A method and system for identifying abnormal flight limit exceeding events

Abstract

The present invention provides a method and system for identifying abnormal flight overrun events, which are applied to the field of data processing technology. Based on historical abnormal flight overrun event data and geographical environment information and flight rule information of different airspaces, the present application processes flight trajectory data and flight attitude data to generate flight state characteristic parameter information; processes aircraft performance parameter data to generate aircraft performance element correlation information; processes flight state characteristic parameter information and aircraft performance element correlation information to generate preliminary identification information of abnormal flight events; processes flight trajectory data based on the preliminary identification information of abnormal flight events to generate abnormal flight overrun judgment information; and processes the preliminary identification information and abnormal flight overrun judgment information of abnormal flight events based on a target abnormal flight overrun event warning model to generate abnormal flight overrun event warning result information.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for identifying abnormal flight limit exceeding events. Background Art

[0002] In the aviation sector, ensuring flight safety remains a top priority. With the continuous improvement of aircraft performance and the increasing complexity of flight missions, accurately identifying abnormal flight limit violations has become increasingly critical. Currently, the industry's processing of flight data often focuses on analyzing a single dimension or a few parameters, making it difficult to fully capture abnormal flight conditions. For example, traditional methods may focus solely on significant deviations from the flight trajectory, while ignoring the combined influence of flight attitude, aircraft performance factors, and external environmental factors. When analyzing flight trajectories, the geographic environment and flight rules of different airspaces are not fully integrated, resulting in limited assessment of abnormal conditions. Furthermore, historical data on abnormal flight limit violations is insufficiently utilized to effectively identify patterns and apply them to current flight status assessments. Furthermore, existing anomaly identification technologies suffer from shortcomings in data fusion and algorithm application, making it difficult to accurately generate abnormal flight risk assessments and provide reliable early warnings for flight safety, posing potential threats to flight safety.

[0003] It should be noted that the information disclosed in the above background technology section is only used to enhance the understanding of the background of the present disclosure, and therefore includes information that does not constitute prior art known to ordinary technicians in this field. Summary of the Invention

[0004] The purpose of this application is to provide a method and system for identifying abnormal flight over-limit events, which at least to a certain extent overcomes the problems existing in the prior art by focusing on the accurate identification of abnormal flight over-limit events. First, various information such as flight trajectory, attitude, performance parameters, historical events, geographical environment and flight rules are collected. Afterwards, based on historical, geographical and rule data, the flight trajectory, attitude and performance parameter data are processed to obtain information related to flight status characteristic parameters and aircraft performance elements. The random forest algorithm is then used to process this information to obtain preliminary identification information of abnormal flight events, and abnormal flight over-limit judgment information is generated in combination with the flight trajectory data. Finally, the relevant information is analyzed through the target warning model to generate a risk assessment value, adjust the warning parameters, and convert to obtain the warning results, so as to help relevant personnel ensure flight safety and reduce risks.

[0005] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by practice of the invention.

[0006] According to one aspect of the present application, a method for identifying abnormal flight exceedance events is provided, including: acquiring flight trajectory data, flight attitude data, aircraft performance parameter data, historical abnormal flight exceedance event data, geographical environment information of different airspaces, and flight rule information; processing the flight trajectory data and flight attitude data based on the historical abnormal flight exceedance event data and the geographical environment information and flight rule information of different airspaces to generate flight status characteristic parameter information; processing the aircraft performance parameter data based on the historical abnormal flight exceedance event data and the geographical environment information and flight rule information of different airspaces to generate aircraft performance element association information; processing the flight status characteristic parameter information and the aircraft performance element association information to generate preliminary identification information of the abnormal flight event; processing the flight trajectory data based on the preliminary identification information of the abnormal flight event to generate abnormal flight exceedance judgment information; processing the preliminary identification information of the abnormal flight event and the abnormal flight exceedance judgment information based on the target abnormal flight exceedance event warning model to generate abnormal flight exceedance event warning result information.

[0007] Another aspect of the present application is an identification device for abnormal flight exceeding limit events, characterized in that it includes: an acquisition module for acquiring flight trajectory data, flight attitude data, aircraft performance parameter data, historical abnormal flight exceeding limit event data, geographical environment information of different airspaces, and flight rule information; a processing module for processing the flight trajectory data and flight attitude data based on the historical abnormal flight exceeding limit event data and the geographical environment information and flight rule information of different airspaces to generate flight status characteristic parameter information; processing the aircraft performance parameter data based on the historical abnormal flight exceeding limit event data and the geographical environment information and flight rule information of different airspaces to generate aircraft performance element association information; processing the flight status characteristic parameter information and the aircraft performance element association information to generate preliminary identification information of the abnormal flight event; processing the flight trajectory data based on the preliminary identification information of the abnormal flight event to generate abnormal flight exceeding limit judgment information; processing the preliminary identification information of the abnormal flight event and the abnormal flight exceeding limit judgment information based on the target abnormal flight exceeding limit event warning model to generate abnormal flight exceeding limit event warning result information.

[0008] According to another aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a second processor, the method for identifying abnormal flight limit violations is implemented.

[0009] The present application provides a method and system for identifying abnormal flight over-limit events, and the server focuses on the accurate identification of abnormal flight over-limit events. First, various information such as flight trajectory, attitude, performance parameters, historical events, geographical environment and flight rules are collected. Afterwards, based on historical, geographical and rule data, the flight trajectory, attitude and performance parameter data are processed to obtain information related to flight status characteristic parameters and aircraft performance elements. The random forest algorithm is then used to process this information to obtain preliminary identification information of abnormal flight events, and abnormal flight over-limit judgment information is generated in combination with the flight trajectory data. Finally, the relevant information is analyzed through the target warning model to generate a risk assessment value, adjust the warning parameters, and convert to obtain the warning results, helping relevant personnel to ensure flight safety and reduce risks.

[0010] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] Figure 1 A flowchart illustrating a method for identifying an abnormal flight limit violation event provided by an embodiment of the present application is shown;

[0012] Figure 2 A schematic structural diagram of a device for identifying abnormal flight limit violations provided in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0013] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0014] The following combination Figure 1 To describe the method for identifying abnormal flight limit exceeding events according to an exemplary embodiment of the present application. In one embodiment, the present application also proposes a method and system for identifying abnormal flight limit exceeding events. Figure 1 As shown, the method is applied to the server and includes:

[0015] S101, obtaining flight trajectory data, flight attitude data, aircraft performance parameter data, historical abnormal flight limit violation event data, geographical environment information of different airspaces and flight rule information.

[0016] In one embodiment, the actual path information of the aircraft during flight includes changes in latitude, longitude, and altitude over time. This data directly reflects the aircraft's flight path. By analyzing the trajectory data, it can be determined whether the aircraft has deviated from the planned route and whether the flight path complies with airspace planning and navigation requirements, providing a basis for subsequent determination of flight anomalies. Flight attitude data includes information such as the aircraft's pitch angle, roll angle, and yaw angle, reflecting the aircraft's attitude changes in the air. Whether the flight attitude is stable is crucial to flight safety. Abnormal attitude changes indicate a malfunction in the aircraft's control system or a special situation, and are an important indicator for assessing flight status.

[0017] Aircraft performance parameter data covers a wide range of data, including engine thrust, fuel consumption, avionics system operating parameters, and airframe structural stress conditions. Engine thrust and fuel consumption reflect the performance of the power system, avionics system parameters are related to the proper operation of functions such as communication, navigation, and surveillance, and airframe structural stress data is related to the safety of the aircraft's structure. These parameters help understand the operating status of each aircraft system and determine whether any performance anomalies exist. Historical abnormal flight limit event data records detailed information about past abnormal flight limit events, such as the event type (altitude or speed limit), the airspace in which the event occurred, the flight phase, the impact, and the severity. By analyzing historical data, patterns and patterns in the occurrence of abnormal events can be identified, providing a reference for analyzing current flight conditions and assisting in determining whether potential risks exist in the current flight state.

