Risk zoning method, device and equipment for helicopter flight and storage medium

Abstract

The embodiment of the invention provides a risk zoning method and device for helicopter flight, equipment and a storage medium. The method is applied to the technical field of data processing, and comprises the following steps: carrying out classification and threshold division on meteorological elements according to a fusion data set and different flight scenes to obtain a meteorological element threshold breakpoint set; based on the meteorological element threshold breakpoint set, performing frequency statistics and data synthesis on the fused data set to obtain a multi-layer meteorological element frequency data set; obtaining an initial clustering result of each meteorological element through clustering analysis according to the meteorological element frequency data set; according to the initial clustering result, carrying out risk grade division on each meteorological element to obtain a standardized single-element risk zoning result; and based on a single-element risk zoning result, adopting a multi-element fusion method to obtain a comprehensive risk zoning map. In this way, the technical problem that in the prior art, due to the fact that multiple elements jointly participate in clustering, the risk level is difficult to judge can be solved.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing, and in particular to a method, apparatus, device, and storage medium for risk zoning of helicopter flights. Background Art

[0002] Currently, multi-factor comprehensive zoning methods mainly include hierarchical zoning and cluster zoning. The hierarchical zoning method uses an entropy weighting method to determine the relative weights of selected meteorological indicators based on their variability. Weight coefficients are assigned to each meteorological factor to construct a comprehensive evaluation index. Multi-factor comprehensive zoning is achieved by grading the comprehensive evaluation index. The cluster zoning method, on the other hand, uses a statistical algorithm to perform relatively objective classification. This method first selects multiple meteorological factors for cluster analysis, sets the number of clusters, and then uses iterative calculations to obtain the final clustering results, thus completing the zoning.

[0003] However, existing technologies have significant shortcomings. The zoning results of the hierarchical zoning method based on a comprehensive assessment index rely heavily on the set threshold boundaries. When the meteorological threshold boundaries are not given, it is difficult to obtain relatively objective zoning results. While the multi-factor clustering method significantly reduces the reliance on threshold boundaries, it clusters multiple factors together, making it difficult to unify the representation of each factor in the resulting partition. When applied to helicopter flights, it is difficult to determine the risk level of each partition. Summary of the Invention

[0004] The present disclosure provides a method, apparatus, equipment and storage medium for risk zoning for helicopter flights. Single-element clustering is performed for each meteorological factor, and the risk level of each single-element clustering result is determined. A data fusion strategy is formulated to synthesize the clustering results of multiple single elements to generate a risk zoning map, thereby solving the technical problem in the prior art that it is difficult to determine the risk level due to the participation of multiple factors in clustering.

[0005] According to a first aspect of the present disclosure, a method for risk zoning for helicopter flight is provided, comprising:

[0006] Based on multi-source meteorological data, a fused dataset containing multiple meteorological elements is obtained through data fusion processing;

[0007] Based on the fused data set, meteorological elements are classified and thresholded according to different flight scenarios to obtain a meteorological element threshold breakpoint set;

[0008] Based on the meteorological element threshold breakpoint set, frequency statistics and data synthesis are performed on the fused data set to obtain a multi-layer meteorological element frequency data set;

[0009] Based on the meteorological element frequency data set, an initial clustering result of each meteorological element is obtained through cluster analysis;

[0010] Based on the initial clustering results, each meteorological element is classified into risk levels to obtain a standardized single-element risk zoning result;

[0011] Based on the single-factor risk zoning results, a multi-factor fusion method is used to obtain a comprehensive risk zoning map.

[0012] According to a second aspect of the present disclosure, there is provided a device for risk zoning for helicopter flight, comprising:

[0013] A processing module is used to obtain a fused data set containing multiple meteorological elements through data fusion processing based on multi-source meteorological data;

[0014] a classification module for classifying and thresholding meteorological elements according to different flight scenarios based on the fused data set to obtain a meteorological element threshold breakpoint set;

[0015] a synthesis module, configured to perform frequency statistics and data synthesis on the fused data set based on the meteorological element threshold breakpoint set to obtain a multi-layer meteorological element frequency data set;

[0016] An analysis module is used to obtain an initial clustering result of each meteorological element through cluster analysis based on the meteorological element frequency data set;

[0017] A clustering module is used to classify the risk level of each meteorological element according to the initial clustering results to obtain a standardized single-element risk zoning result;

[0018] The fusion module is used to obtain a comprehensive risk zoning map based on the single-factor risk zoning results by adopting a multi-factor fusion method.

[0019] According to a third aspect of the present disclosure, an electronic device is provided, comprising: a memory and a processor, wherein a computer program is stored in the memory, and when the processor executes the program, the method according to the first aspect of the present disclosure is implemented.

[0020] According to a fourth aspect of the present disclosure, a computer-readable storage medium is provided, on which a computer program is stored. When the program is executed by a processor, the method according to the first aspect of the present disclosure is implemented.

[0021] Compared with the prior art, the advantages and positive effects achieved by the present disclosure are:

[0022] The present disclosure realizes the effective integration of ground observation data, sounding observation data and satellite monitoring data through the fusion processing method of multi-source meteorological data, ensuring the integrity and accuracy of meteorological data. The technical scheme of classifying meteorological elements and dividing thresholds according to different flight scenarios fully considers the special requirements of different flight missions for meteorological conditions, improves the pertinence and practicality of risk zoning, and at the same time, performs frequency statistics and data synthesis on the fused data set based on the threshold breakpoint set. The obtained multi-layer meteorological element frequency data set not only retains the temporal distribution characteristics of the original data, but also realizes the spatial expression of the data, providing a reliable data basis for subsequent analysis. The processing method of the initial clustering results of each meteorological element obtained through cluster analysis avoids the subjectivity of the traditional fixed threshold division method and improves the objectivity and adaptability of the zoning results. Furthermore, a technical solution is developed to divide the risk level of each meteorological element to obtain standardized single-element risk zoning results, establish a unified risk level assessment standard, and make the risk assessment results of different meteorological elements comparable. Finally, a multi-element fusion method is used to obtain a technical means of obtaining a comprehensive risk zoning map. This not only takes into account the influence of a single meteorological element, but also reflects the comprehensive effect of multiple meteorological elements through reasonable fusion rules, ensuring the scientific nature and reliability of the data processing process.

