Airport Available Runway Monitoring and Early Warning System and Method Based on Multi-Source Data Fusion

Abstract

The present invention provides an airport available runway monitoring and early warning system and method based on multi-source data fusion, which has strong real-time performance, good prediction effect and large monitoring range. The present invention includes a laser wind profiler (1), a CFD numerical simulation module (2), a mesoscale weather forecasting module (3), a machine learning model (4) and a system server (5); the method of the present invention is as follows: the system server performs data assimilation by combining the real-time wind shear detection data measured by the laser wind profiler and the forecast data at the current time point output by the mesoscale weather forecasting module, and then uses the CFD numerical simulation module to process the assimilated data, combines the terrain and building parameters near the airport, generates real-time sub-meter-level gridded three-dimensional wind field data, reconstructs the sub-meter-level three-dimensional wind field structure, so as to predict and early warn the future wind shear at the airport, and further perform available runway prediction. The present invention is applied to the technical field of wind field prediction and judgment.

Description

Technical Field

[0001] The present invention relates to the technical field of wind field prediction and judgment, and particularly to an airport available runway monitoring and early warning system and method based on multi-source data fusion formed by combining four technologies. Background Art

[0002] Wind shear refers to the change of wind vector in the horizontal and vertical directions. Wind shear over the airport can suddenly change the flight attitude of an aircraft, resulting in situations such as bumps, go-arounds, and crashes. Traditional airport wind shear monitoring methods mainly use various ground sensors to monitor wind shear, resulting in their inability to give early warnings for high-altitude wind shear. As a new type of wind field detection device using laser as the detection means, a laser wind profiler has high detection accuracy and spatial resolution, can scan the wind field at different heights over the airport, and can accurately monitor high-altitude wind shear. However, due to the limitations of its detection range and scanning method, it can only obtain limited wind field information within its scanning area, cannot form large-scale three-dimensional grid data, has insufficient monitoring ability for large-scale wind shear systems far from the airport, and does not have the function of forecasting. Therefore, in recent years, a method of combining CFD numerical simulation and mesoscale meteorological forecasting model (WRF) has gradually been applied to airport wind shear monitoring. However, due to the large amount of CFD calculations, only a three-dimensional wind field sample database can be established in advance, and then the sample with the highest matching degree is retrieved according to the current situation as the current three-dimensional wind field, which is not real-time calculation in the true sense and also limits its ability to develop and utilize the three-dimensional wind field data subsequently. Summary of the Invention

[0003] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art and provide an airport available runway monitoring and early warning system and method based on multi-source data fusion with strong real-time performance, good forecasting effect, and large monitoring range.

[0004] The technical solution adopted by the airport available runway monitoring and early warning system based on multi-source data fusion of the present invention is an airport available runway monitoring and early warning system based on multi-source data fusion, including

[0005] A laser wind profiler for detecting the wind field within a set range and at a set height and providing high-precision real-time wind shear detection data for the system;

[0006] A CFD numerical simulation module for forming high-precision grid wind field data through simulation calculation;

[0007] A mesoscale meteorological forecasting module for simulating future large-scale weather changes;

[0008] A machine learning model for improving the CFD calculation speed and predicting the available runway of the airport; and

[0009] A system server, which combines the real-time wind shear detection data measured by the lidar and the forecast data output by the mesoscale meteorological forecasting module, assimilates the real-time detection data with the forecast data at the current time point output by the mesoscale meteorological forecasting module, and then uses the CFD numerical simulation module to process the assimilated data. Combining the terrain and building parameters near the airport, it generates real-time sub-meter gridded three-dimensional wind field data and reconstructs the sub-meter three-dimensional wind field structure, so as to predict and warn of future wind shear at the airport, and further conduct available runway prediction.