[0018] Geographical environment information for different airspaces includes topography (mountains, plains, etc.) and meteorological conditions (temperature, air pressure, wind speed and direction, etc.). Complex terrain affects aircraft flight trajectory and performance, and adverse weather conditions pose a significant threat to flight safety. Understanding this geographical environment information helps analyze its impact on current flight conditions and, combined with other data, more accurately assess flight status. Flight rules information includes flight restrictions, altitude regulations, speed limits, communication requirements, and other regulations for different airspaces. Flight rules are crucial guidelines for ensuring flight safety and order, and aircraft must strictly adhere to them. Obtaining this flight rules information can be used to compare actual aircraft flight data to determine whether the aircraft has violated operational regulations, providing a basis for identifying abnormal flight conditions.

[0019] S102 , based on historical abnormal flight limit exceeding event data and geographical environment information and flight rule information of different airspaces, the flight trajectory data and flight attitude data are processed to generate flight status characteristic parameter information.

[0020] In one implementation, feature extraction is performed on historical abnormal flight limit-exceeding event data to generate event type features, occurrence airspace features, flight phase features, and event severity features. If there is a historical abnormal flight event, the event type is "altitude limit exceeding," and this type feature can clearly identify the nature of the anomaly; the occurrence airspace is "mountainous airspace near a certain airport," which identifies the location of the event. The complex terrain of the mountainous airspace may be related to the anomaly; the flight phase is "takeoff and climb phase," and different flight phases have different requirements for aircraft performance and operation. The occurrence of anomalies in this phase has specific causes; the severity of the event is assessed as "serious," which affects the safe flight of the aircraft. These features provide key information for analyzing similar abnormal events. Quantitative analysis and processing are performed on the geographical environment information and flight rules information of different airspaces to generate quantitative factors for airspace terrain complexity, quantitative factors for airspace meteorological impact, and quantitative factors for rule strictness. In a certain airspace, through analysis of terrain data, the quantification factor of the airspace terrain complexity was found to be 0.8 (the value range is 0-1, and the larger the value, the more complex the terrain), indicating that the terrain in this airspace is complex and may affect the aircraft's flight trajectory and performance; based on meteorological data, the quantification factor of the airspace meteorological impact was calculated to be 0.6, indicating that meteorological conditions have a certain impact on flight, such as strong winds and low visibility; the flight rules in this airspace are strict, and after quantitative analysis, the quantification factor of the rules strictness was found to be 0.7, which means that aircraft flying in this airspace need to strictly abide by many rules, and any illegal operations may cause abnormalities.

[0021] Feature extraction and processing are performed on flight trajectory data to generate trajectory deviation features, trajectory change frequency features, and trajectory speed change features. During one flight, the aircraft's actual flight trajectory differed from the planned route. The trajectory deviation feature showed an average deviation of 5 kilometers, indicating that the aircraft had deviated from its normal route. Over a period of time, the trajectory change frequency feature showed significant trajectory changes every 10 minutes, a relatively frequent occurrence that may indicate an anomaly. The trajectory speed change feature indicated significant speed fluctuations over a certain period, with a maximum speed change of 20 knots, potentially impacting flight safety and stability. Feature extraction and processing are performed on flight attitude data to generate attitude angle deviation features and attitude change rate features. During flight, the attitude angle deviation feature showed a maximum deviation of 5 degrees from the standard attitude, exceeding the normal range and potentially affecting the aircraft's lift and flight direction. The attitude change rate feature indicated that at one point, the aircraft's roll angle changed at a rate of 3 degrees per second, an excessively rapid change that challenged the aircraft's control and stability, suggesting a problem with the aircraft's control system or a unique situation.

[0022] Based on the quantification factors of airspace terrain complexity, airspace meteorological impact, and rule strictness, trajectory deviation, trajectory change frequency, trajectory velocity, attitude angle deviation, and attitude change rate, the trajectory and attitude comprehensive quantitative features are fused to generate trajectory comprehensive quantitative features and attitude comprehensive quantitative features. Combining the quantitative factors of a particular airspace with the flight trajectory and attitude features, for example, if the airspace terrain complexity quantification factor is 0.8 and the average deviation distance in the trajectory deviation features is 5 kilometers, the weighted average fusion algorithm yields a trajectory comprehensive quantitative feature value of 0.7 (ranging from 0 to 1, with larger values ​​indicating a higher likelihood of anomaly), indicating a certain risk of abnormal trajectory deviation in this complex terrain airspace. Similarly, if the airspace meteorological impact quantification factor is 0.6 and the roll angle change rate in the attitude change rate feature is 3 degrees per second, the attitude comprehensive quantitative feature value is 0.65, indicating that the weather conditions and the current attitude change rate together indicate a certain tendency for abnormal aircraft attitude.

[0023] Based on event type characteristics, occurrence airspace characteristics, flight phase characteristics, and event severity characteristics, the trajectory and attitude comprehensive quantitative features are analyzed and processed to generate flight status characteristic parameter information. Combining the previously mentioned historical event characteristics with the fused quantitative features, if a historical altitude overrun event occurred during takeoff and climb in a mountainous airspace and was classified as "severe," the current trajectory comprehensive quantitative characteristic value would be 0.7, and the attitude comprehensive quantitative characteristic value would be 0.65. Through analysis and processing, the generated flight status characteristic parameter information indicates that the current flight status presents a high risk, sharing similarities with the characteristics of historical altitude overrun events. Close monitoring of the aircraft's flight trajectory and attitude changes is necessary, and timely measures should be taken to prevent abnormal flight overrun events.

[0024] S103 , based on historical abnormal flight limit violation event data and geographical environment information and flight rule information of different airspaces, the aircraft performance parameter data is processed to generate aircraft performance factor correlation information.

[0025] In one embodiment, the geographical environment information and flight rule information of different airspaces are quantitatively analyzed and processed to generate a quantitative factor for the airspace altitude, a quantitative factor for the airspace meteorological complexity, and a quantitative factor for the intensity of flight rule restrictions. The altitude of the airspace has many impacts on aircraft flight. Assuming that the average altitude of this particular airspace is 3,000 meters, in order to measure the degree of its impact on flight, it is necessary to compare it with the standard altitude. The standard altitude is an altitude benchmark value used for unified reference in the aviation field. Different flight missions and aircraft types have relatively stable performance at the standard altitude.

[0026] Standard altitude The average altitude of this particular airspace is H = 3000 meters. The relationship between air density and altitude is: ,in is the air density at standard altitude (assuming it is known that ), Is the air density at altitude H. The relationship coefficient between engine thrust and intake volume (obtained through engine performance testing, =0.8, which means that the air intake decreases by 1% and the thrust decreases by 0.8%). The coefficient of lift, air density and speed (obtained through research on aircraft lift systems, =0.6, indicating the degree of influence of air density change on lift). The influence coefficient of speed adjustment on maintaining flight altitude (obtained through flight mechanics research, =0.5, indicating the importance of speed adjustment to maintaining altitude after lift reduction). Engine thrust influence weight =0.4, lift influence weight =0.4, speed adjustment influence weight =0.2 .

