

7. A method for monitoring the grounding grid status of a deep-sea wind turbine based on digital twins as described in claim 6, characterized in that, After receiving the data, the cloud computing platform preprocesses the raw data collected by the sensor. The edge computing device runs an edge computing algorithm to perform preliminary analysis on the data, filter out abnormal data, and transmit the key information of the abnormal data to the cloud computing platform. The cloud computing platform utilizes big data processing technology and machine learning algorithms to perform in-depth data mining and establish grounding grid status assessment models and fault prediction models.

8. A method for monitoring the status of grounding grids of deep-sea wind turbines based on digital twins according to claim 1, characterized in that, The inputs to the grounding grid condition assessment model are the three-dimensional geometric model of the grounding grid, electrical parameters and environmental data, and the outputs are the grounding resistance of the grounding grid, the current distribution in the grounding body, the contact voltage and step voltage of the deep-sea wind turbine platform, the voltage difference between various devices on the deep-sea wind turbine platform and the degree of electrochemical corrosion of the grounding grid. The inputs to the grounding grid fault prediction model are the three-dimensional geometric model of the grounding grid, electrical parameters, and environmental data. The outputs are the grounding resistance variation trend and risk prediction of the grounding grid, suspected fault points of the grounding grid, corrosion rate prediction of the grounding body, and fault causes.

9. A method for monitoring the status of grounding grids of deep-sea wind turbines based on digital twins according to claim 1, characterized in that, The process of comprehensive real-time status assessment includes: The digital twin model of the grounding grid of the deep-sea wind power generation field calculates the electrical parameters of the grounding grid in real time, compares the calculation results with the preset standard values, and judges it as abnormal when the grounding resistance exceeds the set threshold of the standard value and issues an early warning signal. Taking into account parameters such as temperature and corrosion rate of grounding electrode, the condition of grounding grid is comprehensively evaluated in real time. When an abnormality is detected in the grounding grid, the simulation results are compared with the actual monitoring data, and the cause of the fault is determined using the grounding grid condition assessment model.

10. A method for monitoring the status of grounding grids of deep-sea wind turbines based on digital twins according to claim 1, characterized in that, Using time series analysis and deep learning models, historical grounding resistance data of grounding grids are analyzed to predict the changing trends of grounding resistance and corrosion rate of grounding bodies in the next month; the fault prediction model is then corrected by incorporating changes in environmental parameters caused by seasonal variations. Historical data includes electrical parameters, environmental parameters, and maintenance records.

Images