[0010] A method for predicting the available runway of an airport using the above-mentioned airport available runway monitoring and warning system based on multi-source data fusion, the method comprising the following steps:

[0011] a. Deployment and data acquisition of lidar: Deploy the lidar at key positions in the airport and adjacent areas, calibrate the system and test the performance of the lidar to ensure its stable operation and accurate capture of atmospheric information, and then provide real-time, high-resolution real-time wind field scanning data to provide basic data support for the follow-up;

[0012] b. Calculation of future wind field data: Use the mesoscale meteorological forecasting module to simulate the future meteorological change trend in the area where the airport is located to obtain forecast data for a future period of time, and then use the inversion algorithm and the CFD numerical simulation module to process the forecast data. Combining the terrain and building parameters near the airport, conduct simulation calculations on the atmospheric state, and then generate sub-meter gridded three-dimensional wind field data of the airport at future times;

[0013] c. Calculation of real-time wind field data: After the system server receives and analyzes the real-time wind field scanning data sent by the lidar and the forecast data output by the mesoscale meteorological forecasting module, it assimilates the real-time wind field scanning data with the forecast data at the current time point output by the mesoscale meteorological forecasting module, and then uses the CFD numerical simulation module to process the assimilated data. Combining the terrain and building parameters near the airport, it generates real-time sub-meter gridded three-dimensional wind field data;

[0014] d. During the calculation of real-time wind field data, only use the CFD numerical simulation module to calculate the sub-meter gridded three-dimensional wind field data at key time points, and then combine the calculation results at key time points with the data obtained by the real-time detection of the lidar to drive the graph neural network calculation model, so as to quickly obtain real-time sub-meter gridded three-dimensional wind field data;

[0015] e. Wind shear detection: Extract the wind field data of the aircraft's descent to the ground from the three-dimensional wind field data at the current and selected future different times, calculate the wind shear data on the glide path, and then achieve wind shear early warning and forecasting;

[0016] f. Available runway judgment: Combine the three-dimensional wind field data at the current and selected future different times, as well as the external data collected by the airport, and use the random forest model in machine learning to judge the availability of the current runway and the availability of the future runway;

[0017] g. Early warning system construction: Deploy the early warning module to automatically trigger early warning notifications when detecting potential dangerous wind field conditions, ensuring that each user terminal can take corresponding measures in a timely manner.

[0018] In step b, the specific steps of processing the forecast data by using the inversion algorithm and the CFD numerical simulation module are as follows: Perform standardization processing on the forecast data output by the mesoscale meteorological forecast module, including time alignment, spatial interpolation, and format conversion, and unify it to the grid coordinate system compatible with the CFD numerical simulation module; Use the variational inversion algorithm to optimize the low-resolution forecast data, and fuse the statistical characteristics of the forecast data and the historical lidar observation data by minimizing the objective function to generate a high-resolution initial wind field input;

[0019] The specific steps of simulating and calculating the atmospheric state in combination with the terrain and building parameters near the airport to generate sub-meter grid three-dimensional wind field data of the airport at future times are as follows: Import the inverted high-resolution wind field data as the initial condition into the CFD numerical simulation module, and at the same time load the three-dimensional terrain model and building geometric parameters of the airport, and set the boundary condition as a dynamic pressure and velocity coupling field; Based on the Reynolds-averaged Navier-Stokes equation and the k-ε turbulence model, combined with the adaptive grid refinement technology, perform transient simulation calculations on the wind field in the airport area to solve for the three-dimensional wind speed components u, v, w and the turbulent kinetic energy distribution of the sub-meter grid nodes; Store the finally generated sub-meter grid three-dimensional wind field data in the spatio-temporal database of the system server for subsequent wind shear early warning and runway prediction module calls.

[0020] In step c, the specific steps of data assimilation of the real-time wind field scan data and the forecast data are as follows: Use the Newtonian relaxation data assimilation method to fuse the real-time wind field scan data into the WRF model of the mesoscale meteorological forecast module. The momentum equation of the assimilation principle is expressed as:

[0021] ,

[0022] ,

[0023] where ui is the component of vector u in the i direction, t is time, u j is the component of vector u in the j direction, v is the dynamic viscosity coefficient, x i is the coordinate component in the i direction, x j is the coordinate component in the j direction, ρ is density, p is pressure, f is the additional forcing term added according to the Nudging data assimilation method, u c is the detection velocity, u is the WRF forecast velocity, τ u is the Newtonian relaxation coefficient, W(x, y, z) is the weight function;