[0027] Calculate the air density of the airspace ;

[0028] Air density change ratio ; Calculate the degree of impact on engine thrust: engine thrust reduction ratio ;

[0029] Calculate the degree of lift impact: lift reduction ratio ;

[0030] Calculate the speed to maintain the flight altitude and adjust the proportion: the speed needs to increase proportion ;

[0031] Comprehensive impact value The maximum value of the comprehensive impact value (Through a large number of calculations and empirical determinations at different altitudes, assuming ), airspace altitude quantification factor .

[0032] Calculations have yielded a quantification factor for the airspace's altitude of 0.6 (ranging from 0 to 1). This means that the altitude in this airspace has a moderate to high impact on flight. For example, higher altitudes reduce air density, resulting in less air intake for aircraft engines, which in turn affects engine thrust output. Furthermore, this reduced air density reduces the lift generated by the aircraft's wings, requiring higher speeds to maintain altitude. This places higher demands on the aircraft's propulsion system and flight operations.

[0033] Meteorological conditions are a key factor affecting flight safety. Severe convective weather frequently occurs in this particular airspace, making the weather complex and volatile. To quantify this complexity, a specific quantitative model is needed to analyze meteorological data. The diversity of meteorological data is reflected in multiple aspects, including changes in temperature, humidity, air pressure, wind speed, wind direction, and precipitation. Severe convective weather can cause these meteorological factors to fluctuate dramatically over a short period of time. For example, in areas of severe convective weather, vertical wind shear can be significant, causing severe turbulence during aircraft transit, severely impacting flight stability. Sudden changes in horizontal wind direction can also complicate aircraft navigation and control. Using statistical analysis methods, the frequency and magnitude of changes in various elements in historical meteorological data, as well as the correlations between these elements, are analyzed to derive a quantitative value reflecting the meteorological complexity of the airspace. In this example, the quantitative factor for the airspace's meteorological complexity is 0.8, indicating that the meteorological conditions in this airspace have a significant impact on flight. Aircraft face a high meteorological risk when operating in this airspace, requiring pilots to pay close attention to weather changes and adjust their flight strategies promptly.

[0034] Flight rules are crucial for ensuring flight safety and order, and the degree of restrictions varies across different airspaces. Certain airspaces impose strict restrictions on aircraft speed, altitude, and other factors. Assessing the strength of flight rule restrictions requires comprehensive consideration of multiple factors, including the airspace's traffic volume, the layout of surrounding airports, and the impact of military activity on flight. Airspaces with high traffic volumes will impose strict controls on speed and altitude to prevent collisions. Nearby military activity areas will also impose numerous restrictions on civilian aircraft to ensure safety. Using professional assessment methods, these restrictive factors were analyzed and quantified, resulting in a flight rule restriction strength quantification factor of 0.7. This means that aircraft operating in this airspace must strictly adhere to these rules; any violation could result in a safety incident. For example, aircraft speed adjustments must occur at a prescribed rate, and altitude changes must occur within a specified range. This places high demands on pilots' operational precision and awareness of the rules.

[0035] Quantitative factors for airspace altitude, airspace weather complexity, and flight rules restriction intensity play a crucial role in the subsequent analysis of the relationship between aircraft performance and the flight environment. Airlines can use these quantitative factors to develop more optimized flight plans for different flights. For flights to this airspace, aircraft models better suited to high altitudes, complex weather conditions, and strict regulatory restrictions can be selected. During pre-flight preparation, crew members can use these quantitative factors to understand potential difficulties encountered during the flight and prepare countermeasures in advance, such as developing contingency plans for special weather conditions and familiarizing themselves with the specific flight rules for the airspace. During flight, real-time monitoring systems can combine these quantitative factors with actual aircraft performance data to more accurately assess the aircraft's operating status, promptly identify potential safety hazards, and provide strong support for flight safety.

[0036] Aircraft performance parameter data is processed through feature extraction to generate thrust characteristics, fuel consumption characteristics, avionics system performance characteristics, and airframe structural stress characteristics. During a particular flight, sensors collect data. The engine's average thrust during a specific phase is 100 kilonewtons, representing the thrust characteristic. During this phase, the aircraft consumes 500 liters of fuel per 100 kilometers of flight, representing the fuel consumption characteristic. Regarding the avionics system, communication signal strength remains stable at over 90%, and navigation positioning error is within acceptable limits. These characteristics constitute the avionics system performance characteristics. Stress sensors monitor a stress of 50 MPa on key aircraft components, representing the structural stress characteristic. These characteristics reflect the real-time operating status of the aircraft's systems during flight.

[0037] Based on the airspace altitude quantification factor, airspace weather complexity quantification factor, and flight rules restriction intensity quantification factor, thrust characteristics and fuel consumption characteristics are integrated to generate airspace-power correlation quantitative characteristics. An airspace altitude quantification factor of 0.6 indicates that the altitude in this airspace has an above-average impact on flight. Higher altitudes reduce air density, resulting in less engine air intake, impacting thrust output. This also reduces lift, requiring more power to maintain altitude. A weather complexity quantification factor of 0.8 indicates complex weather conditions in this airspace. Severe weather conditions, such as severe convective weather, can cause aircraft to experience turbulence and wind shear, placing higher demands on the aircraft's powertrain stability and responsiveness. A flight rules restriction intensity quantification factor of 0.7 indicates that this airspace has strict restrictions on aircraft speed and altitude changes. Under these regulations, frequent speed and altitude adjustments increase the workload of the powertrain. The aircraft's thrust characteristic is 100 kilonewtons, reflecting the engine's output capacity; the fuel consumption characteristic is 500 liters per 100 kilometers, reflecting the aircraft's fuel consumption during this period. The principle and application of the fusion algorithm is to comprehensively consider these factors through a pre-defined fusion algorithm (such as weighted averaging). The weighted averaging algorithm assigns different weights to each factor based on its importance to the aircraft's power system. Assume that after extensive experiments and data analysis, the airspace altitude quantification factor weight is determined to be 0.2, the weather complexity quantification factor weight is 0.4, the regulation restriction intensity quantification factor weight is 0.3, the thrust characteristic weight is 0.05, and the fuel consumption characteristic weight is 0.05. The airspace and power correlation quantitative characteristic value is calculated as follows: This fusion algorithm integrates different factors, converting multiple seemingly independent data into a quantitative characteristic value that comprehensively reflects the relationship between airspace and power, and can more intuitively evaluate the status of the aircraft power system in a specific environment.

[0038] The quantitative characteristic value of the airspace-power correlation obtained above is 0.75, indicating that the overall performance of the aircraft's power system exhibits certain abnormalities under the constraints of this airspace environment and regulations. The data indicates that 0.75 is relatively high, indicating that the combined impact of the airspace environment and regulations on the power system is significant. In this airspace, the changes in air density caused by high altitude, the additional power requirements in complex weather conditions, and the frequent power adjustments required by strict flight regulations all combine to place significant strain on the aircraft's power system. For example, due to the high quantitative factor of weather complexity, the engine requires frequent thrust adjustments to maintain flight stability and safety during severe convective weather, which may result in increased fuel consumption. However, the current thrust and fuel consumption performance deviates significantly from the ideal state under the airspace environment and regulations, necessitating attention to the rationality of thrust and fuel consumption. Airlines and flight crews can use this quantitative characteristic value to proactively implement countermeasures, such as checking engine performance and optimizing flight plans to reduce unnecessary power consumption, thereby ensuring flight safety and cost control.

