Meteorological monitoring method and system for offshore wind plant

Abstract

The invention discloses a meteorological monitoring method and system for an offshore wind power plant, and particularly relates to the field of meteorological risk assessment, and the method comprises the steps: arranging a plurality of meteorological sensors in a wind power plant, and enabling the plurality of meteorological sensors to be used for collecting the meteorological data of wind speed, air pressure, humidity and wave height in real time, the meteorological data is transmitted to an edge calculation unit through a wireless communication protocol, and the delay time of the meteorological data transmission does not exceed the upper limit value of a preset threshold value; and receiving and processing the meteorological data through an edge calculation unit, wherein the processing comprises calculating a meteorological risk grid in the wind power plant region based on the meteorological data. By arranging a plurality of meteorological sensors and combining the edge calculation unit to carry out real-time data processing, a data transmission path is optimized, and the delay problem caused by satellite signal attenuation, equipment failure and unstable communication link under extreme weather conditions is solved.

Description

Technical Field

[0001] This invention relates to the field of meteorological risk assessment technology, and more specifically, to a meteorological monitoring method and system for offshore wind farms. Background Technology

[0002] During the operation of offshore wind farms, information transmission delays under extreme weather conditions have become a key bottleneck restricting safety management and emergency response. Traditional meteorological monitoring systems mainly rely on equipment such as satellite remote sensing, weather buoys, and weather stations for data collection. These devices may face problems such as signal attenuation, equipment failure, or data transmission interruption under extreme weather conditions, resulting in information transmission delays. For example, during extreme weather events such as typhoons or rainstorms, satellite signals may be affected by ionospheric disturbances, leading to data transmission delays or loss. Furthermore, offshore wind farms are typically located far from land, making the construction and maintenance of communication links costly. In severe weather conditions, the stability and reliability of these links decrease, further exacerbating information transmission delays. These delays can prevent wind farm management systems from obtaining real-time meteorological data in a timely manner, thus affecting equipment status monitoring and emergency decision-making. For example, if accurate wind speed and direction data are not obtained in time before a typhoon strikes, wind turbines may not be shut down in the shortest possible time, increasing the risk of equipment damage. Therefore, information transmission delays not only affect the safe operation of wind farms but can also lead to economic losses and personal injury. The core issue is that under extreme weather conditions, traditional meteorological monitoring systems for offshore wind farms face problems such as signal attenuation, equipment failure, and unstable communication links, leading to information transmission delays and consequently affecting the timeliness and effectiveness of safety management and emergency response. Summary of the Invention

[0003] To overcome the aforementioned deficiencies of the prior art, embodiments of the present invention provide a meteorological monitoring method and system for offshore wind farms. By deploying multiple meteorological sensors and combining them with edge computing units for real-time data processing, the data transmission path is optimized, overcoming delay problems caused by satellite signal attenuation, equipment failure, and unstable communication links under extreme weather conditions, thereby solving the problems mentioned in the background art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a meteorological monitoring method for offshore wind farms, comprising: S1: Multiple meteorological sensors are deployed in the wind farm. The multiple meteorological sensors are used to collect meteorological data such as wind speed, air pressure, humidity and wave height in real time. The meteorological data is transmitted to the edge computing unit through a wireless communication protocol. The delay time of the meteorological data transmission does not exceed the upper limit of a preset threshold. S2: Meteorological data is received and processed through the edge computing unit. The processing includes calculating a meteorological risk grid within the wind farm area based on the meteorological data. The meteorological risk grid generates the probability of meteorological anomalies in each area based on real-time meteorological data and outputs local meteorological disaster early warning information. S3: By combining the real-time operating status of wind farm equipment with the edge computing unit, a weighted prediction algorithm is used to calculate the risk level of each equipment or work location. The risk level is generated based on meteorological data and equipment status. A risk assessment report for each equipment is output based on the risk level. S4: The generated meteorological disaster early warning information and risk assessment report are transmitted to the wind farm control center in real time through the communication network. The communication network automatically selects the best transmission path according to real-time meteorological changes to ensure that the information transmission delay does not exceed the lower limit of the preset threshold. S5: After receiving disaster early warning information and risk assessment reports, the wind farm control center generates emergency response instructions and transmits them to on-site personnel and equipment in real time via wireless communication or satellite signals.

[0005] In a preferred embodiment, S1 includes: S1-1: Multiple meteorological sensors are deployed within the wind farm. These sensors are used to collect meteorological data on wind speed, air pressure, humidity, and wave height in real time. The meteorological data is transmitted to a predetermined receiving end via a wireless communication protocol. The delay time during transmission is recorded in real time and compared with the upper limit of a preset threshold. S1-2: After receiving meteorological data, the data transmission delay time is first compared with the upper limit of the preset threshold. If the transmission delay time does not exceed the upper limit of the preset threshold, the synchronous calculation of the meteorological data is performed. The calculation result includes the analysis of the current meteorological state, and the obtained analysis data is stored for subsequent use. S1-3: If the transmission delay of meteorological data exceeds the upper limit of the preset threshold, then according to the current transmission conditions and network status, select an alternative transmission path and restart data transmission until the transmission delay of the meteorological data meets the real-time requirements. S1-4: After retransmitting the data, check the data transmission delay time again and confirm whether the transmission delay time meets the upper limit of the preset threshold; if it meets the requirements, perform subsequent meteorological data processing; if it still does not meet the requirements, continue to perform the transmission retransmission process.