[0023] It should be understood that the contents described in the Summary of the Invention section are not intended to limit the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. The accompanying drawings are provided for a better understanding of the present disclosure and do not constitute a limitation of the present disclosure. In the accompanying drawings, the same or similar reference numerals represent the same or similar elements, among which:

[0025] Figure 1 A flow chart showing a method for risk zoning for helicopter flight according to an embodiment of the present disclosure is shown;

[0026] Figure 2 A block diagram of an apparatus for risk zoning for helicopter flight according to an embodiment of the present disclosure is shown;

[0027] Figure 3 A block diagram of an exemplary electronic device capable of implementing embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0028] To make the purpose, technical solutions, and advantages of the embodiments of the present disclosure more clear, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments of the present disclosure, all other embodiments obtained by ordinary technicians in this field without making any creative efforts are within the scope of protection of the present disclosure.

[0029] In this document, the term "and / or" simply describes a relationship between related objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, or B exists alone. Furthermore, the character " / " in this document generally indicates that the related objects are in an "or" relationship.

[0030] Figure 1 FIG. 1 shows a flow chart of a method 100 for risk zoning of helicopter flights according to an embodiment of the present disclosure. Figure 1 As shown, the method 100 includes:

[0031] S110: Obtaining a fused data set containing multiple meteorological elements through data fusion processing based on multi-source meteorological data;

[0032] Optionally, in some embodiments, ERA5 reanalysis data is used as background field data, and multi-source meteorological data is constructed from ground observation data, sounding observation data, and satellite monitoring data; the multi-source meteorological data is spatiotemporally fused through the STMAS space-time multi-scale analysis system to obtain initial fused data with a time resolution of 1 hour and a spatial resolution of 10 kilometers; visibility, low cloud cover, cloud base height, wind speed, wind direction, relative humidity, and temperature values are extracted from the initial fused data to establish a fused data set containing multiple meteorological elements; a difference operation is performed based on the high-level wind speed and the low-level wind speed in the fused data set, and when the difference is large, the high-level wind speed is calculated. The wind shear data is marked as positive at zero o'clock and negative when the difference is less than zero. The wind shear data is formed. The air temperature and relative humidity values in the fused dataset are used to calculate the ice accretion factor and generate the ice accretion factor data. The ice accretion factor data is graded according to the numerical range. When the value is less than or equal to 0, it is assigned a value of 0; when the value is greater than 0 and less than or equal to 50, it is assigned a value of 1; when the value is greater than 50 and less than or equal to 80, it is assigned a value of 2; when the value is greater than 80, it is assigned a value of 3 to form the ice accretion index data. The wind shear data and the ice accretion index data are integrated into the fused dataset to form a complete fused dataset containing multiple meteorological elements.

[0033] Among them, ERA5 reanalysis data is first used as background field data. This data selection is based on its global coverage, long time series, and multi-level meteorological elements. ERA5 reanalysis data provides a complete description of the atmospheric state from the surface to the stratosphere, including multiple key meteorological parameters such as temperature, air pressure, wind speed, and humidity. On this basis, a multi-source meteorological data system is constructed by integrating ground observation data, sounding observation data, and satellite monitoring data. Ground observation data mainly comes from routine observations at meteorological stations, providing information on meteorological elements at the surface layer; sounding observation data provides observation information on the vertical profile of the atmosphere, which can reflect the changes in meteorological elements at different altitudes; satellite monitoring data provides information on the spatial distribution of meteorological elements such as cloud cover and precipitation over a large area.

[0034] The STMAS space-time multiscale analysis system plays a central role in the data fusion process. Using four-dimensional variational assimilation technology, the system integrates observational data from different sources and with varying spatial and temporal resolutions. By setting a grid with a temporal resolution of 1 hour and a spatial resolution of 10 kilometers, the observational data is interpolated and assimilated to generate initial fused data that is continuous in time and physically consistent. This choice of resolution takes into account the timeliness of meteorological information required by flight activities and the rational use of computing resources. When extracting key meteorological elements from the initial fused data, emphasis is placed on visibility, low cloud cover, cloud base height, wind speed, wind direction, relative humidity, and temperature, factors that have a direct impact on flight safety. Visibility data reflects atmospheric transparency and directly influences pilots' visual judgment; low cloud cover and cloud base height data influence the choice of flight altitude; wind speed and direction data influence flight route planning; and relative humidity and temperature data are closely related to icing risk.

[0035] When processing wind shear data, the intensity of vertical wind shear is quantified by calculating the difference between upper-level and lower-level wind speeds. A positive difference indicates that the wind speed at high altitude is greater than the wind speed at low altitude, resulting in positive shear; a negative difference indicates that the wind speed at low altitude is greater than the wind speed at high altitude, resulting in negative shear. This wind shear information is crucial for flight safety, especially during takeoff and landing. Icing risk is assessed by calculating an icing factor. This calculation takes into account two key parameters: air temperature, which influences the phase transition of water vapor, and relative humidity, which determines the amount of condensable water vapor in the atmosphere. By setting different thresholds, the icing factor is converted into an icing index, resulting in a graded assessment. An icing factor less than or equal to 0 indicates no icing risk; values between 0 and 50 indicate a mild icing risk; values between 50 and 80 indicate a moderate icing risk; and values greater than 80 indicate a severe icing risk.

[0036] Finally, wind shear and icing index data were integrated into the fused dataset to form a complete, multi-factor meteorological dataset. This dataset provided comprehensive data support for subsequent risk zoning analysis, encompassing all key meteorological factors that significantly impact flight safety.

