A route collision risk prediction method and system

Abstract

The application provides a flight route collision risk prediction method and system, the method comprises the following steps: a dynamic trajectory model for predicting the position of an aircraft in a future time period is established, and the position of the aircraft in the future time period is converted into a Beidou grid code; the flight routes of the aircrafts are preliminarily screened based on whether the time windows of different aircrafts overlap; the positions of the different aircrafts at a certain moment are calculated after the preliminary screening, the Beidou grid codes corresponding to the position coordinates of the aircrafts at the certain moment are obtained, and the spatial distances between the Beidou grid codes corresponding to the positions of the different aircrafts at the certain moment are calculated; the collision risk probability of the different aircrafts at the certain moment is determined and output according to the relative flight speed of the different aircrafts at the certain moment, the distance between the Beidou grid codes and the overlap proportion of the time windows, so that the calculation efficiency and accuracy of the collision risk evaluation are improved.

Description

Technical Field

[0001] This invention relates to the field of aircraft route planning and dynamic safety management, and in particular to a method and system for predicting route collision risks. Background Technology

[0002] With the widespread use of drones, aircraft, and other flying vehicles, route planning and safety management have become increasingly important.

[0003] Existing route planning methods suffer from low computational efficiency when processing large amounts of flight data, leading to poor route safety management. Specifically, current collision risk probability prediction methods typically use data on multiple collision risk influencing factors for all aircraft as direct input to the prediction model to obtain collision risk prediction probabilities. While this can achieve collision risk probability prediction, the large number of aircraft involved in the calculation results in a large number of routes, hindering computational efficiency. Furthermore, directly inputting only one collision risk factor for each aircraft into the prediction model yields inaccurate collision risk prediction probabilities.

[0004] To address this problem, the present invention provides a method and system for predicting flight path collision risks, thereby solving the aforementioned issues. Summary of the Invention

[0005] In order to solve the problems existing in the prior art, this invention innovatively proposes a method and system for predicting flight path collision risks, which effectively solves the problem of low computational efficiency or prediction accuracy of collision risk assessment caused by the prior art, and effectively improves the computational efficiency and accuracy of collision risk assessment.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: The flight information of different aircraft is acquired, including: takeoff time, set flight speed, current flight speed, current location, preset flight path, and flight duration. Based on the aircraft's takeoff time, set flight speed, current flight speed, current location, and preset flight path, a dynamic trajectory model is established to predict the aircraft's position in the future time period, and the aircraft's position in the future time period is converted into BeiDou grid code. A time window is constructed on the time axis based on the takeoff time and flight duration of the aircraft. The collision of aircraft routes is initially screened based on whether the time windows of different aircraft overlap. Calculate the position of different aircraft at a certain moment after the initial screening, obtain the BeiDou grid code corresponding to the coordinates of the aircraft's position at a certain moment, and calculate the spatial distance between the BeiDou grid codes corresponding to the positions of different aircraft at a certain moment. Based on the relative flight speed of different aircraft at a certain moment, the distance between BeiDou grid codes, and the overlap ratio of time windows, the collision risk probability of different aircraft at a certain moment is determined and output.

[0007] Optionally, a time window is constructed on the timeline based on the aircraft's takeoff time and flight duration. Preliminary screening for aircraft flight path collisions is performed based on whether the time windows of different aircraft overlap. Specifically, this includes: Using the takeoff time of the aircraft as the starting point of the time axis, a time window is established on the time axis for the duration of the aircraft's flight. It is determined whether the time windows of any two aircraft overlap. If they overlap, they are initially screened and passed. The overlap ratio of the time windows is the ratio between the overlap duration and the total length of the time windows of the two aircraft.

[0008] Furthermore, the preliminary screening for aircraft flight path collisions based on time windows constructed on the timeline according to the takeoff time and flight duration of the aircraft, and the existence of overlapping time windows for different aircraft, also includes: If there is no overlap, determine whether the time difference between the time windows of any two aircraft is less than a preset time threshold. If it is less, the initial screening is passed; if it is not less, the initial screening is not passed. There is no risk of flight collision between the two aircraft routes. The time window overlap ratio is the ratio between the time difference between the time windows of the two aircraft and the total length of the time windows of the two aircraft. The preset time threshold can be adaptively adjusted according to the aircraft type, airspace congestion, and mission urgency.