[0039] Based on the quantitative factors of airspace altitude, airspace weather complexity and flight rules restriction strength, the avionics system performance characteristics and the airframe structure stress characteristics are fused to generate quantitative characteristics of airspace and system association. A linear weighted approach is used to fuse various indicators. Let the airspace altitude quantitative factor be A, the airspace weather complexity quantitative factor be B, the flight rules restriction strength quantitative factor be C, the avionics system communication signal strength be D (value range 0-1), the navigation positioning error be E (normalize the error degree to (0-1, the smaller the value, the smaller the error), and the airframe structure stress be F (also normalized to 0-1). Assume that the weights of each item are , , , , , Then the calculation formula of the quantitative characteristic value S associated with the spatial domain and the system is: .

[0040] During flight, accurately assessing the compatibility of the avionics system and airframe structure with the flight environment is crucial to ensuring flight safety. Taking a flight in a specific airspace as an example, this paper analyzes in detail the calculation process and significance of the quantitative characteristic values ​​associated with the airspace and the system. The airspace altitude quantification factor A=0.6 indicates that altitude has a certain impact on flight. The airspace meteorological complexity quantification factor B=0.8 indicates complex weather conditions and the possibility of severe convection and other adverse weather conditions. The flight rules restriction intensity quantification factor C=0.7 indicates that the airspace has strict restrictions on aircraft speed, altitude changes, and other factors.

[0041] The avionics system communication signal strength remains stable above 90%, or D = 0.9, indicating a reliable communication link, ensuring normal information exchange between the aircraft and the outside world. The navigation positioning error is within the allowable range. Assuming it is normalized to E = 0.9 (smaller errors are closer to 1), the aircraft can accurately determine its position and fly along its planned route. The structural stress on the aircraft is 50 MPa, and after normalization, F = 0.8 (assuming normalization based on the aircraft's structural design and safety standards). This value is within the safe range and reflects the stress the aircraft is experiencing during flight.

[0042] Substitute the above indicators into the linear weighted fusion algorithm formula: The calculated quantitative eigenvalue for the airspace-system correlation is 0.6. This indicates that under current airspace conditions and regulations, the avionics system and airframe structure are moderately compatible with the environment. While the avionics system currently has good communication, accurate navigation and positioning, and the airframe structure is operating normally, overall operation is stable, potential risks still exist.

[0043] Due to the high quantitative factor of meteorological complexity in this airspace, severe weather conditions may interfere with avionics system communications. For example, lightning activity during severe convective weather can trigger strong electromagnetic interference, leading to interruption or distortion of communication signals, affecting communication between pilots and the ground and remote control of the aircraft. At the same time, strong winds and airflow changes in complex weather conditions may cause sudden changes in the stress on the aircraft structure, exceeding the safe range and threatening the safety of the aircraft structure. Based on the moderate level of adaptability reflected by the quantitative characteristic value, airlines and flight crews need to continuously monitor changes in environmental factors and formulate countermeasures in advance. For example, they can adjust the flight altitude or route before weather conditions deteriorate, and increase the frequency of monitoring of the avionics system and aircraft structure to ensure flight safety.

[0044] Based on the event type, airspace characteristics, flight phase characteristics, and event severity characteristics of historical abnormal flight limit exceedance event data, the quantitative characteristics of airspace-powertrain correlation and airspace-system correlation were analyzed and processed to generate aircraft performance factor correlation information. The historical data includes a serious abnormal event, a powertrain failure, which occurred in airspace similar to the current flight, during the cruise phase. When the current flight was operating in this airspace, the quantitative characteristics of airspace-powertrain correlation were 0.75, and the quantitative characteristics of airspace-system correlation were 0.6. This analysis revealed that the powertrain performance of the current flight in this airspace bears some resemblance to that of the historical abnormal event. The generated aircraft performance factor correlation information indicates that the powertrain operating status requires particular attention during the current flight phase. Although the avionics system and airframe structure are currently within normal ranges, continuous monitoring is required to prevent abnormal conditions and ensure flight safety.

[0045] S104: Process the flight status characteristic parameter information and the aircraft performance factor correlation information to generate preliminary identification information of the abnormal flight event.

[0046] In one embodiment, flight status characteristic parameter information is extracted and classified to generate information on abnormal flight trajectory changes, abnormal flight attitude fluctuations, and abnormal flight status stability. For example, suppose that during a flight, flight trajectory data shows that its average deviation from the scheduled route suddenly increases from a normal 0.5 km to 2 km, and that this deviation fluctuates significantly over a period of time. This constitutes abnormal flight trajectory change information. Regarding flight attitude, the aircraft's pitch angle should normally remain within a relatively stable range, such as within plus or minus 3 degrees. However, during a certain period, the pitch angle frequently fluctuates significantly between plus or minus 5 degrees. This constitutes abnormal flight attitude fluctuation information. Abnormal flight status stability information can be determined through a comprehensive analysis of flight trajectory and attitude data. For example, during the cruising phase, the aircraft's speed and attitude should normally be relatively stable. However, if the aircraft's speed fluctuates significantly and its attitude angle fluctuates frequently, this indicates abnormal flight status stability.

[0047] Information related to aircraft performance elements is extracted and classified to generate information on abnormal aircraft power performance, abnormal avionics system performance, and abnormal airframe structural stress. Regarding aircraft power performance, if the engine thrust drops from the rated 120 kN to 80 kN in a short period of time and fails to return to normal, this constitutes abnormal aircraft power performance. For the avionics system, if the communication signal strength drops sharply from a stable 95% to 70% with frequent signal interruptions, or if the navigation positioning error exceeds the allowable range (e.g., the positioning error originally within 50 meters now reaches 200 meters), these are all considered abnormal avionics system performance information. Regarding airframe structural stress, sensors detected a stress of 80 MPa on a key part of the aircraft's wing, compared to the upper limit of 60 MPa during normal operation. This indicates abnormal airframe structural stress and constitutes abnormal airframe structural stress information.

[0048] The random forest algorithm processes information on abnormal flight trajectory changes, abnormal flight attitude fluctuations, abnormal flight stability, abnormal aircraft power performance, abnormal avionics system performance, and abnormal airframe structural stresses to generate abnormal flight event probability information and an assessment of the severity of the abnormal flight event. The random forest algorithm comprehensively considers all of this abnormal information. Trained with extensive historical data, the model performs calculations upon receiving this abnormal information for a particular flight. If the model outputs an abnormal flight event probability of 0.8 (a value ranges from 0 to 1, with higher values ​​indicating a higher probability of an abnormal event), this indicates a high probability of an abnormal flight event. The model also assesses the severity of the abnormal flight event as "serious" because abnormalities in multiple aspects, including flight trajectory, attitude, power, avionics, and airframe structure, collectively pose a significant threat to flight safety. This indicates that the flight's current flight status is extremely unstable and requires immediate action, such as adjusting flight strategy and inspecting aircraft systems, to avoid a potential serious accident.

[0049] In another embodiment, target data within the flight status characteristic parameter information and aircraft performance element correlation information is labeled and screened based on abnormal flight event probability information and abnormal flight event severity assessment information to generate potential abnormal flight event data screening results. In aviation safety monitoring systems, accurate identification of abnormal flight events is crucial for ensuring flight safety. When a random forest algorithm processes a flight and determines that the probability of an abnormal flight event is 0.8 (a high probability) and the severity is assessed as "severe," subsequent in-depth analysis and processing of the relevant data becomes particularly important. As a powerful machine learning tool, the random forest algorithm integrates the prediction results of multiple decision trees. By learning from a large amount of historical flight data, corresponding flight status, and abnormal event scenarios, it can relatively accurately assess the probability and severity of an abnormality occurring in the current flight. In this example, an abnormal flight event probability of 0.8 means there is an 80% probability of an abnormal flight event occurring under the current flight conditions, while a severity assessment of "severe" indicates that an abnormality would pose a significant threat to flight safety.