[0006] In a preferred embodiment, S2 includes: S2-1: Receive real-time meteorological data collected by various meteorological sensors in the wind farm through the edge computing unit; firstly, perform data cleaning on the meteorological data, including removing outliers, filling in missing data, and performing time synchronization processing on the data from different sensors; S2-2: Distribute the cleaned meteorological data into multiple grid cells within the wind farm area. Each grid cell represents an area within the wind farm. The meteorological data for each grid cell includes real-time values ​​of wind speed, air pressure, humidity, and wave height within that area. Calculate the deviation between the meteorological data in each grid cell and the historical meteorological data for that area, and calculate the probability of meteorological anomalies occurring in that area based on the deviation. S2-3: For each grid cell, the probability of meteorological anomalies occurring in the region is calculated through edge computing cells: the standard deviations of wind speed, air pressure, humidity, and wave height are calculated to reflect the fluctuation range of meteorological variables; based on the deviation between current meteorological data and historical data, the probability of anomalies occurring in the region under current meteorological conditions is calculated. S2-4: Combining the calculation results of all grid cells, the edge computing unit generates a meteorological risk grid within the wind farm area. The meteorological risk grid displays the probability of meteorological anomalies occurring in each area and the corresponding risk level. The risk level of each grid cell is a quantification of the probability value of meteorological anomalies occurring in that area, providing a risk assessment for each area.

[0007] In a preferred embodiment, S2 further includes: S2-5: The edge computing unit outputs local meteorological disaster early warning information based on the meteorological risk grid; the early warning information includes: the specific probability of meteorological anomalies occurring in each region, the possible types of meteorological disasters in the region, and the corresponding risk level; the early warning information will be used for subsequent equipment protection and personnel safety management.

[0008] In a preferred embodiment, in S3, the definition is... The risk level of the i-th equipment or work location. The range is [0, 1]: in Let be the wind speed value at the location of the i-th device at time t; Let be the wind speed value at the location of the i-th device at the previous time t-1; is the standard deviation of the wind speed in the area where the i-th device is located, in meters per second (m / s). Let be the air pressure value at the location of the i-th device at time t; The length of the time window; Let be the state factor of the j-th device at time t for the i-th device; The normalization factor for the j-th device state factor; and These represent the start and end times of the air pressure data, respectively; n represents the total number of devices.

[0009] In a preferred embodiment, S4 includes: S4-1: Receives meteorological disaster early warning information and risk assessment reports generated by the edge computing unit, and converts them into standardized data packets so that the data format of the data packets meets the transmission requirements of the communication network; S4-2: Based on real-time meteorological data, assess the current status of the communication network, including network bandwidth, signal strength, and latency. Normalize each status and calculate the transmission latency of each available transmission path according to the preset weight allocation. S4-3: Based on real-time weather changes, select a communication path with a transmission delay lower than a preset threshold for transmitting meteorological disaster early warning information and risk assessment reports, so that the transmission delay time does not exceed the lower limit of the preset threshold. S4-4: Transmit early warning information and risk assessment reports to the wind farm control center in real time through the selected optimal communication path, monitor the transmission process, and re-evaluate and switch the transmission path if the transmission is interrupted.

[0010] In a preferred embodiment, S5 includes: S5-1: After receiving disaster warning information and risk assessment reports, the wind farm control center first verifies the received data and, based on the risk level and equipment status information in the risk assessment report, allocates the priority of emergency response in combination with the actual operational needs of the wind farm. S5-2: Generate emergency response instructions based on the equipment layout, personnel distribution, and real-time meteorological data of the wind farm; the emergency response instructions include operational instructions for equipment shutdown, personnel evacuation, and vessel evacuation, and determine the timing and execution order of the response according to the urgency of the instructions and the equipment status; S5-3: Transmits generated emergency response instructions to on-site personnel and equipment in real time via wireless communication or satellite signals, monitors the reception of emergency response instructions, and selects an alternative communication path and retransmits if transmission fails.