[0009] Optionally, based on the relative flight speeds of different aircraft at a given moment, the distance between BeiDou grid codes, and the overlap ratio of time windows, the collision risk probability of different aircraft at a given moment is determined and output, specifically including: A risk assessment model is established based on the overlap ratio of time windows, relative flight speed, and spatial distance between BeiDou grid codes. Obtain the overlap ratio of time windows between any two aircraft; Obtain the set flight speed between any two aircraft at a certain moment, calculate the relative flight speed between the two aircraft at that moment; determine the standard value of the relative flight speed between the two aircraft at that moment based on the relative flight speed between the two aircraft at that moment and the minimum and maximum values ​​of the relative flight speed between the two aircraft over the entire journey. Obtain the spatial distance between the BeiDou grid codes corresponding to the locations of any two aircraft at that moment; determine the standardized value of the spatial distance between the BeiDou grid codes corresponding to the locations of any two aircraft at that moment based on the actual spatial distance between the BeiDou grid codes corresponding to the locations of any two aircraft at that moment and the dynamic safe distance threshold; Input the overlap ratio of the time windows of any two aircraft at a given moment, the standard value of their relative flight speed, and the standardized value of the spatial distance between the BeiDou grid codes into the risk assessment model, and output the probability of collision between the two aircraft at a certain moment.

[0010] Furthermore, the risk assessment model is as follows: , Where R is the probability of a collision between the two aircraft at a certain moment; The overlap ratio of time windows between any two aircraft; Basic weighting coefficients; This is a time overlap index. The risk weighting coefficient is amplified to reflect the speed. The growth index is based on the speed dimension; Distance sensitivity risk coefficient; This is a risk parameter related to the distance to the inflection point; Risk curve composite index; The standardized value of the spatial distance between the two spacecraft at that moment, corresponding to the BeiDou grid codes. This represents the standard value of the relative flight speed of the two aircraft at that moment.

[0011] Optionally, based on the actual spatial distance between the corresponding BeiDou grid codes of any two aircraft at that moment and the dynamic safety distance threshold, the standardized value of the spatial distance between the corresponding BeiDou grid codes of the two aircraft at that moment is determined as follows: ,in, This represents the actual spatial distance between the BeiDou grid codes corresponding to the locations of any two spacecraft at that moment. The dynamic safety distance threshold is determined by the flight altitude, flight speed, and airspace density.

[0012] Optionally, based on the relative flight speed of any two aircraft at that moment and the minimum and maximum relative flight speeds of any two aircraft over the entire journey, the standard value of the relative flight speed of the two aircraft at that moment is determined as follows: ,in, Let be the relative flight speed of any two aircraft at that moment; is the dynamic correction factor for the relative flight speed of any two aircraft at that moment; Let be the minimum relative speed between any two aircraft over the entire flight path. It represents the maximum relative speed between any two aircraft over the entire flight path.

[0013] Optionally, it also includes: When the probability of collision between any two aircraft at a certain moment exceeds a preset safety threshold, extract the BeiDou grid code of the possible collision and the time of the collision. Obtain information on the priority influencing factors of the two aircraft, and determine the priority information of the two aircraft based on the priority influencing factors information and the preset priority strategy; For low-priority aircraft, a pause command is generated to stop them in the current or nearest safe grid before the expected collision time window arrives. After the high-priority aircraft passes safely, their flight path is replanned and resumed. For aircraft of the same priority, a cooperative avoidance mechanism is activated, and an avoidance path is generated based on the BeiDou grid coding.

[0014] Furthermore, the priority influencing factors include flight mission type, mission urgency, aircraft endurance, flight altitude, aircraft type, mission execution phase, and user authorization level.

[0015] This invention also proposes a flight path collision risk prediction system, comprising: The acquisition module acquires flight information of different aircraft, including: takeoff time, set flight speed, current flight speed, current location, preset flight path, and flight duration. The module establishes a dynamic trajectory model to predict the aircraft's position in the future time period based on the aircraft's takeoff time, set flight speed, current flight speed, current location, and preset flight path, and converts the aircraft's position in the future time period into BeiDou grid coding. The preliminary screening module constructs time windows on the timeline based on the aircraft's takeoff time and flight duration, and performs preliminary screening for aircraft flight path collisions based on whether the time windows of different aircraft overlap. The calculation module calculates the position of different aircraft at a certain moment after initial screening, obtains the BeiDou grid code corresponding to the coordinates of the aircraft's position at a certain moment, and calculates the spatial distance between the BeiDou grid codes corresponding to the positions of different aircraft at a certain moment. The determination and output module determines and outputs the collision risk probability of different aircraft at a certain moment based on the relative flight speed of different aircraft at a certain moment, the distance between Beidou grid codes, and the overlap ratio of time windows.