[0024] The specific steps for processing the real-time wind field scan data using the described CFD numerical simulation module and generating sub-meter gridded three-dimensional wind field data in combination with the terrain and building parameters near the airport are as follows: Integrate the real-time wind field scan data obtained by the lidar wind profiler with the meteorological data output by the mesoscale meteorological forecasting module to form a unified data format; Adapt the terrain and building parameters to the grid to ensure that the grid can accurately reflect the actual geographical and building environment of the airport and its surroundings; Set the boundary conditions around the airport according to the real-time wind field scan data; Use the CFD numerical simulation module to solve the three-dimensional Navier-Stokes equations and calculate the parameters of each grid point in combination with the terrain and building parameters.

[0025] In step d, the specific steps for calculating the sub-meter gridded three-dimensional wind field data at key time points using the CFD numerical simulation module are as follows: First, determine the key time points for key simulation according to the output data of the mesoscale meteorological forecasting module in combination with the airport operation requirements and historical wind shear event analysis; Then integrate the real-time wind field data obtained by the lidar wind profiler with the future meteorological forecasting data provided by the mesoscale meteorological forecasting module, including wind speed, wind direction, temperature, humidity, and air pressure; Then import the terrain data and building parameters of the airport and its surroundings to generate a sub-meter three-dimensional grid; Use the forecast data as boundary conditions and use the CFD numerical simulation module to solve the sub-meter gridded three-dimensional wind field data at key time points;

[0026] The specific steps for driving the graph neural network calculation model by combining the calculation results at key time points with the data obtained by the real-time detection of the lidar wind profiler to obtain the real-time sub-meter gridded three-dimensional wind field data are as follows: In wind field calculation, regard the wind field data as a graph structure, where nodes represent positions in space and edges represent the relationships between positions. The graph convolutional neural network of the graph neural network learns the representation of nodes by aggregating the features of nodes and their neighbors, thereby calculating the dynamic changes of the wind field. The calculation formula of the graph convolutional neural network is:

[0027] ,

[0028] Wherein:

[0029] is the feature vector of node v at the th layer, N(v) is the set of neighbor nodes of node v, and c ij is the normalized weight between node i and node j, and d v and d j are the degrees of node i and node j respectively, is the weight matrix of the th layer, and σ is the activation function.

[0030] In the e step, from the three-dimensional wind field data at different current and selected future times, extract the wind field data when the aircraft glides to the ground, calculate the wind shear data on the glide path, and the specific steps to realize wind shear warning and forecasting are as follows: extract the wind speed and wind direction on the glide path from the three-dimensional wind field data at different current and selected future times, then generate the time series of wind field parameters at each grid point on the glide path, set the threshold of wind shear intensity according to historical data and flight safety standards, and trigger a warning when the wind shear intensity exceeds the set threshold.

[0031] In the f step, the specific steps to use the random forest model in machine learning to judge the available situation of the current runway and the available situation of the future runway are as follows: extract the sub-meter three-dimensional wind field data, airport observation data, mesoscale weather forecast data, and external message data at the current and future times from the system server for multi-source data fusion and feature construction, convert the input data into a feature vector acceptable to the model through a preprocessing pipeline, input the trained random forest model, generate the runway availability prediction results at the current and future times, and calculate the confidence of the prediction results;

[0032] The mathematical model of the random forest can be expressed as:

[0033] ,

[0034] Wherein, is the predicted value, K is the number of decision trees, is the predicted value of the kth decision tree, is the parameter of the kth decision tree, and x is the input feature vector.

[0035] In the g step, the warning module is a dynamic warning system based on multi-level thresholds, and the multi-level warning thresholds respectively correspond to different wind shear intensities, turbulent kinetic energies, and runway availability risk levels; when the warning module detects potential dangerous wind field conditions, the warning module automatically triggers a warning and notifies each user terminal.

[0036] In step f, the external data is observation data, forecast data, and related message data.