[0050] In terms of flight status characteristic parameter information, the flight trajectory is an important basis for determining whether the flight is normal. Under normal circumstances, the average deviation distance of the aircraft from the route should be within 0.5 kilometers, which is the standard range for ensuring flight safety and order. However, when the average deviation distance of the aircraft from the route is monitored to reach 2 kilometers, this significant deviation, combined with the previously obtained high abnormal probability and severity assessment, makes it a key potential abnormality indicator. Larger trajectory deviations will cause the aircraft to enter a dangerous area, increasing the risk of conflict with other aircraft. It also means that the aircraft's navigation system has malfunctioned or is subject to external interference. Therefore, based on the set abnormality judgment rules, the trajectory deviation data will be marked as potential abnormal data.

[0051] Among the information related to aircraft performance factors, engine thrust is one of the core indicators for measuring the health of the aircraft's power system. The thrust of a normally operating engine should remain stable under rated conditions. If the engine thrust drops sharply from the rated 120 kN to 80 kN, this is a clear performance anomaly. Considering that the severity of the abnormal flight event was previously assessed as "serious", this thrust data was also marked as potentially abnormal data. The sudden drop in engine thrust may cause the aircraft to be unable to maintain normal flight speed and altitude, affecting flight stability and safety, and may even cause a more serious flight accident.

[0052] To comprehensively and accurately capture potentially abnormal data, a series of reasonable thresholds and rules must be established. These thresholds and rules are based on extensive historical data, industry standards, and the experience of flight safety experts. For example, for flight trajectory deviation, an average deviation distance exceeding 0.5 kilometers is set as an abnormality threshold; for engine thrust, a thrust drop exceeding a certain percentage (e.g., 20%) is considered abnormal. Within aircraft performance element correlation information, if the avionics system communication signal strength falls below 90% and persists for more than a certain period (e.g., one minute), it is considered unstable and classified as potentially abnormal data. Using these established thresholds and rules, a comprehensive scan of flight status characteristic parameter information and aircraft performance element correlation information is performed. During this scanning process, the system automatically compares real-time data with pre-set thresholds and rules. Any data that meets the abnormal criteria is flagged. After flagging, all flagged data is filtered out, and together they constitute the potential abnormal flight event data screening results. The potentially abnormal data screened encompasses multiple aspects, including trajectory deviation data and engine thrust anomaly data within the specified time period mentioned above, as well as unstable avionics system communication signal data. Unstable avionics system communication signals can lead to communication interruptions or errors between the aircraft and ground control centers, as well as other aircraft, compromising flight control and coordination, and posing a serious threat to flight safety. These potentially abnormal data reflect the aircraft's current abnormal condition from different perspectives. These data are interrelated and collectively indicate the possibility of an abnormal flight event, providing important evidence for subsequent analysis and decision-making.

[0053] The results of the potential abnormal flight event data screening are integrated and quantified to generate preliminary identification information for abnormal flight events. This information is used to characterize the likelihood of abnormal flight events, the flight systems involved, and the potential risk level. After obtaining the data screening results for potential abnormal flight events, they are integrated. Different types of potential abnormal data are classified according to flight systems, such as trajectory deviation data being classified as belonging to the flight trajectory system, thrust anomaly data being classified as belonging to the power system, and communication signal instability data being classified as belonging to the avionics system. Quantification is then performed to calculate a comprehensive anomaly index based on factors such as the number of abnormal data and the severity of the anomaly. The resulting anomaly index for this flight is 0.7 (ranging from 0 to 1, with larger values ​​indicating more severe anomalies). Based on this, the preliminary identification information of abnormal flight events generated shows that there is a high possibility that an abnormal flight event has occurred on this flight (echoing the previous abnormal probability information), involving multiple flight systems such as flight trajectory, power, and avionics. The potential risk level is relatively high, specifically manifested in flight trajectory deviation, insufficient power system thrust, unstable avionics system communication and other problems, which may pose a serious threat to flight safety, prompting relevant personnel to take timely measures to deal with it, such as further inspection of the aircraft system and adjustment of the flight plan.

[0054] S105: Process the flight trajectory data based on the preliminary identification information of the abnormal flight event to generate abnormal flight limit violation judgment information.

[0055] In one embodiment, preliminary identification information of abnormal flight events is extracted and classified to generate information on changes in the probability of abnormal events, the degree of abnormalities in the involved flight systems, and potential risk trends. Suppose the preliminary identification information for a particular flight abnormal event indicates a high probability of 0.8, involving multiple systems such as the flight trajectory, powertrain, and avionics. Information on changes in the probability of abnormal events is extracted from this information. For example, if the probability of an abnormal flight event for this flight has rapidly increased from 0.3 to 0.8 over a period of time, this indicates a significant change in the probability of abnormality. Regarding the degree of abnormality in flight systems, if the flight trajectory deviates by 2 kilometers (normally within 0.5 kilometers), the engine thrust decreases by 30% (far exceeding the normal fluctuation range), and the avionics system communication signal strength drops sharply from a stable 95% to 70%, these data can be used to assess the degree of abnormality in the flight trajectory system, the degree of abnormality in the powertrain system, and the degree of abnormality in the avionics system. Regarding potential risk trends, based on the aircraft's current state and environmental factors, if the flight is in airspace with complex weather conditions and multiple systems are experiencing abnormalities, an increasing potential risk trend is predicted for the coming period.

[0056] Flight trajectory data is extracted and classified to generate information on trajectory deviation magnitude changes, abnormal trajectory speed changes, and sudden trajectory direction changes. During the flight, flight trajectory data was continuously monitored. The trajectory deviation magnitude change information showed that the aircraft initially deviated from its route by a small distance, but at a certain moment, the deviation suddenly increased from 0.5 kilometers to 2 kilometers, a significant change in the magnitude of the deviation. Regarding the abnormal trajectory speed change information, the aircraft's normal speed during the cruising phase should remain stable around a certain value. However, the actual speed dropped from the standard 800 km / h to 700 km / h in a short period of time, and then quickly increased to 850 km / h. This speed fluctuation exceeded the normal range and is considered an abnormal trajectory speed change. Sudden trajectory direction changes indicate that the aircraft, while regularly changing direction according to its planned route during normal flight, suddenly experienced a turn angle far exceeding the normal turning range. For example, the normal turning angle was within 5 degrees, but this time it reached 15 degrees. This is considered a sudden trajectory direction change.

[0057] The random forest algorithm processes information on the probability of abnormal events, the degree of abnormalities in the flight systems involved, potential risk trends, changes in trajectory deviation magnitude, abnormal changes in trajectory speed, and sudden changes in trajectory direction to generate information on the probability of an abnormal flight exceeding limits and an assessment of the severity of the abnormal flight exceeding limits. The random forest algorithm, trained on extensive historical data, analyzes this information for this flight. The model, trained on this information, calculates this information based on the flight. The model comprehensively considers factors such as the large change in the probability of abnormal events, the high degree of abnormalities in multiple flight systems, the increasing trend in potential risk, and various abnormal trajectory changes. It outputs a probability of 0.9 (indicating a 90% probability of an abnormal flight exceeding limits event) and assesses the severity of the abnormal flight exceeding limits as "extremely severe." This is because multiple key indicators indicate that the aircraft's current state is extremely unstable, and any abnormality could have a devastating impact on flight safety.