[0016] The technical solution adopted in this invention has the following technical effects: 1. This invention performs preliminary screening for collisions of different aircraft routes based on whether their time windows overlap; further collision risk probability calculations are then performed on the different aircraft that pass the preliminary screening, reducing the number of routes that need to be calculated and improving the computational efficiency of collision risk assessment; moreover, in the process of further collision risk probability calculation, the relative flight speed of different aircraft, the distance between BeiDou grid codes, and the overlap ratio of time windows are comprehensively considered to determine and output the collision risk probability of different aircraft at a certain moment, thereby improving the computational efficiency of collision risk assessment.

[0017] 2. In the preliminary screening process of the technical solution of this invention, it can be determined whether the time windows of any two aircraft overlap. If they overlap, the preliminary screening is passed. If they do not overlap, it is determined whether the time difference between the time windows of any two aircraft is less than a preset time threshold. If it is less than the preset time threshold, the preliminary screening is passed. If it is not less than the preset time threshold, the preliminary screening is not passed. There is no risk of flight collision between the flight paths of the two aircraft. The impact of different time window overlaps of different aircraft on the collision risk can be comprehensively considered. Moreover, the preset time threshold can be adaptively adjusted according to the aircraft type, airspace congestion, and mission urgency, which improves the adaptability of flight path collision risk assessment and prediction.

[0018] 3. In the technical solution of this invention, the overlap ratio of the time window corresponding to any two aircraft at a certain moment, the standard value of their relative flight speed, and the standardized value of the spatial distance between the Beidou grid codes are input into the risk assessment model, and the collision risk probability of the two aircraft at a certain moment is output. Instead of simply inputting the relative flight speed or spatial distance of the aircraft at that moment directly into the risk assessment model, these parameters are standardized. The risk assessment result includes multi-dimensional information such as collision probability, time point, and spatial location, which provides comprehensive decision support for aircraft route planning and safety management and improves the calculation efficiency of collision risk assessment.

[0019] 4. In the technical solution of this invention, when the probability of collision between any two aircraft at a certain moment exceeds a preset safety threshold, the BeiDou grid code of the possible collision and the time of the collision are extracted; the priority influencing factors of the two aircraft are obtained; the priority information of the two aircraft is determined according to the priority influencing factors and the preset priority strategy; different avoidance strategies are determined according to the priority of the aircraft, which has stronger adaptability and decision rationality, and effectively improves the reliability of air traffic management.

[0020] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 This is a flowchart illustrating the method of Embodiment 1 in the present invention; Figure 2 This is another flowchart illustrating the method of Embodiment 1 in the present invention; Figure 3 This is a schematic diagram illustrating the generation of the L-shaped obstacle avoidance path in the method of Embodiment 1 of the present invention; Figure 4 This is a schematic diagram illustrating the generation of the oblique avoidance path in the method of Embodiment 1 of the present invention; Figure 5 This is a schematic diagram of the system structure in Embodiment 2 of the present invention. Detailed Implementation

[0023] To clearly illustrate the technical features of this solution, the invention will be described in detail below through specific embodiments and in conjunction with the accompanying drawings. The following disclosure provides many different embodiments or examples for implementing different structures of the invention. To simplify the disclosure of the invention, components and arrangements of specific examples are described below. Furthermore, reference numerals and / or letters may be repeated in different examples. This repetition is for simplification and clarity and does not in itself indicate a relationship between the various embodiments and / or arrangements discussed. It should be noted that the components illustrated in the drawings are not necessarily drawn to scale. Descriptions of well-known components, processing techniques, and processes are omitted in this invention to avoid unnecessarily limiting the invention.