[0037] The beneficial effects of the present invention are as follows: The present invention combines a laser wind profiler, CFD numerical simulation, a mesoscale weather forecasting model (WRF), and machine learning to construct an airport wind shear monitoring and early warning system. By combining these four technologies, a sub-meter-level airport wind shear monitoring, early warning, and available runway prediction system based on multi-source data fusion is designed. It can not only detect wind shear over the airport in real time but also reconstruct a sub-meter-level three-dimensional wind field structure, thereby forecasting and warning future wind shear at the airport and further realizing the function of available runway prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] Figure 1 is a simplified structural block diagram of the system of the present invention;

[0039] Figure 2 is a flowchart of the method of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] As Figure 1 shown, an airport available runway monitoring and early warning system based on multi-source data fusion includes

[0041] a laser wind profiler 1 for detecting the wind field within a set range and at a set height and providing high-precision real-time wind shear detection data for the system;

[0042] a CFD numerical simulation module 2 for forming high-precision grid wind field data through simulation calculations;

[0043] a mesoscale weather forecasting module 3 for simulating future weather changes over a large area;

[0044] a machine learning model 4 for improving the CFD calculation speed and predicting available runways at the airport; and

[0045] a system server 5. The system server 5 combines the real-time wind shear detection data measured by the laser wind profiler 1 and the forecast data output by the mesoscale weather forecasting module 3, performs data assimilation on the real-time detection data and the forecast data at the current time point output by the mesoscale weather forecasting module 3, then processes the assimilated data using the CFD numerical simulation module 2, combines the terrain and building parameters near the airport, generates real-time sub-meter-level grid three-dimensional wind field data, reconstructs a sub-meter-level three-dimensional wind field structure, thereby forecasting and warning future wind shear at the airport and further performing available runway prediction.

[0046] A method for predicting available runways at an airport using the above-mentioned airport available runway monitoring and early warning system based on multi-source data fusion includes the following steps:

[0047] a. Deployment and data acquisition of the lidar wind profiler: Deploy the lidar wind profiler 1 at key locations within the airport and adjacent areas, calibrate the system and test the performance of the lidar wind profiler 1 to ensure its stable operation and accurate capture of atmospheric information, thereby providing real-time, high-resolution real-time wind field scanning data to provide basic data support for subsequent processes;

[0048] b. Calculation of future wind field data: Use the mesoscale meteorological forecasting module 3 to simulate the future meteorological change trends in the area where the airport is located to obtain forecast data for a certain period in the future, and then use the inversion algorithm and the CFD numerical simulation module 2 to process the forecast data. Combine the terrain and building parameters near the airport to perform simulation calculations on the atmospheric state, and then generate sub-meter grid three-dimensional wind field data for the airport at future times;

[0049] c. Calculation of real-time wind field data: After the system server 5 receives and analyzes the real-time wind field scanning data sent by the lidar wind profiler 1 and the forecast data output by the mesoscale meteorological forecasting module 3, perform data assimilation on the real-time wind field scanning data and the forecast data at the current time point output by the mesoscale meteorological forecasting module 3, and then use the CFD numerical simulation module 2 to process the assimilated data. Combine the terrain and building parameters near the airport to generate real-time sub-meter grid three-dimensional wind field data;

[0050] d. During the calculation of real-time wind field data, only use the CFD numerical simulation module 2 to calculate the sub-meter grid three-dimensional wind field data at key time points, and then combine the calculation results at key time points with the data obtained from the real-time detection of the lidar wind profiler 1 to drive the graph neural network calculation model, so as to quickly obtain real-time sub-meter grid three-dimensional wind field data;

[0051] e. Wind shear detection: Extract the wind field data when the aircraft descends to the ground from the three-dimensional wind field data at different current and selected future times, and calculate the wind shear data on the glide path, thereby realizing wind shear early warning and forecasting;

[0052] f. Available runway judgment: Combine the three-dimensional wind field data at different current and selected future times, as well as external data such as observation data, forecast data, and relevant messages collected by the airport, and use the random forest model in machine learning to judge the availability of the current runway and the availability of the future runway;

[0053] g. Early warning system construction: Deploy an early warning module to automatically trigger an early warning notification when detecting potential dangerous wind field conditions to ensure that each user terminal can take corresponding measures in time.