[0037] It should be noted that in the embodiment, first, the key meteorological elements of multiple flight scenarios are determined. Based on knowledge and experience, the corresponding sensitive meteorological elements are extracted for different flight scenarios, and a statistical table of sensitive elements of typical flight scenarios is prepared, as shown in Table 1.

[0038] Table 1 Meteorological elements of concern in typical flight scenarios

[0039] Serial number Task Type Sensitive elements 1 General scenarios Visibility, low cloud cover, high cloud base, strong winds, wind shear, and ice accumulation 2 coastal flight Visibility, low cloud cover, high cloud base, strong winds 3 High-altitude flight High winds, low cloud cover, wind shear, and ice accumulation 4 ferry flight Ice accumulation, low cloud cover, wind shear 5 Daily training Visibility, low cloud cover, strong winds

[0040] The data used for helicopter flight risk zoning is fused using the ERA5 reanalysis data as the background field. This data is combined with ground-based observations, sounding data, and satellite monitoring data using the STMAS (Space and Time Multiscale Analysis System) model. The fused data spans 10 years with a temporal resolution of 1 hour, and the horizontal resolution for the national data is 10 km. This data includes key meteorological elements such as visibility, low cloud cover, cloud base height, wind speed, wind direction, relative humidity, and temperature. Furthermore, wind shear can be calculated by subtracting low-level wind speed from high-level wind speed (Equation 1), and the icing index can be calculated by combining temperature and relative humidity (Equations 2-3).

[0041] shear=wspd h -wspd l ; (1)

[0042] Where shear is the vertical wind shear. When the difference is greater than zero, it is positive shear, and when it is less than zero, it is negative shear. h is the upper wind speed (m / s); wspd l is the low-level wind speed (m / s).

[0043] ice_factor=2×(rh-50)×tem×(tem+14) / (-49) (2)

[0044]

[0045] Where icing is the icing index; rh is the relative humidity (%); tem is the temperature (°C); and ice_factor is the icing risk index.

[0046] For example, radiosonde data for a particular area shows a wind speed of 15 meters per second at 2,000 meters and a ground wind speed of 5 meters per second. A difference calculation yields a wind shear value of 10 meters per second. Furthermore, the temperature in the area is -5 degrees Celsius and the relative humidity is 85%. Substituting this into the icing factor calculation formula yields a value of 75, corresponding to a moderate icing risk level of 2. These processed data, combined with other meteorological data, form a complete description of the meteorological characteristics of the area, providing a reliable foundation for subsequent risk zoning. The entire data processing process embodies the integration of multi-source data, the extraction of key elements, and the quantitative assessment of risk indicators.

[0047] S120: Classifying and thresholding meteorological elements according to different flight scenarios based on the fused data set to obtain a meteorological element threshold breakpoint set;

[0048] Optionally, in some embodiments, the fused data set is classified according to the characteristics of different flight scenarios to obtain sensitive meteorological elements corresponding to each flight scenario; the sensitive meteorological elements are threshold-divided according to their numerical characteristics to obtain threshold intervals of visibility meteorological elements; the power meteorological elements among the sensitive meteorological elements are threshold-divided to obtain threshold intervals of power meteorological elements; and a meteorological element threshold breakpoint set is established based on the threshold intervals of visibility meteorological elements and the threshold intervals of power meteorological elements.

[0049] Based on the fused dataset, accurate feature recognition and classification are performed for different flight scenarios. Flight scenarios are mainly divided into five categories: general scenarios, coastal flight scenarios, plateau flight scenarios, transfer flight scenarios, and routine training scenarios. Each scenario has its own unique combination of meteorological sensitive factors. The general scenario is the most comprehensive flight scenario, considering six meteorological factors: visibility, low cloud cover, cloud base height, strong winds, wind shear, and icing. These factors comprehensively reflect all aspects that affect flight safety: visibility is directly related to the pilot's visual conditions, low cloud cover and cloud base height affect the choice of flight altitude, strong winds and wind shear affect the helicopter's maneuverability, and icing may cause changes in the helicopter's aerodynamic characteristics.

[0050] Coastal flight scenarios focus on four factors: visibility, low cloud cover, cloud base height, and strong winds. This choice is based on the special meteorological characteristics of coastal areas: local circulation caused by the temperature difference between land and sea, the impact of sea fog on visibility, the characteristics of marine low clouds, and changes in wind fields near the coastline. The combination of these factors can better reflect the risk characteristics of coastal flights. Plateau flight scenarios focus on four factors: strong winds, low cloud cover, wind shear, and icing. The special terrain of the plateau will lead to a complex wind field structure. At the same time, cloud cover changes and icing risks in a low-pressure environment also require special attention. The terrain-induced wind shear unique to the plateau is an important risk factor in this scenario.

[0051] For visibility meteorological factors (including visibility, low cloud cover, and cloud base height), the threshold ranges are determined based on the pilot's visual judgment needs. Specifically, the visibility thresholds are set in a sequence of 700 to 5000 meters, corresponding to the flight visibility level standards; the low cloud thresholds range from 0.3 to 0.9, reflecting the impact of varying degrees of cloud cover on flight; and the cloud base thresholds range from 70 to 500 meters, corresponding to the minimum safe altitude requirements for different flight phases. The thresholds for dynamic meteorological factors (including wind speed, wind shear, and icing) are based on helicopter performance characteristics and flight mechanics. The wind speed thresholds range from 8 to 28 meters per second, covering levels ranging from slight to severe impacts on flight safety; the wind shear thresholds are set from 0.067 to 0.206 meters per second, reflecting the impact of varying intensities of wind shear on helicopter attitude control; and the icing index thresholds range from 0 to 3, corresponding to different risk levels from no icing to severe icing.