[0024] Example 1 like Figure 1 As shown, the present invention provides a method for predicting flight path collision risk, comprising: S1, acquire flight information of different aircraft, including: takeoff time, set flight speed, current flight speed, current location, preset flight path, and flight duration; S2, based on the aircraft's takeoff time, set flight speed, current flight speed, current location, and preset flight path, establishes a dynamic trajectory model to predict the aircraft's position in the future time period, and converts the aircraft's position in the future time period into BeiDou grid coding; S3, based on the take-off time and flight duration of the aircraft, constructs a time window on the time axis, and performs preliminary screening for collisions of aircraft routes based on whether the time windows of different aircraft overlap. S4. Calculate the position of different aircraft at a certain moment after the initial screening, obtain the BeiDou grid code corresponding to the coordinates of the aircraft's position at a certain moment, and calculate the spatial distance between the BeiDou grid codes corresponding to the positions of different aircraft at a certain moment. S5 determines and outputs the collision risk probability of different aircraft at a certain moment based on the relative flight speed of different aircraft at a certain moment, the distance between Beidou grid codes, and the overlap ratio of time windows.

[0025] In step S1, flight information of different aircraft is acquired. The flight information includes: takeoff time (estimated takeoff time), takeoff position (estimated takeoff position), set flight speed, current flight speed (flight speed of the aircraft at a certain moment in the future time period), current position (position of the aircraft at a certain moment in the future time period), preset flight path, and flight duration.

[0026] In step S2, based on the aircraft's takeoff time, set flight speed, current flight speed, current location, and preset flight path, a dynamic trajectory model is established to predict the aircraft's position in the future time period, and the aircraft's position in the future time period is converted into BeiDou grid coding. The dynamic trajectory model can be an existing aircraft dynamic trajectory model, i.e., a dynamic trajectory model obtained by training historical data through a neural network; this will not be elaborated upon here.

[0027] Latitude and Longitude Conversion: First, this invention employs a high-precision coordinate transformation algorithm to convert the latitude and longitude coordinates of the aircraft's takeoff point into BeiDou grid code. BeiDou grid code is a spatial position coding method based on the BeiDou satellite navigation system. It can map any location on the Earth's surface to a unique grid code, thereby improving the accuracy and speed of position identification.

[0028] In its implementation, the system first calculates the space coordinates of the aircraft in different time segments, starting from the takeoff time and combining flight speed and flight path. Then, based on the BeiDou system's geographic grid coding standard (e.g., GB / T 39409-2020), the continuous spatial coordinates are mapped to the corresponding BeiDou grid codes, thereby constructing a gridded flight path sequence of the aircraft in the future spatiotemporal dimension. Compared with existing technologies, this solution not only introduces a time dimension for dynamic modeling but also integrates the BeiDou grid coding system to discretize the flight trajectory, supporting multi-resolution grid precision control. Furthermore, it can dynamically optimize the prediction results by periodically updating flight status information (such as wind speed correction and heading adjustment), improving the real-time performance, adaptability, and computational efficiency of the prediction, and providing an efficient and structured data foundation for subsequent collision risk assessment.

[0029] In step S3, a time window is constructed on the time axis based on the aircraft's takeoff time and flight duration. Preliminary screening for aircraft flight path collisions is performed based on whether the time windows of different aircraft overlap. Specifically, this includes: Using the takeoff time of the aircraft as the starting point of the time axis, a time window is established on the time axis for the duration of the aircraft's flight. It is determined whether the time windows of any two aircraft overlap. If they overlap, they are initially screened and passed. The overlap ratio of the time windows is the ratio between the overlap duration and the total length of the time windows of the two aircraft.

[0030] Specifically, for example, one aircraft takes off at 9:00 AM with a flight duration of 2 hours, and its time window is 9:00 AM to 11:00 AM. Another aircraft takes off at 10:00 AM with a flight duration of 2 hours, and its time window is 10:00 AM to 12:00 PM. In this case, the time windows of the two aircraft overlap, and the initial screening is passed, pending further screening and calculation. Simultaneously, the time window overlap ratio is the ratio between the overlapping duration and the total length of the time windows for both aircraft (two flight paths), i.e., the time window overlap ratio. = =1 / 3.

[0031] The preliminary time-based screening mechanism in this invention is based on the specific takeoff time of the aircraft to initially screen flight routes to determine whether they might intersect with other routes in time and space, thus entering the subsequent collision risk assessment calculation process. Specifically, it works as follows: First, the estimated takeoff time and flight duration of each route are obtained to construct its "activity window" on the timeline; then, by comparing whether the time windows of different routes overlap, it is determined whether they should be included in the same assessment batch. If two routes intersect in time (two time periods overlap), it is considered that there is a possibility of them meeting in space, thus requiring further calculation and exclusion.