[0011] A meteorological monitoring system for offshore wind farms includes a data acquisition module, a processing module, a risk assessment module, an information transmission optimization module, and an emergency response module. The data acquisition module is used to deploy multiple meteorological sensors in the wind farm. The multiple meteorological sensors are used to collect meteorological data such as wind speed, air pressure, humidity and wave height in real time. The meteorological data is transmitted to the edge computing unit through a wireless communication protocol. The delay time of the meteorological data transmission does not exceed the upper limit of a preset threshold. The processing module receives and processes meteorological data through the edge computing unit. The processing includes calculating a meteorological risk grid within the wind farm area based on the meteorological data; the meteorological risk grid generates the probability of meteorological anomalies in each area based on real-time meteorological data, and outputs local meteorological disaster early warning information. The risk assessment module uses an edge computing unit to combine the real-time operating status of wind farm equipment and employs a weighted prediction algorithm to calculate the risk level of each piece of equipment or work location. The risk level is calculated and generated based on meteorological data and equipment status, and a risk assessment report for each piece of equipment is output based on the risk level. The information transmission optimization module transmits the generated meteorological disaster early warning information and risk assessment report to the wind farm control center in real time through the communication network. The communication network automatically selects the best transmission path according to real-time meteorological changes to ensure that the information transmission delay does not exceed the lower limit of a preset threshold. The emergency module is used to generate emergency response instructions after the wind farm control center receives disaster early warning information and risk assessment reports, and transmits them to on-site personnel and equipment in real time via wireless communication or satellite signals.

[0012] The technical effects and advantages of this invention are as follows: This solution optimizes communication path selection to ensure that the delay time of meteorological data transmission does not exceed a preset threshold under extreme weather conditions. It solves problems such as signal attenuation, equipment failure and link instability, improves the emergency response time of offshore wind farms, ensures the timeliness and accuracy of information transmission, and enhances safety management capabilities. The solution introduces edge computing units to process meteorological data in real time on-site, avoiding reliance on remote data centers and improving the reliability of the wind farm meteorological monitoring system. Under severe weather conditions, the edge computing units can analyze data and generate early warning information in real time, effectively reducing information transmission delays and improving the response speed of emergency decisions. The plan assesses risk levels by integrating real-time meteorological data and equipment status, and uses a weighted prediction algorithm to calculate the risk of each piece of equipment or work location, providing a scientific basis for wind farm equipment protection and decision-making, and ensuring timely response. Based on the meteorological risk grid, local meteorological disaster early warning information is generated, and emergency response instructions are generated in combination with equipment layout and personnel distribution. This mechanism ensures that wind farms can respond in a timely manner under extreme weather conditions, optimizes the execution of personnel evacuation, equipment protection and risk avoidance instructions, and improves the efficiency and safety of on-site management. By generating early weather warnings and emergency response instructions, the solution reduces the risk of equipment downtime and damage. Attached Figure Description

[0013] Figure 1 This is a flowchart of the method steps of the present invention.

[0014] Figure 2 This is a schematic diagram of the system modules of the present invention. Detailed Implementation

[0015] 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 embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] Refer to the instruction manual appendix Figure 1-2 An embodiment of the present invention provides a meteorological monitoring method for offshore wind farms, comprising: S1: Multiple meteorological sensors are deployed in the wind farm. The multiple meteorological sensors are used to collect meteorological data such as wind speed, air pressure, humidity and wave height in real time. The meteorological data is transmitted to the edge computing unit through a wireless communication protocol. The delay time of the meteorological data transmission does not exceed the upper limit of a preset threshold. S2: Meteorological data is received and processed through the edge computing unit. The processing includes calculating a meteorological risk grid within the wind farm area based on the meteorological data. The meteorological risk grid generates the probability of meteorological anomalies in each area based on real-time meteorological data and outputs local meteorological disaster early warning information. S3: By combining the real-time operating status of wind farm equipment with the edge computing unit, a weighted prediction algorithm is used to calculate the risk level of each equipment or work location. The risk level is generated based on meteorological data and equipment status. A risk assessment report for each equipment is output based on the risk level. S4: The generated meteorological disaster early warning information and risk assessment report are transmitted to the wind farm control center in real time through the communication network. The communication network automatically selects the best transmission path according to real-time meteorological changes to ensure that the information transmission delay does not exceed the lower limit of the preset threshold. S5: After receiving disaster early warning information and risk assessment reports, the wind farm control center generates emergency response instructions and transmits them to on-site personnel and equipment in real time via wireless communication or satellite signals.