[0058] Based on the abnormal flight exceedance probability information and the abnormal flight exceedance severity assessment information, target data within the preliminary abnormal flight event identification information and flight trajectory data are marked and screened to generate potential abnormal flight exceedance data screening results. Based on the previously obtained abnormal flight exceedance probability of 0.9 and severity assessment of "extremely severe," marking and screening rules are set. Within the preliminary abnormal flight event identification information, data related to high flight system anomalies, such as abnormal engine thrust and unstable avionics system communication signals, are marked. Within the flight trajectory data, data with large trajectory deviations, abnormal speed changes, and sudden changes in direction are also marked. These marked data are then screened to generate potential abnormal flight exceedance data screening results. Data showing a continuous decrease in engine thrust within a specific time period, data showing avionics system signal strength below a specific threshold, and data showing trajectory deviations exceeding warning values ​​are screened out as being closely associated with abnormal flight exceedance events.

[0059] The results of the potential abnormal flight limit violation data screening are integrated and quantified to generate abnormal flight limit violation judgment information. After obtaining the potential abnormal flight limit violation data screening results, the first step is to systematically integrate these data. This means categorizing and summarizing the data by flight system and anomaly type. Flight systems primarily include the flight trajectory system, power system, avionics system, and airframe structure system, while anomaly types include deviations, abnormal changes, and failures. For example, within the potential abnormal flight limit violation data for a particular flight, all data related to changes in trajectory deviation magnitude, abnormal changes in trajectory speed, and sudden changes in trajectory direction are grouped together. For the power system, data related to abnormal engine thrust, such as a sudden drop from the rated 120 kN to 80 kN, is separately aggregated. For the avionics system, data related to sudden drops in communication signal strength and navigation positioning errors exceeding the allowable range are classified as avionics system anomaly data. This categorized and summarized approach clearly identifies the anomalies within each flight system, facilitating subsequent targeted analysis and resolution.

[0060] After data integration, quantification is required to more accurately assess the severity of flight anomalies. This quantification process comprehensively considers multiple key factors, with the number of anomaly data and its severity being key elements. Different anomaly data types have varying impacts on flight safety, so corresponding weights are assigned to each anomaly type. Severe deviations from flight trajectory are given a higher weight because they directly impact whether the aircraft will enter a hazardous area and collide with other aircraft. Relatively minor anomalies, such as minor malfunctions of auxiliary equipment, are assigned lower weights. The number of anomaly data, their severity, and their corresponding weights are comprehensively calculated. When calculating the anomaly index for a particular flight, a weighted summation algorithm is used, resulting in a final value of 0.85 (ranging from 0 to 1, with higher values ​​indicating more severe anomalies). This index intuitively reflects the high level of anomaly conditions on the flight, indicating a significant safety risk.

[0061] Based on the calculated comprehensive anomaly index of 0.85, the generated abnormal flight limit violation information will provide critical information for flight safety decision-making. This information indicates a high probability of an abnormal flight limit violation on this flight. The flight systems involved include multiple critical systems, such as flight trajectory, powertrain, and avionics, all of which play an indispensable role in the aircraft's normal operation and flight safety. The severity of the anomaly indicates that the aircraft's current state has significantly deviated from normal operating ranges. Specifically, the flight trajectory has significantly deviated, with the aircraft straying significantly from its planned route. This not only increases the risk of collision with other aircraft but also places the aircraft in hazardous areas, such as no-fly zones or areas with complex terrain. Abnormal speed fluctuations affect the aircraft's stability, increasing the difficulty of flight operations and placing additional stress on the aircraft's structure, threatening the aircraft's safety. Insufficient engine thrust can prevent the aircraft from maintaining normal altitude and speed, potentially leading to a stall and a serious accident. Instable avionics system communications can interfere with communications between the pilot and ground control, as well as with other aircraft, compromising flight control and coordination, preventing the pilot from obtaining timely and accurate flight information, and further exacerbating flight risks. Given this, flight safety is seriously threatened, prompting immediate action. For example, air traffic control should direct the aircraft to land as quickly as possible, select an appropriate alternate airport, and ensure a safe landing to avoid the more serious consequences of continuing to fly under abnormal conditions. Alternatively, flight plans should be adjusted based on actual conditions, avoiding dangerous areas and rerouting routes to mitigate flight risks, safeguard the lives of passengers and crew, and ensure the safe operation of the aircraft.

[0062] S106 , processing the abnormal flight event preliminary identification information and the abnormal flight limit judgment information based on the target abnormal flight limit event warning model to generate abnormal flight limit event warning result information.

[0063] In one embodiment, a targeted abnormal flight overrun event warning model analyzes and processes preliminary abnormal flight event identification information and abnormal flight overrun judgment information to generate an abnormal flight risk assessment value. For example, suppose the preliminary abnormal flight event identification information for a particular flight indicates abnormal trajectory changes, indicating an average deviation of 2 kilometers from its flight path (normally within 0.5 kilometers), and abnormal flight attitude fluctuations, indicating frequent and significant fluctuations in the pitch angle between plus and minus 5 degrees (normally within plus and minus 3 degrees). Furthermore, the abnormal flight overrun judgment information indicates a probability of 0.9 (indicating a 90% probability of an abnormal flight overrun event), with a severity assessment of "extremely severe." Upon receiving this information, the targeted abnormal flight overrun event warning model analyzes factors such as the severity, probability of occurrence, and potential impact on flight safety, and calculates an abnormal flight risk assessment value of 0.8 (ranging from 0 to 1, with higher values ​​indicating higher risk). This indicates that the flight is currently at high risk, with a high probability of an abnormal flight overrun event, requiring close attention and appropriate measures.

[0064] Based on the abnormal flight risk assessment value, the warning decision parameter vector within the target abnormal flight limit event warning model is processed to generate a warning deviation correction vector. Upon receiving an abnormal flight risk assessment value of 0.8, the model adjusts certain parameters originally set within the warning decision parameter vector, such as sensitivity to flight trajectory deviation and weighting for abnormal event severity. For example, the weight for flight trajectory deviation distance was originally set to 0.3, but given the significant deviation and high risk assessment value of the flight, it is adjusted to 0.4. Similarly, the weight for a sub-parameter in the abnormal event severity assessment, originally set to 0.2, is now adjusted to 0.3. These parameter adjustments generate a new vector, the warning deviation correction vector. This vector records the direction and magnitude of the model's corrections to the original decision parameters based on the current flight situation, ensuring that subsequent warnings are more accurately aligned with actual flight conditions.

[0065] The warning deviation correction vector is parsed and converted to generate abnormal flight over-limit event warning result information. After parsing and converting the warning deviation correction vector, the generated abnormal flight over-limit event warning result information is displayed as follows: "The flight is currently in a highly dangerous state and an abnormal flight over-limit event is very likely to occur. The main abnormal conditions include serious deviations from the flight trajectory and abnormally unstable flight attitude. It is estimated that within the next 5-10 minutes, if effective measures are not taken, the aircraft may enter a no-fly zone and the risk of collision with other aircraft is extremely high. It is recommended to immediately guide the aircraft to make an emergency landing, select the nearest alternate airport, and closely monitor the various parameters of the aircraft." Such warning result information clearly points out the problems, potential risks and response suggestions during the flight, providing a clear decision-making basis for airlines, air traffic control departments and other relevant parties, and helping to take timely measures to ensure flight safety.

[0066] In another embodiment, the target abnormal flight overrun event warning model receives preliminary identification information and abnormal flight overrun assessment information. The preliminary identification information includes information on abnormal flight trajectory changes, abnormal flight attitude fluctuations, and abnormal aircraft power performance. The overrun assessment information includes key information such as the probability of abnormal flight overruns and severity assessment. The model comprehensively analyzes this information, considering factors such as the severity, probability of occurrence, and potential impact on flight safety, to calculate an abnormal flight risk assessment value. For example, if the preliminary identification information for a flight's abnormal flight event indicates significant deviations from the flight trajectory and frequent and significant fluctuations in flight attitude, and the overrun assessment information indicates a probability of 0.9 and an "extremely severe" severity assessment, the model calculates an abnormal flight risk assessment value of 0.8 (ranging from 0 to 1, with higher values ​​indicating higher risk), indicating a high-risk status for the flight.