[0032] Compared with existing technologies, this solution has the following advantages in time-based filtering: First, it uses takeoff time as the core filtering factor, rather than relying solely on time series matching of trajectory prediction, which improves the accuracy of filtering (considering takeoff time is more accurate than just looking at the time series of trajectory prediction, since takeoff time is certain); Second, this mechanism not only reduces computational load, but also forms a tight coupling with subsequent spatial grid coding distance assessment, constituting an efficient spatiotemporal collaborative filtering framework, which significantly improves overall assessment efficiency and real-time response capability.

[0033] Furthermore, in step S3, the preliminary screening for aircraft flight path collisions based on the time windows constructed on the time axis according to the takeoff time and flight duration of the aircraft, and the existence of overlapping time windows for different aircraft, also includes: If there is no overlap, determine whether the time difference between the time windows of any two aircraft is less than a preset time threshold. If it is less, the initial screening is passed; if it is not less, the initial screening is not passed. There is no risk of flight collision between the two aircraft routes. The time window overlap ratio is the ratio between the time difference between the time windows of the two aircraft and the total length of the time windows of the two aircraft. The preset time threshold can be adaptively adjusted according to the aircraft type, airspace congestion, and mission urgency.

[0034] The initial time-based screening mechanism is based on the aircraft's specific takeoff time and a preset time threshold to preliminarily screen flight routes to determine whether they are likely to intersect with other routes in time and space, thus entering the subsequent collision risk assessment process. Specifically, it works as follows: First, the estimated takeoff time and flight duration of each route are obtained to construct its "active window" on the timeline; then, by comparing whether the time windows of different routes overlap, and combining this with a preset time threshold (such as the maximum allowable time difference Δt), it is determined whether to include them in the same assessment batch. If two routes do not intersect in time (directly determining whether the two time periods overlap) or the time difference between the two routes exceeds the preset time threshold, the probability of them meeting in space is considered extremely low, thus they are excluded in advance to avoid invalid calculations.

[0035] Specifically, for example, one aircraft takes off at 9:00 AM and has a flight duration of 2 hours, with a time window of 9:00 AM to 11:00 AM. Another aircraft takes off at 11:10 AM and has a flight duration of 2 hours, with a time window of 11:10 AM to 12:10 PM. In this case, the time windows of the two aircraft do not overlap. The system checks if the time difference (10 minutes) between the two aircraft's time windows is less than a preset time threshold (e.g., 30 minutes). If it is less, the initial screening passes, and further screening calculations are pending. If it is not less, the initial screening fails, and there is no risk of flight collision between the two aircraft's routes, pending further screening calculations. Simultaneously, the time window overlap ratio is the ratio between the time difference between the two aircraft's time windows and the total length of the time windows for both aircraft (two routes), i.e., the time window overlap ratio. = =1 / 19.

[0036] The modulation method in which the preset time threshold can be adaptively adjusted according to the aircraft type, airspace congestion, and mission urgency can be: , Where T is a preset time threshold. Based on a preset time frame, the threshold aircraft type adjustment parameters are used. The value is determined based on the performance parameters and operational characteristics of different types of aircraft. The higher the safety requirements of the aircraft, the higher this value, and the higher the final calculated T. (Airspace congestion adjustment coefficient) When the airspace is at a high congestion level, =0.6, the time threshold is lowered, accelerating route selection. Task urgency adjustment coefficient. For aircraft performing missions that do not prioritize practical effectiveness, This increases the time threshold and enhances the security of the screening process.

[0037] The initial time screening mechanism also introduces a configurable time threshold mechanism, which can be flexibly adjusted according to the aircraft type, airspace busyness, or mission urgency to enhance the system's adaptability. For example, when the airspace is in busy mode, the time threshold can be lowered to improve efficiency, and when the mission is not urgent, the time threshold can be raised to ensure higher safety.