[0017] S1 includes: S1-1: Multiple meteorological sensors are deployed within the wind farm. These sensors are used to collect meteorological data on wind speed, air pressure, humidity, and wave height in real time. The meteorological data is transmitted to a predetermined receiving end via a wireless communication protocol. The delay time during transmission is recorded in real time and compared with the upper limit of a preset threshold. S1-2: Upon receiving meteorological data, the data transmission delay time is first compared with the upper limit of a preset threshold. If the transmission delay time does not exceed the upper limit of the preset threshold, synchronous calculation of the meteorological data is performed. The calculation results include an analysis of the current meteorological state, and the obtained analysis data is stored for later use. Synchronous calculation refers to the process by which the edge computing unit processes and analyzes the received meteorological data in real time. First, data such as wind speed, air pressure, humidity, and wave height from different meteorological sensors are integrated into a unified dataset through data fusion, ensuring temporal consistency and data integrity. Then, a mathematical model is used to update the meteorological data in real time, calculate the current meteorological state, such as wind speed change trends and air pressure fluctuations, and perform anomaly detection. By comparing with historical data, possible meteorological anomalies are identified, and potential extreme meteorological events are predicted. Next, through comprehensive analysis of the meteorological state, a meteorological state report is output, including information such as the meteorological risk level of each region and weather conditions affecting equipment and operations, providing a basis for subsequent decision-making. The final calculation results not only include quantitative analysis data but also form meteorological maps and risk maps to support meteorological monitoring and emergency response in wind farms. S1-3: If the transmission delay of meteorological data exceeds the upper limit of a preset threshold, an alternative transmission path is selected based on the current transmission conditions and network status, and data transmission is restarted until the transmission delay of the meteorological data meets the real-time requirements. The transmission conditions and network status include current network bandwidth, signal strength, network latency, communication link stability, and potential interference factors, all of which jointly affect data transmission efficiency and latency. Alternative transmission paths include other available communication links, such as different satellite signal channels, radio signal channels, or fiber optic links. When selecting an alternative transmission path, the system evaluates the availability and reliability of each path based on real-time network status (such as bandwidth, latency, and signal strength), prioritizing the path with the lowest latency and highest stability for data transmission. S1-4: After retransmitting the data, check the data transmission delay time again and confirm whether the transmission delay time meets the upper limit of the preset threshold; if it meets the requirements, perform subsequent meteorological data processing; if it still does not meet the requirements, continue to perform the transmission retransmission process to ensure that the timeliness of the meteorological data meets the needs of subsequent analysis and early warning processing.

[0018] S2 includes: S2-1: Receive real-time meteorological data from various meteorological sensors within the wind farm via the edge computing unit; firstly, perform data cleaning on the meteorological data, including removing outliers, filling in missing data, and performing time synchronization processing on data from different sensors to ensure the timeliness and consistency of the data; S2-2: The cleaned meteorological data is distributed into multiple grid cells within the wind farm area, with each grid cell representing a region within the wind farm. The meteorological data for each grid cell includes real-time values ​​of wind speed, air pressure, humidity, and wave height within that region. The deviation between the meteorological data in each grid cell and the historical meteorological data for that region is calculated, and the probability of meteorological anomalies occurring in that region is calculated based on the deviation. Specifically, by calculating the deviation between the meteorological data and historical data for that region, and combining it with the standard deviation, statistical analysis methods (such as normal distribution or Bayesian inference) are used to assess the probability that the current deviation occurs within the historical fluctuation range, thereby deriving the probability of meteorological anomalies occurring. S2-3: For each grid cell, the probability of meteorological anomalies in the region is calculated using edge computing cells: the standard deviations of wind speed, air pressure, humidity, and wave height are calculated to reflect the fluctuation range of meteorological variables; based on the deviation between current meteorological data and historical data, the probability of an abnormal event occurring in the region under current meteorological conditions is calculated, and statistical methods are used to map this probability value to a risk level (risk levels include low, medium, and high); abnormal events include extreme wind speed or air pressure fluctuations; S2-4: Combining the calculation results of all grid cells, the edge computing unit generates a meteorological risk grid within the wind farm area. The meteorological risk grid displays the probability of meteorological anomalies occurring in each area and the corresponding risk level. The risk level of each grid cell is a quantification of the probability value of meteorological anomalies occurring in that area, providing a risk assessment for each area.

[0019] S2 also includes: S2-5: The edge computing unit outputs local meteorological disaster early warning information based on the meteorological risk grid; the early warning information includes: the specific probability of meteorological anomalies occurring in each region, the possible types of meteorological disasters in the region (such as high wind speed, large waves, etc.), and the corresponding risk level (such as mild, severe); the early warning information will be used for subsequent equipment protection and personnel safety management. It should also be noted that, in this solution, the edge computing unit refers to a dedicated computing device deployed at the wind farm site. Its main function is to process and analyze the data collected by meteorological sensors in real time. Specifically, the edge computing unit includes the following components: Hardware components include computing units (such as embedded processors, GPUs, FPGAs, etc.) for performing data processing, analysis, and storage tasks; storage units for caching and storing real-time data and intermediate calculation results; and network interface units for communicating with sensors and other devices. Data preprocessing module: First, the edge computing unit receives data from various meteorological sensors in the wind farm, performs data cleaning (such as noise removal and missing data filling) and synchronization processing to ensure that the transmitted data is error-free and has a consistent timestamp; Calculation Module: After data preprocessing, the edge computing unit performs real-time calculations according to preset calculation logic; for example, it uses the standard deviation calculation method to process the fluctuation range of meteorological data, and calculates the probability of meteorological anomalies occurring in the region based on the deviation between current meteorological data and historical data; the specific calculation process is as follows: Standard deviation calculation: Calculate the standard deviation of historical data for each meteorological parameter (such as wind speed, air pressure, humidity) to represent the range of fluctuations in historical meteorological conditions; Deviation calculation: By comparing the differences between current meteorological data and historical data, the deviation of meteorological variables in this region is calculated; Probability assessment: Based on the current deviation value and the standard deviation, statistical methods (such as normal distribution, chi-square distribution, etc.) are used to calculate the probability of the current meteorological conditions occurring within the historical fluctuation range, thereby obtaining the probability of meteorological anomalies occurring in the region; Early warning generation module: After calculating the probability of meteorological anomalies in each region, the edge computing unit converts them into risk levels according to the set threshold, generates local meteorological disaster early warning information, and outputs the results to the wind farm control system to notify relevant personnel to carry out emergency response. Through this computational logic, the edge computing unit can calculate, process, and analyze meteorological data in real time at the wind farm site, generating accurate meteorological risk assessments and providing real-time basis for subsequent decision-making.