[0052] For example, when analyzing meteorological elements for a common scenario, the six meteorological elements required for the scenario are first extracted from the fused dataset. Regarding visibility data, statistical analysis revealed that visibility in a certain area varied from 500 to 6000 meters over a period of time. Based on this data distribution, visibility thresholds were set at six breakpoints: 700 meters, 1000 meters, 1500 meters, 2000 meters, 3000 meters, and 5000 meters. These breakpoints were selected based on the actual data distribution while also meeting flight safety metrics. Similarly, wind speed data showed a range of 5 to 30 meters per second, so multiple threshold breakpoints were set, ranging from 8 to 28 meters per second.

[0053] In the embodiment of the present application, threshold breakpoints of focus for different meteorological elements are designed, and a table of threshold conditions for typical meteorological elements is formulated, as shown in Table 2.

[0054] Table 2 Typical element threshold conditions

[0055]

[0056] S130: Based on the meteorological element threshold breakpoint set, frequency statistics and data synthesis are performed on the fused dataset to obtain a multi-layer meteorological element frequency dataset.

[0057] Optionally, in some embodiments, the meteorological elements in the fused data set are segmented according to the meteorological element threshold breakpoint set, and the cumulative number of hours of the meteorological elements in each threshold interval is counted to obtain the meteorological element distribution data of each threshold interval; the meteorological element distribution data of each threshold interval is divided by the total number of hours per year, and the average occurrence frequency of each meteorological element in different threshold intervals is calculated to obtain the meteorological element frequency data; the meteorological element frequency data is normalized to obtain the meteorological element standardized frequency data; the meteorological element standardized frequency data is stratified according to the number of threshold breakpoints to generate a frequency layer sequence; the data between adjacent threshold breakpoints in the frequency layer sequence are merged into one layer to obtain multiple frequency composite layers; and the multiple frequency composite layers are combined to form a multi-layer meteorological element frequency data set.

[0058] The meteorological elements in the fused dataset are segmented and counted according to pre-set threshold breakpoints, converting continuous meteorological data into discrete frequency distribution features. The division of threshold intervals is based on the threshold breakpoint set of meteorological elements, and each meteorological element has its own specific threshold sequence. For example, for visibility, the threshold breakpoints include 700 meters, 1000 meters, 1500 meters, 2000 meters, 3000 meters, and 5000 meters, forming multiple intervals; for wind speed, the threshold breakpoints range from 8 meters per second to 28 meters per second, also dividing multiple intervals. Within each interval, the cumulative number of hours that the meteorological element appears is counted. This process is actually a segmented counting of the time series data of the meteorological element.

[0059] The statistics of the cumulative number of hours require a traversal calculation of the data for the entire year. Since the time resolution of the fused dataset is 1 hour, the total number of hours per year is 8760 hours (non-leap year). By dividing the cumulative number of hours within each threshold interval by the total number of hours per year, the average occurrence frequency of each interval is obtained. This frequency value reflects the probability of a certain meteorological condition occurring throughout the year and is an important reference indicator for assessing meteorological risks. In order to make the frequency data of different meteorological elements comparable, they need to be normalized. Normalization converts frequency data of different dimensions and different numerical ranges to the same standard scale, usually the interval [0, 1]. The standardized frequency data processed in this way facilitates subsequent comprehensive analysis and risk assessment.

[0060] Normalized frequency data needs to be stratified according to the number of threshold breakpoints. Taking visibility as an example, if there are six threshold breakpoints, seven data layers will be formed, each corresponding to a specific threshold interval. This hierarchical structure gives the data a spatial dimension, facilitating subsequent spatial analysis and visualization. After obtaining the stratified data, the data between adjacent threshold breakpoints needs to be merged to form a frequency composite layer. This merging process is not a simple data overlay, but rather takes into account the continuity and transition characteristics of the data. The composite layer retains the main features of the original data while reducing data redundancy.

[0061] For example, when processing wind speed data for a certain area, the wind speed data is first divided into multiple intervals based on the threshold breakpoints (8, 10, 11, 12, 13, 15, 16, 18, 20, 22, 23, and 28 meters per second). By statistically analyzing the wind speed records for one year, the cumulative number of hours with wind speed in each interval is obtained. For example, if the interval of 8-10 meters per second has accumulated 1000 hours, the frequency of occurrence of this interval is 1000 / 8760. After performing similar statistics on all intervals, a set of raw frequency data is obtained. After normalization, these data form a standardized frequency distribution. Then, 12 data layers are divided according to the 11 threshold breakpoints, each layer corresponding to a wind speed interval. Finally, these data layers are combined into a complete wind speed frequency dataset. This dataset not only reflects the intensity distribution of wind speed but also contains statistical characteristics of the time dimension.

[0062] It should be noted that in the embodiments of the present application, the cumulative annual average frequency statistics are based on 10 years of meteorological data, and the cumulative annual average frequency of different meteorological elements occurring within different threshold intervals is calculated, that is, the ratio of the number of hours that meet the conditions in each year to the total number of hours in the year (Formula 4).

[0063]

[0064] Where, P YEAR is the cumulative average frequency of the element in the i-th threshold interval; hour i_n The number of hours that the meteorological element is within the threshold interval of the i-th year; hour sum_n is the total number of hours of the meteorological element in the nth year; n is the number of years.

[0065] Synthesis of cumulative frequency data. Synthesize the cumulative frequency data of the same element. If the number of threshold breakpoints of the element is n, then the number of layers of the synthesized data is n+1. The synthesis method is shown in Equation 5.

[0066]

[0067] In the formula, data is the synthetic dataset of the feature, δi (i=1, 2, ..n) is the i-th breakpoint threshold of the meteorological element.

[0068] S140: Obtaining initial clustering results of each meteorological element through cluster analysis based on the meteorological element frequency data set;

[0069] Optionally, in some embodiments, three data points are randomly selected from the meteorological element frequency data set as initial cluster center points to form an initial cluster space; based on the initial cluster space, the Euclidean distance from each data point in the meteorological element frequency data set to the three cluster center points is calculated to obtain a distance matrix; according to the distance matrix, each data point in the meteorological element frequency data set is divided into the category to which the nearest cluster center point belongs to generate a first round of cluster grouping; a new center point position is calculated for each category in the first round of cluster grouping to form an updated cluster center point set; the distance calculation and grouping process is repeated using the updated cluster center point set until the change in the cluster center point position is less than a preset threshold to obtain a final cluster grouping; the final cluster grouping is organized into the initial clustering results of each meteorological element.