[0067] Limit violations encompass both actual abnormal flight events and false triggers caused by data quality issues. These event records contain rich flight status information, which is crucial for understanding the nature of the anomaly. When a limit violation event is triggered, the system automatically saves the relevant parameters at the time of triggering. For example, at touchdown, these parameters may include not only speed and altitude, but also touchdown angle, pitch angle, roll angle, and engine thrust. These parameters describe the aircraft's flight status at that specific moment from multiple perspectives, providing comprehensive data support for subsequent analysis. For example, in one touchdown violation event, the recorded speed at touchdown was 250 knots, altitude was 10 meters, touchdown angle was 3 degrees, pitch angle was 5 degrees, roll angle was 2 degrees, and engine thrust was 80%. These parameters constitute the event's feature vector, reflecting the aircraft's specific flight conditions at that moment.

[0068] The extracted relevant parameters at the time of event triggering are used as input to the random forest algorithm. During the training phase, the random forest model is trained using known real and false over-limit event data. The model will learn the association patterns between different parameter combinations and the truth or falsehood of events. For example, when the touchdown speed is too high and the altitude is abnormal, the event is more likely to be a true abnormal event; when certain parameters have obvious data fluctuations or do not conform to normal flight logic, it may be a false trigger event. For new over-limit events, the random forest algorithm will judge the truth or falsehood of the event based on the input parameters through a voting mechanism of multiple decision trees. For example, for a new touchdown over-limit event, after the parameters are input, after voting by 100 decision trees, 80 of them believe that the event is true and 20 believe it is false, then the model will determine that the event is a true abnormal event.

[0069] After identifying true or false events, the model adjusts the internal warning decision parameter vector based on the abnormal flight risk assessment value. The abnormal flight risk assessment value is calculated by comprehensively considering factors such as the severity, probability of occurrence, and potential impact on flight safety of the abnormal flight event. The warning decision parameter vector includes multiple parameter weights related to abnormal flight judgment, which determine the importance of each parameter in the warning judgment. For example, parameters such as flight trajectory deviation distance, abnormal flight speed, and flight attitude change have corresponding weights. When a flight's abnormal flight risk assessment value is high, it indicates that the abnormal situation is more serious, and the warning decision parameter vector needs to be adjusted to improve the accuracy of the warning. For example, the original weight of flight trajectory deviation distance in the warning judgment was set at 0.3. Considering the serious deviation and high risk assessment value of this flight, the weight was adjusted to 0.4, indicating that the flight trajectory deviation distance parameter will play a more important role in subsequent warning judgments. Similarly, for the sub-parameters used in assessing the severity of abnormal events, such as the severity of flight attitude changes, the original weight was 0.2, but it has now been adjusted to 0.3 based on the risk assessment, allowing the model to pay more attention to changes in flight attitude when judging abnormal events.

[0070] By adjusting the warning decision parameter vector, a warning deviation correction vector is generated. This vector reflects the extent to which the model adjusts the warning judgment criteria based on the current flight situation. The purpose of the warning deviation correction vector is to make the model's subsequent warning judgments more accurate and consistent with actual flight conditions. For example, in previous warning judgments, improper weighting of certain parameters resulted in inaccurate or untimely warnings for some abnormal situations. By adjusting the parameter weights to generate the warning deviation correction vector, the model can more sensitively detect actual abnormal situations, reducing false alarms and improving its ability to warn of real abnormal events. The warning deviation correction vector is continuously updated based on new limit-exceeding events and abnormal flight risk assessments to ensure that the model maintains an accurate assessment of flight safety conditions. By combining limit-exceeding events with the random forest algorithm to optimize decision parameters, through data collection, algorithm analysis, and parameter adjustment, the abnormal flight event warning model can provide more intelligent and accurate warnings of flight safety conditions, providing strong support for aviation safety.

[0071] The warning deviation correction vector is parsed and converted to generate detailed abnormal flight limit event warning result information. This information not only clearly points out problems during flight, such as serious deviation from the flight trajectory and abnormal and unstable flight attitude, but also explains potential risks. For example, it is expected that within the next 5-10 minutes, if effective measures are not taken, the aircraft may enter a no-fly zone and the risk of collision with other aircraft is extremely high. At the same time, specific response suggestions are given, such as recommending that the aircraft be immediately guided to make an emergency landing, selecting the nearest alternate airport, and closely monitoring various aircraft parameters. This provides clear decision-making basis for airlines, air traffic control departments and other relevant parties, helping to ensure flight safety in a timely manner.

[0072] This application aims to achieve accurate identification of abnormal flight over-limit events. First, multi-source information such as flight trajectory, attitude, performance parameters, historical events, geographical environment and flight rules is obtained. Then, based on historical data, geographical environment and flight rules, the flight trajectory and attitude data, and aircraft performance parameter data are processed respectively to generate flight status characteristic parameter information and aircraft performance element correlation information. Then, the above two types of information are processed, and preliminary identification information of abnormal flight events is generated with the help of random forest algorithm, and then abnormal flight over-limit judgment information is obtained in combination with flight trajectory data. Finally, the target abnormal flight over-limit event warning model is used to analyze the preliminary identification and over-limit judgment information to generate an abnormal flight risk assessment value, and the warning decision parameter vector is adjusted accordingly. The warning result information is obtained through analytical conversion, which provides a strong guarantee for flight safety and helps relevant personnel to grasp the abnormal flight situation in a timely manner and take measures to reduce flight risks.

[0073] In one embodiment, Figure 2As shown, the present application also provides a device for identifying abnormal flight limit exceeding events, comprising:

[0074] Acquisition module 201, for acquiring flight trajectory data, flight attitude data, aircraft performance parameter data, historical abnormal flight limit violation event data, geographical environment information of different airspaces and flight rule information;

[0075] Processing module 202 is used to process flight trajectory data and flight attitude data based on historical abnormal flight limit violation event data and geographical environment information and flight rule information of different airspaces to generate flight status characteristic parameter information; process aircraft performance parameter data based on historical abnormal flight limit violation event data and geographical environment information and flight rule information of different airspaces to generate aircraft performance element association information; process flight status characteristic parameter information and aircraft performance element association information to generate preliminary identification information of abnormal flight events; process flight trajectory data based on the preliminary identification information of abnormal flight events to generate abnormal flight limit judgment information; process the preliminary identification information of abnormal flight events and abnormal flight limit judgment information based on the target abnormal flight limit violation event warning model to generate abnormal flight limit violation event warning result information.

[0076] Each embodiment of this application is described in a related manner. Similar portions between embodiments can be referenced to each other. Each embodiment focuses on the differences from other embodiments. In particular, the embodiments of the method, electronic device, electronic device, and readable storage medium for evaluating abnormal flight overrun events are generally similar to the aforementioned embodiment of the method for identifying abnormal flight overrun events, so the description is relatively simple. For relevant portions, reference can be made to the description of the aforementioned embodiment of the method for identifying abnormal flight overrun events.