[0020] It should be noted that in the formula structure involved in this scheme, dimensionless terms can be used as proportional or structural adjustment factors. When combined with quantities with units, they only play a role in numerical scaling and do not introduce new physical dimensions. Therefore, they will not change or confuse the overall unit system. This combination of "dimensionless terms and terms with units" can be understood as a composite structural expression commonly used in mathematical physics modeling. It conforms to the principle of dimensional consistency and has a clear physical interpretation basis. Secondly, in the formula structure of this scheme, if multiple variables with different physical units are involved, including but not limited to time, mass or energy variables, their joint appearance is to express the collaborative modeling relationship of multiple physical mechanisms. Each variable can form a unified structure through function mapping, ratio combination or normalization adjustment, with clear units and clear meaning. The overall expression conforms to the principle of dimensional consistency and the conventional formula of engineering modeling. In this solution, constants, weights, adjustment factors, threshold parameters, proportional coefficients, etc., are all adjustable control parameters for different application environments. Their values ​​depend on the target equipment configuration, data input characteristics, and performance optimization goals. During the implementation phase, they are set to converge within a reasonable range through model verification, performance constraints, or engineering calibration. Although these parameters do not have a unique preset value, they have clear adjustment logic and calculation paths. They belong to the deterministic setting process in engineering implementation. The purpose of this setting is to ensure that the solution is both universally adaptable and reproducible and operable, without affecting its technical clarity and feasibility. In S3, define The risk level of the i-th equipment or work location. The value range is [0, 1], representing the risk level of the equipment or work location under the current weather conditions. The closer to 1, the higher the risk. in Let be the wind speed at the location of the i-th device at time t, in meters per second (m / s). The wind speed at the location of the i-th device at the previous time t-1 is expressed in meters per second (m / s). Let be the standard deviation of the wind speed in the area where the i-th device is located, in meters per second (m / s). Used to measure the amplitude of wind speed fluctuations and reflect the degree of abnormality in wind speed changes; Let be the air pressure value at the location of the i-th device at time t, in Pascals (Pa). The length of the time window is expressed in seconds (s). Within this time window, the contribution of air pressure changes to the risk level is calculated. Let be the state factor of the i-th device at time t. The state factor of a device represents the real-time health status of the device, and the unit is a dimensionless value. The state factor of a device includes indicators that affect the status of the device, such as the device speed, load, and failure rate. This is the standardization factor for the j-th equipment status factor, ensuring a uniform range of equipment status values, with the unit being a dimensionless value. and These represent the start and end times of the air pressure data, respectively; n represents the total number of devices. The calculation process is explained below: 1. Impact of Wind Speed ​​Changes: Calculate the difference between the current wind speed and the wind speed at the previous moment, and reflect the impact of wind speed changes on equipment risk using a Gaussian function (exponential decay form); the more drastic the wind speed change, the higher the risk level; this is achieved through the following method: in, The calculation is the wind speed over time. and The range of variation between them, standard deviation Represents the range of wind speed fluctuations; 2. Impact of air pressure changes: The impact of air pressure changes on equipment risk is calculated by using an integral method to accumulate air pressure fluctuations within a time window. This integral represents the time period. Internally, the long-term impact of air pressure changes on equipment; air pressure changes will have a continuous impact on equipment, especially under extreme weather conditions, when air pressure fluctuations are large, the operational stability of the equipment will be affected; 3. Impact of Equipment Health Status: By calculating the health status factors for each piece of equipment, the contribution of equipment operating status to risk is assessed. Equipment status factors include equipment speed, load, failure rate, etc., reflecting the real-time health status of the equipment. The impact of equipment status is calculated using the following formula: This calculation sums up all equipment health status factors to reflect the comprehensive impact of equipment operating status on risk level; Comprehensive Risk Assessment: Finally, wind speed changes, air pressure changes, and equipment health status factors are combined according to the above formula to generate a comprehensive risk level for the equipment or work location. The higher the risk level value, the greater the risk faced by the equipment or location, and the higher the probability of equipment failure or damage. Risk assessment report: Risk level obtained through calculation The edge computing unit outputs a risk assessment report, which includes the risk level of each device or work location; possible types of failures; the potential probability of equipment damage; and early warning information for specific risk levels, providing wind farm managers with real-time and accurate risk data support.