[0054] In step b, the specific steps of processing the forecast data using the inversion algorithm and the CFD numerical simulation module 2 are as follows: Standardize the forecast data output by the mesoscale weather forecast module 3, including time alignment, spatial interpolation, and format conversion, and unify it to the grid coordinate system compatible with the CFD numerical simulation module 2; Use the variational inversion algorithm to optimize the low-resolution forecast data, and fuse the statistical characteristics of the forecast data and the historical lidar observation data by minimizing the objective function (including the weighted sum of squares of the background field error and the observation error) to generate a high-resolution initial wind field input;

[0055] The specific steps of combining the terrain and building parameters near the airport to simulate the atmospheric state and then generate the sub-meter grid three-dimensional wind field data of the airport at a future time are as follows: Import the inverted high-resolution wind field data as the initial condition into the CFD numerical simulation module 2, and at the same time load the airport three-dimensional terrain model (DEM) and building geometric parameters (including height, surface roughness, and layout topological relationship), and set the boundary condition as the dynamic pressure and velocity coupling field; Based on the Reynolds-averaged Navier-Stokes equation (RANS) and the k-ε turbulence model, combined with the adaptive mesh refinement technology (AMR), perform transient simulation calculations on the wind field in the airport area to solve for the three-dimensional wind speed components u, v, w and the turbulent kinetic energy distribution of the sub-meter grid nodes; Store the finally generated sub-meter grid three-dimensional wind field data (including time stamp, spatial coordinates, and wind speed vector) in the spatio-temporal database of the system server 5 for subsequent wind shear warning and runway prediction module calls.

[0056] In step c, the specific steps of data assimilation of the real-time wind field scan data and the forecast data are as follows: Use the Newtonian relaxation data assimilation method to fuse the real-time wind field scan data into the WRF model of the mesoscale weather forecast module 3. The momentum equation of the assimilation principle is expressed as:

[0057] ,

[0058] ,

[0059] where u i is the component of the vector u in the i direction, t is time, u j is the component of the vector u in the j direction, v is the dynamic viscosity coefficient, x i is the coordinate component in the i direction, x j is the coordinate component in the j direction, ρ is the density, p is the pressure, f is the additional forcing term added according to the Nudging data assimilation method, u c is the detection speed, u is the WRF forecast speed, τ u is the Newtonian relaxation coefficient, and W(x, y, z) is the weight function;

[0060] The specific steps for processing the real-time wind field scan data by using the CFD numerical simulation module 2 and generating sub-meter grid three-dimensional wind field data in combination with the terrain and building parameters near the airport are as follows: integrating the real-time wind field scan data obtained by the lidar 1 with the meteorological data output by the mesoscale meteorological forecasting module 3 to form a unified data format; adapting the terrain and building parameters to the grid to ensure that the grid can accurately reflect the actual geographical and building environment of the airport and its surrounding areas; setting boundary conditions around the airport according to the real-time wind field scan data, including wind speed, wind direction, air pressure, etc.; using the CFD numerical simulation module 2 to solve the three-dimensional Navier-Stokes equation and calculating parameters such as wind speed and wind direction at each grid point in combination with the terrain and building parameters.

[0061] In step d, the specific steps for calculating the sub-meter grid three-dimensional wind field data at key time points by using the CFD numerical simulation module 2 are as follows: first, according to the output data of the mesoscale meteorological forecasting module 3 and in combination with the analysis of airport operation requirements and historical wind shear events, determine the key time points for key simulations, which usually include the current time point, future time points when wind shear may occur, and peak periods of airport flight takeoffs and landings, etc.; then integrate the real-time wind field data obtained by the lidar 1 with the future meteorological forecasting data provided by the mesoscale meteorological forecasting module 3, and these data include wind speed, wind direction, temperature, humidity, air pressure; then import the terrain data (such as elevation, slope, etc.) and building parameters (such as height, shape, distribution, etc.) of the airport and its surrounding areas to generate a sub-meter three-dimensional grid; use the forecasting data as boundary conditions and use the CFD numerical simulation module 2 to solve the sub-meter grid three-dimensional wind field data at key time points;