[0070] The goal of K-means clustering is to group data points into K clusters, ensuring that each data point belongs to the nearest cluster center while minimizing the sum of the squared distances from all points to their cluster centers. In this method, the K value is set to 3, corresponding to the three risk levels of high, medium, and low. Cluster analysis first involves randomly selecting three data points from the meteorological frequency dataset as initial cluster centers. The choice of these initial centers affects the speed of clustering convergence but does not affect the final clustering results. These initial cluster centers form the initial cluster space, which serves as the starting point for subsequent clustering iterations. After determining the initial cluster centers, the Euclidean distance from each data point in the dataset to the three cluster centers is calculated. Euclidean distance is the most commonly used distance metric, reflecting the straight-line distance between two points in multidimensional space. For each data point in the meteorological frequency dataset, its distance from the three cluster centers is calculated, forming a distance matrix. This matrix contains the distance information from all data points to each cluster center.

[0071] Based on the nearest neighbor principle, each data point is assigned to the category of the closest cluster center. This process forms the first round of clustering, in which each data point is labeled as belonging to a specific category. After the first round of clustering, the distribution of data points may not be rational enough and requires iterative optimization to improve. For each category in the first round of clustering, the average position of all data points in that category is calculated and used as the new cluster center. This new set of cluster centers reflects the overall characteristics of the current grouping and will be used for distance calculation and grouping in the next round. By continuously updating the positions of the cluster centers, the clustering results are gradually optimized.

[0072] During each iteration, the steps of calculating distances and updating clusters are repeated. When the change in the position of the cluster center between two consecutive iterations is less than a preset threshold, the clusters are considered converged and the iteration process is terminated. The selection of this threshold requires a balance between computational efficiency and clustering accuracy. The cluster groupings represent the initial clustering results for each meteorological element. This result divides the data for each meteorological element into three categories, providing the basis for subsequent risk classification.

[0073] For example, suppose a wind speed frequency data set for a certain area contains wind speed statistics from multiple measuring points. First, the data from three measuring points are randomly selected as the initial cluster centers. The wind speed frequency distribution characteristics of these points are different. Then, the Euclidean distances from all measuring points to these three center points are calculated to form a distance matrix. Based on the distance matrix, each measuring point is assigned to the category to which the nearest center point belongs. After that, the average wind speed frequency distribution of all measuring points in each category is calculated as the new cluster center. After multiple rounds of iterative optimization, three stable categories are finally obtained. These categories represent different combinations of wind speed characteristics, providing a basis for subsequent risk level determination.

[0074] S150: Based on the initial clustering results, the risk level of each meteorological element is divided into risk levels to obtain a standardized single-element risk zoning result;

[0075] Optionally, in some embodiments, regional characteristic values of the three clustering areas are obtained by calculating the cumulative annual average value of each clustering area in the initial clustering results; the low cloud cover, wind speed, wind shear, and ice accumulation meteorological elements in the regional characteristic values are sorted in size, and the larger the value, the higher the risk level, to form a risk level mapping for power elements; the visibility and cloud base height meteorological elements in the regional characteristic values are sorted in size, and the smaller the value, the higher the risk level, to form a risk level mapping for visibility elements; based on the risk level mapping for power elements, the corresponding areas are relabeled as values 1, 2, and 3 to generate risk zoning results for power elements; based on the risk level mapping for visibility elements, the corresponding areas are relabeled as values 1, 2, and 3 to generate risk zoning results for visibility elements; the risk zoning results for power elements are integrated with the risk zoning results for visibility elements to form a standardized single-element risk zoning result, where the value 1 represents a high-risk area, 2 represents a medium-risk area, and 3 represents a low-risk area.

[0076] The cumulative annual average value is calculated for each cluster area in the initial clustering results, and a statistical analysis of the meteorological element data in each area in the time dimension is performed to obtain a numerical value that can represent the characteristics of the area. This process actually combines the spatial distribution characteristics obtained by clustering with the time series characteristics to form a more comprehensive description of regional characteristics. Meteorological elements can be divided into dynamic elements and visibility elements according to the physical mechanism of their impact on flight safety. Dynamic elements include low cloud cover, wind speed, wind shear and ice accumulation, which directly affect the aerodynamic characteristics and flight performance of helicopters. Visibility elements include visibility and cloud base height, which mainly affect the visual observation conditions of pilots. Different risk level judgment criteria are required for these two types of elements.

[0077] For power-related factors, the risk level is positively correlated with the numerical value. For example, higher wind speeds have a greater impact on helicopters and a higher risk level. A higher wind shear value indicates a more pronounced vertical wind speed difference, posing a greater threat to flight safety. A higher icing index indicates a higher likelihood and severity of icing. A greater amount of low cloud cover indicates a wider cloud cover and greater flight restrictions. Therefore, when mapping the risk levels for power-related factors, the regions are sorted in descending order based on their characteristic values. Regions with the largest characteristic values correspond to high risk, followed by medium risk, and the smallest values correspond to low risk.

[0078] For visibility-related elements, the risk level is negatively correlated with the numerical value. The lower the visibility, the worse the pilot's visual observation conditions and the higher the risk level. The lower the cloud base, the more severe the flight altitude restrictions and the higher the risk level. Therefore, when mapping the risk levels of visibility-related elements, the regions are sorted in ascending order according to the size of the regional characteristic values. The region with the smallest characteristic value corresponds to high risk, followed by medium risk, and the largest corresponds to low risk. Based on this risk level mapping relationship, the power and visibility elements are regionally relabeled separately. The power elements are labeled 1, 2, and 3 in descending order of risk, generating the risk zoning results for the power elements. Similarly, the visibility elements are also labeled 1, 2, and 3 in descending order of risk, generating the risk zoning results for the visibility elements. This unified labeling method makes different types of meteorological elements comparable.