[0021] S4 includes: S4-1: Receives meteorological disaster early warning information and risk assessment reports generated by the edge computing unit, and converts them into standardized data packets so that the data format of the data packets meets the transmission requirements of the communication network; S4-2: Based on real-time meteorological data, assess the current status of the communication network, including network bandwidth, signal strength, and latency. Normalize each status and calculate the transmission latency of each available transmission path according to the preset weight allocation. S4-3: Based on real-time weather changes, select a communication path with a transmission delay lower than a preset threshold for transmitting meteorological disaster early warning information and risk assessment reports, so that the transmission delay time does not exceed the lower limit of the preset threshold. S4-4: Transmit early warning information and risk assessment reports to the wind farm control center in real time through the selected optimal communication path, monitor the transmission process, ensure data integrity and timeliness, and re-evaluate and switch the transmission path if the transmission is interrupted.

[0022] S5 includes: S5-1: After receiving disaster warning information and risk assessment reports, the wind farm control center first verifies the received data and, based on the risk level and equipment status information in the risk assessment report, allocates the priority of emergency response in combination with the actual operational needs of the wind farm. S5-2: Based on the equipment layout, personnel distribution, and real-time meteorological data of the wind farm, emergency response instructions are generated. These instructions include operational commands for equipment shutdown, personnel evacuation, and vessel evacuation, and the timing and execution order of the response are determined according to the urgency of the instructions and the equipment status. The process of generating emergency response instructions based on the wind farm's equipment layout, personnel distribution, and real-time meteorological data involves a comprehensive analysis of multiple factors. First, the system acquires the wind farm's equipment layout information, including the location, operating status, load conditions, and equipment failure history of each device. Then, real-time meteorological data (such as wind speed, air pressure, humidity, and wave height) is used for evaluation. The system assesses the impact of current weather conditions on equipment and personnel safety, especially in extreme weather conditions, evaluating which equipment may face a higher risk of failure or operational interruption. Then, based on the distribution of personnel within the wind farm (such as the location of operators and maintenance personnel) and weather risks, the system generates specific evacuation or shelter instructions to ensure that personnel can be quickly evacuated to safe areas. Finally, by integrating this information, the system generates priority-based emergency response instructions, such as shutdown instructions, equipment protection instructions, personnel evacuation instructions, and vessel shelter instructions, ensuring that the timeliness and execution order of the instructions meet the actual needs of wind farm emergency response and protect the safety of equipment and personnel. S5-3: Transmits generated emergency response instructions to on-site personnel and equipment in real time via wireless communication or satellite signals, ensuring that the instruction transmission is not affected by extreme weather or communication interference, monitoring the reception of emergency response instructions, and selecting an alternative communication path and transmitting again if transmission fails.

[0023] A meteorological monitoring system for offshore wind farms includes a data acquisition module, a processing module, a risk assessment module, an information transmission optimization module, and an emergency response module. The data acquisition module is used to deploy multiple meteorological sensors in the wind farm. The multiple meteorological sensors are used to collect meteorological data such as wind speed, air pressure, humidity and wave height in real time. The meteorological data is transmitted to the edge computing unit through a wireless communication protocol. The delay time of the meteorological data transmission does not exceed the upper limit of a preset threshold. The processing module receives and processes meteorological data through the edge computing unit. The processing includes calculating a meteorological risk grid within the wind farm area based on the meteorological data; the meteorological risk grid generates the probability of meteorological anomalies in each area based on real-time meteorological data, and outputs local meteorological disaster early warning information. The risk assessment module uses an edge computing unit to combine the real-time operating status of wind farm equipment and employs a weighted prediction algorithm to calculate the risk level of each piece of equipment or work location. The risk level is calculated and generated based on meteorological data and equipment status, and a risk assessment report for each piece of equipment is output based on the risk level. The information transmission optimization module transmits the generated meteorological disaster early warning information and risk assessment report to the wind farm control center in real time through the communication network. The communication network automatically selects the best transmission path according to real-time meteorological changes to ensure that the information transmission delay does not exceed the lower limit of a preset threshold. The emergency module is used to generate emergency response instructions after the wind farm control center receives disaster early warning information and risk assessment reports, and transmits them to on-site personnel and equipment in real time via wireless communication or satellite signals.