[0062] The specific steps for obtaining the real-time sub-meter grid three-dimensional wind field data by combining the calculation results at key time points with the data detected in real time by the lidar 1 to drive the graph neural network calculation model are as follows: in wind field calculation, regard the wind field data as a graph structure, where nodes represent positions in space and edges represent the relationships between positions. The graph convolutional neural network of the graph neural network learns the representation of nodes by aggregating the features of nodes and their neighbors, so as to calculate the dynamic changes of the wind field. The calculation formula of the graph convolutional neural network is:

[0063] ,

[0064] where:

[0065] is the feature vector of node v at the layer, N(v) is the set of neighbor nodes of node v, c ijis the normalized weight between node i and node j, d v and d j are the degrees of node i and node j respectively, is the weight matrix of the

[0066] In the e step, from the three-dimensional wind field data at different current and selected future times, the wind field data when the aircraft glides to the ground is extracted, and the wind shear data on the glide path is calculated. The specific steps for realizing wind shear early warning and forecasting are as follows: from the three-dimensional wind field data at different current and selected future times, the wind speed and wind direction on the glide path are extracted, and then the time series of wind field parameters at each grid point on the glide path is generated. According to historical data and flight safety standards, the threshold of wind shear intensity is set. When the wind shear intensity exceeds the set threshold, an early warning is triggered.

[0067] In the f step, the random forest model in machine learning is used to judge the available situation of the current runway and the available situation of the future runway. The specific steps are as follows: extract the sub-meter three-dimensional wind field data (including wind speed, wind direction, turbulent kinetic energy), airport observation data (runway surface temperature, visibility, precipitation intensity), mesoscale meteorological forecast data (pressure gradient, temperature field), and external message data (flight scheduling, runway maintenance status) at the current and future times from the system server 5 for multi-source data fusion and feature construction. The input data is converted into a feature vector acceptable to the model through a preprocessing pipeline, and then input into the trained random forest model to generate the runway availability prediction results at the current and future times, and calculate the confidence of the prediction results;

[0068] The mathematical model of the random forest can be expressed as:

[0069] ,

[0070] where, is the predicted value, K is the number of decision trees, is the predicted value of the kth decision tree, is the parameter of the kth decision tree, and x is the input feature vector.

[0071] In the g step, the early warning module is a dynamic early warning system based on multi-level thresholds. The multi-level early warning thresholds correspond to different wind shear intensities, turbulent kinetic energies, and runway availability risk levels respectively; when the early warning module detects potential dangerous wind field conditions, the early warning module automatically triggers an early warning and notifies each user terminal.

[0072] The present invention will improve the monitoring and early warning capabilities for airport wind shear, prevent the impact of wind shear on the aircraft during takeoff and landing, and provide a more scientific and accurate decision-making basis for the airport through available runway prediction. The present invention can be popularized and used at domestic military and civil airports, effectively improving the safety level and operation efficiency of airports, and having a huge market prospect.