[0038] Specifically, step S4 includes: S41, a risk assessment model is established based on the overlap ratio of time windows, relative flight speed, and spatial distance between BeiDou grid codes; In step S41, the risk assessment model is specifically as follows: , Where R is the probability of a collision between the two aircraft at a certain moment; The overlap ratio of time windows between any two aircraft; The basic weighting coefficient is (0.5-1.5). The time overlap index (1.2-2.0, controlling the degree of non-linearity in the time dimension). Increase the risk weighting coefficient for speed (0.5-2.0, to strengthen the risk weighting for high-speed scenarios); The growth index for the speed dimension is 1.5-3.0, controlling for the non-linear growth of the speed dimension. Distance sensitivity risk coefficient (2.5-5.0 controls the intensity of the impact of distance changes on risk); The distance inflection point risk parameter is 0.3-0.7, which controls the inflection point location of risk as a function of distance. Risk Curve Composite Index (1.0-2.0, adjusting for the steepness of the overall risk curve). The standardized value of the spatial distance between the two spacecraft at that moment, corresponding to the BeiDou grid codes. This represents the standard value of the relative flight speed of the two aircraft at that moment.

[0039] S42, obtain the overlap ratio of time windows between any two aircraft; The specific acquisition process is shown in step S3, where the time window overlap ratio is calculated and determined. S43, obtain the set flight speed between any two aircraft at a certain moment, calculate the relative flight speed between any two aircraft at that moment; determine the standard value of the relative flight speed between the two aircraft at that moment based on the relative flight speed between any two aircraft at that moment and the minimum and maximum values ​​of the relative flight speed between any two aircraft over the entire journey. In step S43, specifically: ,in, Let be the relative flight speed of any two aircraft at that moment; is the dynamic correction factor for the relative flight speed of any two aircraft at that moment; Let be the minimum relative speed between any two aircraft over the entire flight path. It represents the maximum relative speed between any two aircraft over the entire flight path.

[0040] Where 11.11 is m / s, corresponding to 40 km / h, 40 km / h is the relative flight speed threshold of the aircraft, and 0.2 is the set weight. Considering that the higher the relative speed of the aircraft, the greater the possibility of collision and the more serious the consequences, weighting is applied to high-speed approach scenarios.

[0041] S44, obtain the spatial distance between the BeiDou grid codes corresponding to the locations of any two aircraft at that time; determine the standardized value of the spatial distance between the BeiDou grid codes corresponding to the locations of any two aircraft at that time based on the actual spatial distance between the BeiDou grid codes corresponding to the locations of any two aircraft at that time and the dynamic safe distance threshold. In step S44, specifically: ,in, This represents the actual spatial distance between the BeiDou grid codes corresponding to the locations of any two spacecraft at that moment. This is the dynamic safety distance threshold.

[0042] The actual spatial distance between BeiDou grid codes is calculated based on the BeiDou grid codes corresponding to the positions of the two flight paths in the same time segment (calculating the BeiDou grid codes where the aircraft is located every 1 second and calculating the distance between the two aircraft). After converting them into spatial coordinates, the Euclidean distance or Manhattan distance is calculated. The distance calculation formula is the existing calculation method, which will not be elaborated here.

[0043] S45 inputs the overlap ratio of the time windows of any two aircraft at a given moment, the standard value of their relative flight speed, and the standardized value of the spatial distance between the BeiDou grid codes into the risk assessment model, and outputs the probability of collision between the two aircraft at a certain moment.

[0044] This embodiment quantifies the spatial proximity of two objects by using the spatial distance between them via BeiDou grid coding. Unlike existing technologies that typically calculate the physical distance between trajectories directly based on latitude and longitude coordinates, this scheme uses BeiDou grid coding, a standardized spatial discrete expression, for distance calculation. This not only improves data processing efficiency but also effectively reduces the impact of errors caused by differences in coordinate accuracy. Furthermore, this method sets a dynamic safety distance threshold based on the airspace characteristics of the area where the aircraft is located. This threshold can be adaptively adjusted according to factors such as flight altitude, flight speed, and airspace density, further improving the accuracy and applicability of collision probability assessment. Through these methods, this invention achieves higher computational efficiency, stronger environmental adaptability, and superior risk identification capabilities in collision probability calculation, demonstrating significant advantages and technological advancements compared to existing technologies.