[0024] Working principle: This invention relates to a meteorological monitoring method for offshore wind farms, which aims to ensure the safe operation of wind farms through real-time meteorological data collection, risk assessment, and emergency response mechanisms; First, multiple meteorological sensors are deployed within the wind farm to collect data such as wind speed, air pressure, humidity, and wave height in real time. This data is transmitted to the edge computing unit via a wireless communication protocol to ensure that the data transmission delay does not exceed a preset threshold. After receiving the meteorological data, the edge computing unit processes it in real time, generates a meteorological risk grid within the wind farm area, calculates the probability of meteorological anomalies in each area, and outputs local meteorological disaster early warning information. Next, the edge computing unit, combined with the real-time operating status of the wind farm equipment, uses a weighted prediction algorithm to calculate the risk level of each piece of equipment or work location and generates a risk assessment report for each piece of equipment. These meteorological disaster warnings and risk assessment reports are transmitted to the wind farm control center in real time through the communication network. The communication network automatically selects the best transmission path based on real-time weather changes to ensure that the information transmission delay does not exceed the lower limit of the preset threshold. After receiving the disaster warning information, the wind farm control center generates emergency response instructions, including operations such as equipment shutdown, personnel evacuation, and vessel avoidance. These instructions are transmitted to on-site personnel and equipment in real time via wireless communication or satellite signals to ensure that emergency instructions can be executed in a timely and effective manner. During the data acquisition phase, meteorological sensors are deployed to acquire real-time meteorological data such as wind speed, air pressure, humidity, and wave height, which are then transmitted to the edge computing unit for processing. Data processing includes cleaning and synchronous calculation of meteorological data, and risk assessment is performed in conjunction with historical meteorological data. If the transmission delay exceeds the upper limit of a preset threshold, the edge computing unit will select an alternative transmission path based on network conditions and restart data transmission to ensure data timeliness. The processed meteorological data will be used to generate a meteorological risk grid for the wind farm area and the probability of meteorological anomalies in each area, while also outputting corresponding disaster warning information. In the risk assessment phase, the edge computing unit combines real-time meteorological data and equipment status to calculate the risk level of each device using a weighted prediction algorithm, and then outputs a risk assessment report for the device. This information will be transmitted to the wind farm control center in real-time through optimized transmission paths. After receiving the early warning information, the control center combines the equipment layout, personnel distribution and meteorological data of the wind farm to generate priority emergency response instructions, and ensures that the instructions can be transmitted to on-site personnel and equipment in a timely manner via wireless communication or satellite signals; if the transmission fails, the system will automatically switch to the backup communication path to ensure that the instructions can be delivered to the site without delay. By fully integrating meteorological data acquisition, real-time processing, risk assessment, and emergency response functions, dynamic monitoring and emergency response of wind farms under extreme weather conditions have been achieved, ensuring the safety of equipment and personnel.

[0025] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A meteorological monitoring method for offshore wind farms, characterized in that, include: S1: Multiple meteorological sensors are deployed in the wind farm. The multiple meteorological sensors are used to collect meteorological data such as wind speed, air pressure, humidity and wave height in real time. The meteorological data is transmitted to the edge computing unit through a wireless communication protocol. The delay time of the meteorological data transmission does not exceed the upper limit of a preset threshold. S2: Meteorological data is received and processed through the edge computing unit. The processing includes calculating a meteorological risk grid within the wind farm area based on the meteorological data. The meteorological risk grid generates the probability of meteorological anomalies in each area based on real-time meteorological data and outputs local meteorological disaster early warning information. S3: By combining the real-time operating status of wind farm equipment with the edge computing unit, a weighted prediction algorithm is used to calculate the risk level of each equipment or work location. The risk level is generated based on meteorological data and equipment status. A risk assessment report for each equipment is output based on the risk level. S4: The generated meteorological disaster early warning information and risk assessment report are transmitted to the wind farm control center in real time through the communication network. The communication network automatically selects the best transmission path according to real-time meteorological changes to ensure that the information transmission delay does not exceed the lower limit of the preset threshold. S5: After receiving disaster early warning information and risk assessment reports, the wind farm control center generates emergency response instructions and transmits them to on-site personnel and equipment in real time via wireless communication or satellite signals.

2. The meteorological monitoring method for offshore wind farms according to claim 1, characterized in that: S1 includes: S1-1: Multiple meteorological sensors are deployed within the wind farm. These sensors are used to collect meteorological data on wind speed, air pressure, humidity, and wave height in real time. The meteorological data is transmitted to a predetermined receiving end via a wireless communication protocol. The delay time during transmission is recorded in real time and compared with the upper limit of a preset threshold. S1-2: After receiving meteorological data, the data transmission delay time is first compared with the upper limit of the preset threshold. If the transmission delay time does not exceed the upper limit of the preset threshold, the synchronous calculation of the meteorological data is performed. The calculation result includes the analysis of the current meteorological state, and the obtained analysis data is stored for subsequent use. S1-3: If the transmission delay of meteorological data exceeds the upper limit of the preset threshold, then according to the current transmission conditions and network status, select an alternative transmission path and restart data transmission until the transmission delay of the meteorological data meets the real-time requirements. S1-4: After retransmitting the data, check the data transmission delay time again and confirm whether the transmission delay time meets the upper limit of the preset threshold; if it meets the requirements, perform subsequent meteorological data processing; if it still does not meet the requirements, continue to perform the transmission retransmission process.