[0079] The risk zoning results for power and visibility factors are integrated to form a standardized single-factor risk zoning result. In this result, a value of 1 indicates a high-risk area, meaning that the weather conditions in this area pose a significant threat to flight activities; a value of 2 indicates a medium-risk area, meaning that the weather conditions have some impact on flight activities, but the impact is relatively small; and a value of 3 indicates a low-risk area, meaning that the weather conditions have a small impact on flight activities.

[0080] For example, the initial clustering results for a certain area include three clusters. The cumulative annual average values for these clusters are calculated to obtain regional characteristic values for wind speed. Analysis reveals that the first cluster has the highest average wind speed, reaching 15 meters per second. The second cluster has an average wind speed of 10 meters per second, and the third cluster has an average wind speed of 5 meters per second. Based on the risk level mapping rules for dynamic elements, the region with an average wind speed of 15 meters per second is labeled 1 (high risk), the region with an average wind speed of 10 meters per second is labeled 2 (medium risk), and the region with an average wind speed of 5 meters per second is labeled 3 (low risk). Simultaneously, the visibility data for this region is divided into three zones: the first zone has an average visibility of 800 meters, the second zone has an average visibility of 2000 meters, and the third zone has an average visibility of 5000 meters. Based on the risk level mapping rules for visibility elements, the zone with an average visibility of 800 meters is labeled 1, the zone with a visibility of 2000 meters is labeled 2, and the zone with a visibility of 5000 meters is labeled 3. This method creates standardized risk zoning results, providing a foundation for subsequent comprehensive risk assessment.

[0081] S160: Based on the single-factor risk zoning results, a multi-factor fusion method is used to obtain a comprehensive risk zoning map.

[0082] Optionally, in some embodiments, the risk level of each meteorological element in the single-element risk zoning result is extracted to generate a risk level distribution matrix; based on the risk level distribution matrix, it is detected whether any meteorological element in each regional location is in a high-risk state, and a high-risk area identification is generated; the areas not identified as high-risk in the risk level distribution matrix are detected to determine whether any meteorological element is in a medium-risk state, and a medium-risk area identification is generated; the remaining unidentified areas in the risk level distribution matrix are marked as low-risk areas, and a low-risk area identification is generated; the high-risk area identification, the medium-risk area identification, and the low-risk area identification are merged to form a final risk area distribution matrix; and the comprehensive risk zoning map is generated based on the final risk area distribution matrix.

[0083] The risk level information for each meteorological element is extracted from the single-element risk zoning results to construct a risk level distribution matrix. This matrix contains the risk level values for all meteorological elements at each regional location, forming a multidimensional data structure. The construction of the risk level distribution matrix involves processing the spatial correspondence of the data. Each element of the matrix represents the risk level of a meteorological element at a specific location. These risk levels are standardized in the initial processing to obtain the three levels of 1, 2, and 3. In this way, the risk information of all meteorological elements is integrated into a single data structure, facilitating subsequent comprehensive analysis.

[0084] After obtaining the risk level distribution matrix, each regional location is first tested for high risk. The core principle of the test is "one vote veto", that is, as long as there is any meteorological element in a high-risk state (risk level value is 1) at a certain location, the location will be marked as a high-risk area. This approach reflects a cautious attitude towards flight safety, because any high-risk factor may pose a serious threat to flight safety. For those areas that are not identified as high-risk, medium-risk testing is carried out. The detection method is to determine whether there are any meteorological elements in these areas that are in a medium-risk state (risk level value is 2). If there are medium-risk elements, the area is marked as a medium-risk area. This grading method ensures the continuity and integrity of risk assessment.

[0085] The remaining areas that are not identified as high-risk or medium-risk are automatically classified as low-risk areas. All meteorological elements in these areas are in a low-risk state (risk level value is 3), indicating that the meteorological conditions in this area have relatively little impact on flight activities. The high-risk area identification, medium-risk area identification and low-risk area identification are merged to form the final risk area distribution matrix. This matrix is a spatial distribution data structure that comprehensively considers the influence of all meteorological elements and reflects the comprehensive risk level of different areas. A comprehensive risk zoning map is generated based on the final risk area distribution matrix. This zoning map is an intuitive spatial visualization product that clearly shows the risk level distribution of different areas and provides an intuitive reference for flight decisions.

[0086] For example, in a risk analysis of the area surrounding an airport, the risk level data for all meteorological elements in the area is first extracted. Taking a specific location as an example, the visibility risk level at that location is 2 (medium risk), the cloud base risk level is 3 (low risk), the wind speed risk level is 1 (high risk), the wind shear risk level is 2 (medium risk), and the icing risk level is 3 (low risk). After organizing these data into a risk level distribution matrix, a high-risk detection is performed. Since the wind speed at this location is in a high-risk state, the location is marked as a high-risk area. This processing method performs the same analysis on each spatial location to form a complete risk zoning map.

[0087] It should be noted that in the embodiment of the present application, the K-means clustering method is used to cluster the frequency composite data of each single element, generating m clustering results. Where m is the number of elements in the flight scene. The specific clustering method is as follows:

[0088] (1) Select K points as the cluster centers for the initial aggregation of the synthetic data (non-sample points can also be selected). The present invention sets the K value to 3;

[0089] (2) Calculate the distance between each sample point and the K cluster cores (the distance here is generally Euclidean distance or cosine distance), find the cluster core closest to the point, and assign it to the corresponding cluster;

[0090] (3) After all points are assigned to clusters, all sample points are divided into K clusters. Then the centroid (average distance center) of each cluster is recalculated and set as the new "cluster core";

[0091] (4) Repeat steps 2-3 until the termination condition is reached.