[0073] Finally, it should be emphasized that the above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for predicting the available runways of an airport using an airport available runway monitoring and early warning system based on multi-source data fusion, wherein: The airport available runway monitoring and early warning system based on multi-source data fusion includes: A laser wind radar (1) for detecting wind fields within a set range and at a set height, and providing the system with high-precision, real-time wind shear detection data; A CFD numerical simulation module (2) for generating high-precision gridded wind field data through simulation calculation; Mesoscale weather forecast module for simulating future weather changes over large areas (3); Machine learning models for improving CFD calculation speed and predicting airport runway availability (4); and A system server (5), wherein the system server (5) combines the real-time wind shear detection data measured by the laser wind radar (1) and the forecast data output by the mesoscale meteorological forecast module (3), performs data assimilation on the real-time detection data and the forecast data at the current time point output by the mesoscale meteorological forecast module (3), and then uses the CFD numerical simulation module (2) to process the assimilated data, combines the terrain and building parameters near the airport, generates real-time sub-meter gridded three-dimensional wind field data, and reconstructs a sub-meter three-dimensional wind field structure, thereby forecasting and warning the future wind shear of the airport, and further predicting the available runway; Characterized in that the method comprises the following steps: a. Deployment and data acquisition of laser wind radar: deploy the laser wind radar (1) at key locations in the airport and adjacent areas, perform system calibration and performance testing on the laser wind radar (1) to ensure its stable operation and accurate capture of atmospheric information, thereby providing real-time, high-resolution real-time wind field scanning data to provide basic data support for subsequent operations; b. Calculation of future wind field data: using the mesoscale weather forecast module (3) to simulate the future weather change trend in the area where the airport is located, to obtain forecast data for a period of time in the future, and then using the inversion algorithm and the CFD numerical simulation module (2) to process the forecast data, combining the terrain and building parameters near the airport, to simulate and calculate the atmospheric state, and then generate sub-meter gridded three-dimensional wind field data of the airport at the future time; c. Real-time wind field data calculation: after receiving and parsing the real-time wind field scanning data sent by the laser wind measuring radar (1) and the forecast data output by the mesoscale meteorological forecast module (3), the system server (5) performs data assimilation on the real-time wind field scanning data and the forecast data at the current time point output by the mesoscale meteorological forecast module (3), and then uses the CFD numerical simulation module (2) to process the assimilated data, and combines the terrain and building parameters near the airport to generate real-time sub-meter gridded three-dimensional wind field data; d. In the process of calculating the real-time wind field data, only the CFD numerical simulation module (2) is used to calculate the sub-meter gridded three-dimensional wind field data at the key time point, and then the calculation results at the key time point are combined with the data obtained by the real-time detection of the laser wind radar (1) to drive the graph neural network calculation model, so as to quickly obtain the real-time sub-meter gridded three-dimensional wind field data; e. Wind shear detection: Extract the wind field data of the aircraft sliding down to the ground from the three-dimensional wind field data at the current and selected future different times, and calculate the wind shear data on the glide path, thereby realizing wind shear warning and forecast; f. Runway availability judgment: Combine the current and selected future three-dimensional wind field data at different times, as well as external data collected by the airport, and use the random forest model in machine learning to judge the current and future runway availability; g. Early warning system construction: Deploy an early warning module to automatically trigger early warning notifications when potential dangerous wind field conditions are detected, ensuring that each user terminal can take timely response measures.

2. The method according to claim 1, characterized in that In step b, the specific steps of using the inversion algorithm and the CFD numerical simulation module (2) to process the forecast data are as follows: standardizing the forecast data output by the mesoscale meteorological forecast module (3), including time alignment, spatial interpolation and format conversion, and unifying it into a grid coordinate system compatible with the CFD numerical simulation module (2); optimizing the low-resolution forecast data using a variational inversion algorithm, and fusing the forecast data with the statistical features of the historical lidar observation data by minimizing the objective function to generate a high-resolution initial wind field input; The specific steps of simulating and calculating the atmospheric state in combination with the terrain and building parameters near the airport, and then generating the sub-meter gridded three-dimensional wind field data of the airport at a future moment are as follows: importing the inverted high-resolution wind field data as the initial condition into the CFD numerical simulation module (2), loading the airport three-dimensional terrain model and building geometric parameters at the same time, and setting the boundary condition as the dynamic pressure and velocity coupling field; based on the Reynolds averaged Navier-Stokes equation and the k-ε turbulence model, combined with the adaptive grid refinement technology, performing transient simulation calculations on the airport area wind field, solving and obtaining the three-dimensional wind speed components u, v, w and turbulent kinetic energy distribution of the sub-meter grid nodes; and storing the finally generated sub-meter gridded three-dimensional wind field data in the spatiotemporal database of the system server (5) for subsequent wind shear warning and runway prediction modules to call.