Claims

1. A method for identifying abnormal flight limit exceeding events, characterized in that: include: Obtain flight trajectory data, flight attitude data, aircraft performance parameter data, historical abnormal flight limit event data, geographical environment information of different airspaces and flight rules information; Based on historical abnormal flight limit violation event data and geographical environment information and flight rule information of different airspaces, flight trajectory data and flight attitude data are processed to generate flight status characteristic parameter information, including feature extraction processing of historical abnormal flight limit violation event data to generate event type characteristics, occurrence airspace characteristics, flight phase characteristics, and event severity characteristics; Quantitative analysis and processing of geographical environment information and flight rule information of different airspaces are performed to generate quantitative factors of airspace terrain complexity, airspace meteorological impact, and rule strictness; feature extraction and processing of flight trajectory data are performed to generate trajectory deviation features, trajectory change frequency features, and trajectory speed change features; feature extraction and processing of flight attitude data are performed to generate attitude angle deviation features and attitude change rate features; Based on the quantitative factors of airspace terrain complexity, airspace meteorological impact, and rule strictness, the trajectory deviation characteristics, trajectory change frequency characteristics, trajectory speed change characteristics, attitude angle deviation characteristics, and attitude change rate characteristics are fused and processed to generate trajectory comprehensive quantitative characteristics and attitude comprehensive quantitative characteristics. Based on the event type characteristics, occurrence airspace characteristics, flight phase characteristics, and event severity characteristics, the trajectory comprehensive quantitative characteristics and attitude comprehensive quantitative characteristics are analyzed and processed to generate flight status characteristic parameter information. If the altitude overrun event in the historical event occurs during the takeoff and climb phase in a mountainous airspace and the severity is severe, the generated flight status characteristic parameter information will indicate that the current flight status is risky. Based on historical abnormal flight limit violation event data and geographical environment information and flight rules information of different airspaces, aircraft performance parameter data is processed to generate aircraft performance factor correlation information; Processing flight status characteristic parameter information and aircraft performance factor correlation information to generate preliminary identification information of abnormal flight events; Process the flight trajectory data based on the preliminary identification information of abnormal flight events to generate abnormal flight limit judgment information; Based on the target abnormal flight over-limit event warning model, the preliminary identification information of the abnormal flight event and the abnormal flight over-limit judgment information are processed to generate the abnormal flight over-limit event warning result information.

2. The method according to claim 1, wherein Based on historical abnormal flight limit violation event data and geographical environment information and flight rules information of different airspaces, aircraft performance parameter data is processed to generate aircraft performance factor correlation information, including: Quantitatively analyze and process the geographical environment information and flight rules information of different airspaces to generate quantitative factors for airspace altitude, airspace meteorological complexity, and flight rules restriction intensity; Perform feature extraction and processing on aircraft performance parameter data to generate thrust characteristics, fuel consumption characteristics, avionics system performance characteristics, and airframe structure stress characteristics; Based on the quantitative factors of airspace altitude, airspace meteorological complexity, and flight rules restriction intensity, the thrust characteristics and fuel consumption characteristics are fused to generate quantitative characteristics related to airspace and power. Based on the quantitative factors of airspace altitude, airspace meteorological complexity, and flight rules restriction intensity, the avionics system performance characteristics and the aircraft structure stress characteristics are integrated to generate quantitative characteristics related to airspace and system. Based on the event type characteristics, occurrence airspace characteristics, flight phase characteristics, and event severity characteristics in historical abnormal flight limit exceedance event data, the quantitative characteristics of the airspace-power association and the airspace-system association are analyzed and processed to generate aircraft performance factor association information.

3. The method according to claim 1, wherein Process the flight status characteristic parameter information and aircraft performance factor correlation information to generate preliminary identification information of abnormal flight events, including: Extract and classify the characteristic parameter information of the flight status to generate information on abnormal flight trajectory changes, abnormal flight attitude fluctuations, and abnormal flight status stability; Extract and classify the relevant information of aircraft performance elements to generate abnormal information of aircraft power performance, abnormal information of avionics system performance, and abnormal information of aircraft structure stress; Based on the random forest algorithm, the information on abnormal changes in flight trajectory, abnormal fluctuations in flight attitude, abnormal flight state stability, abnormal aircraft power performance, abnormal avionics system performance, and abnormal airframe structure stress is processed to generate abnormal flight event probability information and abnormal flight event severity assessment information.

4. The method according to claim 3, wherein Processing of flight status characteristic parameter information and aircraft performance factor correlation information to generate preliminary identification information of abnormal flight events, including: Based on the abnormal flight event probability information and abnormal flight event severity assessment information, target data in the flight status characteristic parameter information and aircraft performance element correlation information are marked and screened to generate potential abnormal flight event data screening results; The results of the data screening of potential abnormal flight events are integrated and quantified to generate preliminary identification information of abnormal flight events. The preliminary identification information of abnormal flight events is used to characterize the possibility of abnormal flight events, the flight systems involved and the potential risk level.

5. The method according to claim 1, wherein Based on the preliminary identification information of abnormal flight events, the flight trajectory data is processed to generate abnormal flight limit judgment information, including: Extract and classify preliminary identification information of abnormal flight events to generate information on the possibility of abnormal events, the degree of abnormality of the involved flight systems, and potential risk trends; Extract and classify flight trajectory data to generate information on trajectory deviation amplitude changes, abnormal trajectory speed changes, and sudden trajectory direction changes; Based on the random forest algorithm, the system processes information on the possibility of abnormal events, the degree of abnormalities in the flight system, potential risk trends, trajectory deviation amplitude changes, abnormal trajectory speed changes, and trajectory direction mutations to generate abnormal flight limit violation probability information and abnormal flight limit violation severity assessment information; Based on the abnormal flight limit violation probability information and abnormal flight limit violation severity assessment information, the target data in the abnormal flight event preliminary identification information and flight trajectory data are marked and screened to generate potential abnormal flight limit violation data screening results; The screening results of potential abnormal flight limit violations are integrated and quantified to generate abnormal flight limit violation judgment information.

6. The method according to claim 5, wherein Based on the target abnormal flight over-limit event warning model, the preliminary identification information of abnormal flight events and the abnormal flight over-limit judgment information are processed to generate abnormal flight over-limit event warning result information, including: Based on the target abnormal flight limit exceeding event warning model, the preliminary identification information of abnormal flight events and abnormal flight limit exceeding judgment information are analyzed and processed to generate abnormal flight risk assessment values; Based on the abnormal flight risk assessment value, the warning decision parameter vector within the target abnormal flight limit exceeding event warning model is processed to generate a warning deviation correction vector; The warning deviation correction vector is analyzed and converted to generate abnormal flight limit exceeding event warning result information.

7. A device for identifying abnormal flight limit events, characterized in that: For implementing the method of claim 1, the apparatus comprises: The acquisition module is used to obtain flight trajectory data, flight attitude data, aircraft performance parameter data, historical abnormal flight limit violation event data, geographical environment information of different airspaces and flight rules information; The processing module is used to process flight trajectory data and flight attitude data based on historical abnormal flight limit violation event data and geographical environment information and flight rule information of different airspaces to generate flight status characteristic parameter information; process aircraft performance parameter data based on historical abnormal flight limit violation event data and geographical environment information and flight rule information of different airspaces to generate aircraft performance element correlation information; process flight status characteristic parameter information and aircraft performance element correlation information to generate preliminary identification information of abnormal flight events; process flight trajectory data based on the preliminary identification information of abnormal flight events to generate abnormal flight limit judgment information; process the preliminary identification information of abnormal flight events and abnormal flight limit judgment information based on the target abnormal flight limit violation event warning model to generate abnormal flight limit violation event warning result information.

8. An electronic device, characterized in that: include: a first processor; and a memory for storing executable instructions of the first processor; The first processor is configured to execute the method for identifying abnormal flight limit exceeding events according to any one of claims 1 to 6 by executing the executable instructions.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the second processor, the method for identifying abnormal flight limit exceeding events according to any one of claims 1 to 6 is implemented.

Images