3. The meteorological monitoring method for offshore wind farms according to claim 2, characterized in that: S2 includes: S2-1: Receive real-time meteorological data collected by various meteorological sensors in the wind farm through the edge computing unit; firstly, perform data cleaning on the meteorological data, including removing outliers, filling in missing data, and performing time synchronization processing on the data from different sensors; S2-2: Distribute the cleaned meteorological data into multiple grid cells within the wind farm area. Each grid cell represents an area within the wind farm. The meteorological data for each grid cell includes real-time values ​​of wind speed, air pressure, humidity, and wave height within that area. Calculate the deviation between the meteorological data in each grid cell and the historical meteorological data for that area, and calculate the probability of meteorological anomalies occurring in that area based on the deviation. S2-3: For each grid cell, the probability of meteorological anomalies occurring in the region is calculated through edge computing cells: the standard deviations of wind speed, air pressure, humidity, and wave height are calculated to reflect the fluctuation range of meteorological variables; based on the deviation between current meteorological data and historical data, the probability of anomalies occurring in the region under current meteorological conditions is calculated. S2-4: Combining the calculation results of all grid cells, the edge computing unit generates a meteorological risk grid within the wind farm area. The meteorological risk grid displays the probability of meteorological anomalies occurring in each area and the corresponding risk level. The risk level of each grid cell is a quantification of the probability value of meteorological anomalies occurring in that area, providing a risk assessment for each area.

4. The meteorological monitoring method for offshore wind farms according to claim 3, characterized in that: S2 also includes: S2-5: The edge computing unit outputs local meteorological disaster early warning information based on the meteorological risk grid; the early warning information includes: the specific probability of meteorological anomalies occurring in each region, the possible types of meteorological disasters in the region, and the corresponding risk level; the early warning information will be used for subsequent equipment protection and personnel safety management.

5. A meteorological monitoring method for offshore wind farms according to claim 4, characterized in that: In S3, define The risk level of the i-th equipment or work location. The range is [0, 1]: in Let be the wind speed value at the location of the i-th device at time t; Let be the wind speed value at the location of the i-th device at the previous time t-1; is the standard deviation of the wind speed in the area where the i-th device is located, in meters per second (m / s). Let be the air pressure value at the location of the i-th device at time t; The length of the time window; Let be the state factor of the j-th device at time t for the i-th device; The normalization factor for the j-th device state factor; and These represent the start and end times of the air pressure data, respectively; n represents the total number of devices.

6. A meteorological monitoring method for offshore wind farms according to claim 5, characterized in that: S4 includes: S4-1: Receives meteorological disaster early warning information and risk assessment reports generated by the edge computing unit, and converts them into standardized data packets so that the data format of the data packets meets the transmission requirements of the communication network; S4-2: Based on real-time meteorological data, assess the current status of the communication network, including network bandwidth, signal strength, and latency. Normalize each status and calculate the transmission latency of each available transmission path according to the preset weight allocation. S4-3: Based on real-time weather changes, select a communication path with a transmission delay lower than a preset threshold for transmitting meteorological disaster early warning information and risk assessment reports, so that the transmission delay time does not exceed the lower limit of the preset threshold. S4-4: Transmit early warning information and risk assessment reports to the wind farm control center in real time through the selected optimal communication path, monitor the transmission process, and re-evaluate and switch the transmission path if the transmission is interrupted.

7. A meteorological monitoring method for offshore wind farms according to claim 6, characterized in that: S5 includes: S5-1: After receiving disaster warning information and risk assessment reports, the wind farm control center first verifies the received data and, based on the risk level and equipment status information in the risk assessment report, allocates the priority of emergency response in combination with the actual operational needs of the wind farm. S5-2: Generate emergency response instructions based on the equipment layout, personnel distribution, and real-time meteorological data of the wind farm; the emergency response instructions include operational instructions for equipment shutdown, personnel evacuation, and vessel evacuation, and determine the timing and execution order of the response according to the urgency of the instructions and the equipment status; S5-3: Transmits generated emergency response instructions to on-site personnel and equipment in real time via wireless communication or satellite signals, monitors the reception of emergency response instructions, and selects an alternative communication path and retransmits if transmission fails.

8. A meteorological monitoring system for offshore wind farms, comprising a data acquisition module, a processing module, a risk assessment module, an information transmission optimization module, and an emergency response module, characterized in that: The data acquisition module is used to deploy multiple meteorological sensors in the wind farm. The multiple meteorological sensors are used to collect meteorological data such as wind speed, air pressure, humidity and wave height in real time. The meteorological data is transmitted to the edge computing unit through a wireless communication protocol. The delay time of the meteorological data transmission does not exceed the upper limit of a preset threshold. The processing module receives and processes meteorological data through the edge computing unit. The processing includes calculating a meteorological risk grid within the wind farm area based on the meteorological data; the meteorological risk grid generates the probability of meteorological anomalies in each area based on real-time meteorological data, and outputs local meteorological disaster early warning information. The risk assessment module uses an edge computing unit to combine the real-time operating status of wind farm equipment and employs a weighted prediction algorithm to calculate the risk level of each piece of equipment or work location. The risk level is calculated and generated based on meteorological data and equipment status, and a risk assessment report for each piece of equipment is output based on the risk level. The information transmission optimization module transmits the generated meteorological disaster early warning information and risk assessment report to the wind farm control center in real time through the communication network. The communication network automatically selects the best transmission path according to real-time meteorological changes to ensure that the information transmission delay does not exceed the lower limit of a preset threshold. The emergency module is used to generate emergency response instructions after the wind farm control center receives disaster early warning information and risk assessment reports, and transmits them to on-site personnel and equipment in real time via wireless communication or satellite signals.

Images