[0092] Clustering results are synthesized to generate a helicopter flight risk zoning map. Based on the clustering results of each element, the cumulative annual average value of each element in the Kth (K = 0, 1, 2) partition is calculated. When the elements are low cloud cover, wind speed, wind shear, and ice accumulation, the larger the average value of the partition, the higher the risk level; when the elements are visibility and cloud base height, the smaller the average value of the partition, the higher the risk level. Based on this, the clustering results of this type of elements are reassigned according to the statistical data to ensure that the clustering results of each type of element are 1, which represents a high-risk area, 2, which represents a medium-risk area, and 3, which represents a low-risk area. For the comprehensive helicopter flight risk zoning, when a key element is in a high-risk area, the area should be defined as a high-risk area. According to this rule, the clustering results are synthesized (Equation 6) to generate a helicopter flight risk zoning map (1 - high-risk area, 2 - medium-risk area, 3 - low-risk area).

[0093]

[0094] In the formula, Cluster is the risk zoning result, m represents the number of elements in the flight scenario, i represents the row number of the pixel, and j represents the column number of the pixel.

[0095] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present disclosure is not limited by the order of the actions described, because according to the present disclosure, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0096] The above is an introduction to the method embodiment. The following is a further explanation of the solution disclosed in the present disclosure through an apparatus embodiment.

[0097] Figure 2 FIG. 2 shows a block diagram of an apparatus 200 for risk zoning of helicopter flights according to an embodiment of the present disclosure. Figure 2 As shown, the apparatus 200 includes:

[0098] The processing module 210 is used to obtain a fused data set containing multiple meteorological elements through data fusion processing based on multi-source meteorological data;

[0099] A classification module 220 is configured to classify and divide meteorological elements into thresholds according to different flight scenarios based on the fused data set to obtain a meteorological element threshold breakpoint set;

[0100] A synthesis module 230 is configured to perform frequency statistics and data synthesis on the fused dataset based on the meteorological element threshold breakpoint set to obtain a multi-layer meteorological element frequency dataset;

[0101] An analysis module 240 is configured to obtain an initial clustering result of each meteorological element through cluster analysis based on the meteorological element frequency data set;

[0102] Clustering module 250, configured to classify the risk levels of each meteorological element based on the initial clustering results to obtain standardized single-element risk zoning results;

[0103] The fusion module 260 is used to obtain a comprehensive risk zoning map based on the single-factor risk zoning results by adopting a multi-factor fusion method.

[0104] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the described module can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0105] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device and a readable storage medium.

[0106] Figure 3 A schematic block diagram of an electronic device 300 that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0107] Electronic device 300 includes a computing unit 301, which can perform various appropriate actions and processes according to a computer program stored in ROM 302 or a computer program loaded from storage unit 308 into RAM 303. RAM 303 may also store various programs and data required for the operation of electronic device 300. Computing unit 301, ROM 302, and RAM 303 are interconnected via bus 304. I / O interface 305 is also connected to bus 304.

[0108] Multiple components in the electronic device 300 are connected to the I / O interface 305, including an input unit 306, such as a keyboard, a mouse, etc.; an output unit 307, such as various types of displays, speakers, etc.; a storage unit 308, such as a magnetic disk, an optical disk, etc.; and a communication unit 309, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 309 allows the electronic device 300 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0109] Computing unit 301 can be any general-purpose and / or specialized processing component with processing and computing capabilities. Some examples of computing unit 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Computing unit 301 performs the various methods and processes described above, such as the method for risk zoning for helicopter flights. For example, in some embodiments, the method for risk zoning for helicopter flights can be implemented as a computer software program tangibly embodied in a machine-readable medium, such as storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by computing unit 301, one or more steps of the method for risk zoning for helicopter flights described above can be performed. Alternatively, in other embodiments, the computing unit 301 may be configured to execute the risk zoning method for helicopter flight in any other appropriate manner (for example, by means of firmware).

[0110] Various embodiments of the systems and techniques described herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0111] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0112] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium can include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0113] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0114] The systems and techniques described herein can be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), and the Internet.

[0115] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises through computer programs running on the respective computers and having a client-server relationship with each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0116] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not limited herein.

[0117] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for risk zoning of helicopter flights, characterized in that: include: Based on multi-source meteorological data, a fused dataset containing multiple meteorological elements is obtained through data fusion processing; Based on the fused data set, meteorological elements are classified and thresholded according to different flight scenarios to obtain a meteorological element threshold breakpoint set; Based on the meteorological element threshold breakpoint set, frequency statistics and data synthesis are performed on the fused data set to obtain a multi-layer meteorological element frequency data set; Based on the meteorological element frequency data set, an initial clustering result of each meteorological element is obtained through cluster analysis; Based on the initial clustering results, each meteorological element is classified into risk levels to obtain a standardized single-element risk zoning result; Based on the single-factor risk zoning results, a multi-factor fusion method is used to obtain a comprehensive risk zoning map.

2. The method according to claim 1, characterized in that The fusion data set containing multiple meteorological elements is obtained by data fusion processing based on multi-source meteorological data, including: The ERA5 reanalysis data is used as background field data, and the multi-source meteorological data is constructed from ground observation data, sounding observation data and satellite monitoring data; The multi-source meteorological data are subjected to spatiotemporal fusion through the STMAS space-time multi-scale analysis system to obtain initial fused data with a time resolution of 1 hour and a spatial resolution of 10 kilometers; Extracting visibility, low cloud cover, cloud base height, wind speed, wind direction, relative humidity, and temperature values from the initial fused data to establish the fused data set containing multiple meteorological elements; Performing a difference operation based on the high-level wind speed and the low-level wind speed in the fused data set, marking it as positive shear when the difference is greater than zero, and marking it as negative shear when the difference is less than zero, thereby forming wind shear data; Calculating ice accumulation factors using the air temperature and relative humidity values in the fused data set to generate ice accumulation factor data; The ice accretion factor data is graded according to a numerical range, where a value of 0 is assigned when the value is less than or equal to 0, a value of 1 is assigned when the value is greater than 0 and less than or equal to 50, a value of 2 is assigned when the value is greater than 50 and less than or equal to 80, and a value of 3 is assigned when the value is greater than 80, thereby forming ice accretion index data; The wind shear data and ice accumulation index data are integrated into the fused data set to form a complete fused data set including multiple meteorological elements.