3. The method according to claim 1, characterized in that In step c, the specific steps of assimilating the real-time wind field scanning data with the forecast data are as follows: using the Newton relaxation data assimilation method to fuse the real-time wind field scanning data into the WRF model of the mesoscale meteorological forecast module (3), and the assimilation principle momentum equation is expressed as: ， ， in u i For vector u Component in the i direction, t is time, u j For vector u The component in the j direction, v is the dynamic viscosity coefficient, x i is the coordinate component in the i direction, x j is the coordinate component in the j direction, ρ is the density, p is the pressure, and f is the additional forcing term added according to the Nudging data assimilation method. u c To detect the speed, u is the WRF forecast speed, τ u is the Newton relaxation coefficient, W ( x , y , z ) is the weight function; The specific steps of using the CFD numerical simulation module (2) to process the real-time wind field scanning data and combining it with the terrain and building parameters near the airport to generate sub-meter gridded three-dimensional wind field data are as follows: integrating the real-time wind field scanning data obtained by the laser wind radar (1) with the meteorological data output by the mesoscale meteorological forecast module (3) to form a unified data format; adapting the terrain and building parameters to the grid to ensure that the grid can accurately reflect the actual geographical and architectural environment of the airport and its surroundings; According to the real-time wind field scanning data, the boundary conditions around the airport are set; the CFD numerical simulation module (2) is used to solve the three-dimensional Navier-Stokes equation, and the parameters of each grid point are calculated by combining the terrain and building parameters.

4. The method according to claim 1, characterized in that: In the step d, the specific steps of using the CFD numerical simulation module (2) to calculate the sub-meter gridded three-dimensional wind field data at the key time point are as follows: first, based on the output data of the mesoscale meteorological forecast module (3), combined with the airport operation requirements and historical wind shear event analysis, the key time point for key simulation is determined; then, the real-time wind field data obtained by the laser wind radar (1) is integrated with the future meteorological forecast data provided by the mesoscale meteorological forecast module (3), which data includes wind speed, wind direction, temperature, humidity, and air pressure; then, the terrain data and building parameters of the airport and its surroundings are imported to generate a sub-meter gridded three-dimensional grid; the forecast data is used as a boundary condition, and the CFD numerical simulation module (2) is used to solve the sub-meter gridded three-dimensional wind field data at the key time point; By combining the calculation results at key time points with the data obtained by real-time detection of the laser wind radar (1), the graph neural network calculation model is driven to obtain real-time sub-meter gridded three-dimensional wind field data. The specific steps are as follows: in wind field calculation, the wind field data is regarded as a graph structure, in which nodes represent positions in space and edges represent the relationship between positions. The graph convolutional neural network of the graph neural network learns the representation of nodes by aggregating the features of nodes and their neighbors, thereby calculating the dynamic changes of the wind field. The calculation formula of the graph convolutional neural network is: ， in: Is a node v In the The feature vector of the layer, N ( v ) is a node v The set of neighbor nodes of c ij Is a node i and nodes j The normalized weight between d v and d j The nodes are i and nodes j The degree, It is is the weight matrix of the layer, and σ is the activation function.

5. The method according to claim 1, characterized in that: In the step e, the wind field data of the aircraft sliding down to the ground is extracted from the three-dimensional wind field data at different moments in the current and selected future, and the wind shear data on the glide path is calculated, and the specific steps of realizing wind shear warning and forecast are: from the three-dimensional wind field data at different moments in the current and selected future, the wind speed and wind direction on the glide path are extracted, and then a time series of wind field parameters for each grid point on the glide path is generated, and a threshold value of wind shear intensity is set according to historical data and flight safety standards. When the wind shear intensity exceeds the set threshold, an early warning is triggered.

6. The method according to claim 1, characterized in that In step f, the specific steps of using the random forest model in machine learning to judge the current runway availability and the future runway availability are as follows: extracting sub-meter-level three-dimensional wind field data, airport observation data, mesoscale meteorological forecast data and external message data at the current and future times from the system server (5) to perform multi-source data fusion and feature construction, converting the input data into a feature vector acceptable to the model through a preprocessing pipeline, inputting the trained random forest model, generating the runway availability prediction results at the current and future times, and calculating the confidence of the prediction results; The mathematical model of random forest can be expressed as: ， in, is the predicted value, K is the number of decision trees, is the predicted value of the kth decision tree, is the parameter of the kth decision tree, x is the input feature vector.

7. The method according to claim 1, characterized in that In step g, the warning module is a dynamic warning system based on multi-level thresholds, and the multi-level warning thresholds correspond to different wind shear intensity, turbulent kinetic energy and runway availability risk levels respectively; When the early warning module detects a potentially dangerous wind field condition, the early warning module automatically triggers an early warning notification to each user terminal.

8. The method according to claim 1, characterized in that In step f, the external data includes observation data, forecast data and related message data.

Images