3. The method according to claim 1, characterized in that According to the fused data set, meteorological elements are classified and thresholded according to different flight scenarios to obtain a meteorological element threshold breakpoint set, including: Classifying the fused data set according to the characteristics of different flight scenarios to obtain sensitive meteorological elements corresponding to each flight scenario; The sensitive meteorological elements are divided into thresholds according to their numerical characteristics to obtain threshold intervals of visibility meteorological elements; Performing threshold division on the dynamic meteorological elements among the sensitive meteorological elements to obtain the threshold intervals of the dynamic meteorological elements; The meteorological element threshold breakpoint set is established based on the threshold interval of the visibility meteorological element and the threshold interval of the power meteorological element.

4. The method according to claim 1, wherein The method of performing frequency statistics and data synthesis on the fused data set based on the meteorological element threshold breakpoint set to obtain a multi-layer meteorological element frequency data set includes: Segmenting the meteorological elements in the fused data set according to the meteorological element threshold breakpoint set, counting the cumulative number of hours of meteorological elements within each threshold interval, and obtaining meteorological element distribution data for each threshold interval; Dividing the meteorological element distribution data of each threshold interval by the total number of hours in a year, calculating the average occurrence frequency of each meteorological element in different threshold intervals, and obtaining meteorological element frequency data; Normalizing the frequency data of meteorological elements to obtain standardized frequency data of meteorological elements; stratifying the standardized frequency data of meteorological elements according to the number of threshold breakpoints to generate a frequency layer sequence; Merging data between adjacent threshold breakpoints in the frequency layer sequence into one layer to obtain multiple frequency composite layers; The multiple frequency synthesis layers are combined to form the multi-layer meteorological element frequency dataset.

5. The method according to claim 1, wherein The initial clustering results of each meteorological element are obtained by cluster analysis based on the meteorological element frequency data set, including: Randomly select three data points from the meteorological element frequency data set as initial cluster center points to form an initial cluster space; Based on the initial cluster space, calculating the Euclidean distance from each data point in the meteorological element frequency data set to the three cluster center points to obtain a distance matrix; According to the distance matrix, each data point in the meteorological element frequency data set is divided into the category to which the nearest cluster center point belongs, and a first round of cluster grouping is generated; Calculate the new center point position for each category in the first round of clustering grouping to form an updated cluster center point set; Repeat the distance calculation and grouping process using the updated cluster center point set until the change in the cluster center point position is less than a preset threshold, thereby obtaining the final cluster grouping; The final cluster grouping is organized into the initial clustering results of the meteorological elements.

6. The method according to claim 1, characterized in that According to the initial clustering results, each meteorological element is divided into risk levels to obtain a standardized single-element risk zoning result, including: By calculating the cumulative annual average value of each cluster area in the initial clustering result, regional characteristic values of the three cluster areas are obtained; The low cloud cover, wind speed, wind shear, and ice accumulation meteorological elements in the regional characteristic values are ranked by order, with larger values corresponding to higher risk levels, thereby forming a risk level mapping for dynamic elements; The visibility and cloud base height meteorological elements in the regional characteristic values are sorted by size, with smaller values corresponding to higher risk levels, thereby forming a risk level mapping for visibility elements; Based on the risk level mapping of the power-related elements, the corresponding areas are re-marked as values 1, 2, and 3 to generate risk zoning results for the power-related elements; Based on the risk level mapping of the visibility elements, the corresponding areas are re-marked as values 1, 2, and 3 to generate risk zoning results for the visibility elements; The risk zoning results of the power-related elements are integrated with the risk zoning results of the visibility-related elements to form the standardized single-element risk zoning results, where the value 1 represents a high-risk area, 2 represents a medium-risk area, and 3 represents a low-risk area.

7. The method according to claim 1, characterized in that Based on the single-factor risk zoning results, a multi-factor fusion method is used to obtain a comprehensive risk zoning map, including: Extracting the risk level of each meteorological element in the single-element risk zoning result to generate a risk level distribution matrix; Based on the risk level distribution matrix, detecting whether any meteorological element in each area is in a high-risk state and generating a high-risk area identifier; Detecting areas not identified as high risk in the risk level distribution matrix to determine whether any meteorological element is in a medium risk state, and generating a medium risk area identification; Marking the remaining unidentified areas in the risk level distribution matrix as low-risk areas, and generating low-risk area identifications; Merging the high-risk area identifier, the medium-risk area identifier, and the low-risk area identifier to form a final risk area distribution matrix; The comprehensive risk zoning map is generated based on the final risk area distribution matrix.

8. A device for risk zoning of helicopter flights, characterized in that: include: A processing module is used to obtain a fused data set containing multiple meteorological elements through data fusion processing based on multi-source meteorological data; a classification module for classifying and thresholding meteorological elements according to different flight scenarios based on the fused data set to obtain a meteorological element threshold breakpoint set; a synthesis module, configured to perform frequency statistics and data synthesis on the fused data set based on the meteorological element threshold breakpoint set to obtain a multi-layer meteorological element frequency data set; An analysis module is used to obtain an initial clustering result of each meteorological element through cluster analysis based on the meteorological element frequency data set; A clustering module is used to classify the risk level of each meteorological element according to the initial clustering results to obtain a standardized single-element risk zoning result; The fusion module is used to obtain a comprehensive risk zoning map based on the single-factor risk zoning results by adopting a multi-factor fusion method.

9. An electronic device comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 7.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are configured to cause the computer to execute the method according to any one of claims 1 to 7.

Images