[0045] The adaptive adjustment method for the dynamic safety distance threshold is as follows: , in, The dynamic safety distance threshold is defined by flight altitude h (meters), flight speed v (meters per second), and airspace density ρ (flights per square kilometer). An altitude influence coefficient is introduced. Speed ​​influence coefficient Spatial density influence coefficient (These coefficients can be flexibly weighted according to actual conditions), and the basic safety distance. (Initial safe distance value set according to aviation safety regulations, unit: meters).

[0046] The flight path collision risk assessment method of this invention constructs a dynamic and quantifiable risk assessment model based on a comprehensive consideration of multiple dimensions such as the aircraft's time overlap, grid coding distance, and flight speed. Finally, by fusing data from the above three dimensions, a nonlinear weighted algorithm is used to generate a collision risk index R, and multiple threshold intervals are set to correspond to different levels of risk warnings. The output includes a quantified value of the collision probability, the specific time and spatial location where a collision may occur, and other assessment results.

[0047] Based on the calculation results of the risk index R, three risk levels are defined: Risk level = , Compared with existing technologies, this solution differs significantly in its implementation: First, it not only focuses on single-dimensional distance or time factors but also organically combines temporal overlap, spatial distance, and flight status to form a more comprehensive risk assessment model. Second, it adopts BeiDou grid coding, a structured spatial representation method, making spatial distance calculation more efficient and stable, and supporting multi-resolution analysis. Third, it introduces flight speed as a dynamic weighting factor, enhancing the model's adaptability and sensitivity to different flight situations. Fourth, the output not only provides the collision probability but also specifies the exact time and spatial grid location of the collision, providing a more granular decision-making basis for subsequent escape strategies. These designs significantly improve the accuracy, real-time performance, and practicality of risk assessment compared to existing technologies.

[0048] like Figure 2 As shown, this embodiment also provides a method for predicting flight path collision risk, which further includes: S6. When the probability of collision between any two aircraft at a certain moment exceeds a preset safety threshold (e.g., 0.6, or 0.3), extract the BeiDou grid code of the possible collision and the time of the collision. S7, obtain priority influencing factor information for the two aircraft, and determine the priority information of the two aircraft based on the priority influencing factor information and the preset priority strategy; Priority influencing factors include flight mission type, mission urgency, aircraft endurance, flight altitude, aircraft type, mission execution phase, and user authorization level. The dynamic priority allocation mechanism in this invention comprehensively considers the multi-dimensional mission attributes of the aircraft, achieving a more reasonable and comprehensive priority determination through a hierarchical rule system, avoiding the one-sidedness of decision-making caused by relying solely on simple comparisons of a single attribute. Specific rules are as follows: First, flight mission type is used as the top-level priority (first-level priority influencing factor) for classification, dividing them into fixed-route missions (such as logistics transportation, regular inspections, and other missions with long-term planned paths) and temporary flight missions (such as surveying, inspection, emergency response, and other non-fixed-route missions). Among them, fixed-route missions enjoy higher basic right-of-way in conflict scenarios due to their strong planning and stable paths.

[0049] Secondly, when dealing with similar tasks or when further detailed assessment is required, urgency is introduced as a second-level evaluation factor (the first-level priority factor). For example, for high-priority urgent tasks such as medical rescue, disaster monitoring, and emergency relief, corresponding identifiers can be set in the system to automatically elevate their priority, breaking through the conventional task ranking.

[0050] Third, when mission types and urgency levels are similar, aircraft endurance is introduced as a secondary decision-making factor (third-level priority factor). Aircraft with shorter endurance are more significantly constrained by energy and should be given priority under the same conditions to reduce the risk of mission interruption due to waiting. The priority factors are considered in descending order: first-level, second-level, third-level, and fourth-level priority factors. Lower-level factors are only considered when the earlier-priority factors are the same.

[0051] In addition, the following optional attribute factors (fourth-level priority influencing factors) can be added to enhance the adaptability and flexibility of right-of-way determination: Flight altitude level: High-altitude aircraft typically have higher navigation rights; Aircraft type: Manned aircraft should be given priority over unmanned aircraft under certain airspace management strategies; Mission execution phase: Aircraft in the return or landing phase should receive higher priority; User authorization level: Differentiated access permissions are set based on the operator's qualifications or authorization level.

[0052] To achieve the aforementioned multi-attribute collaborative judgment, this solution employs a weighted rule engine combined with a priority sorting table. Different weights are assigned to each attribute, and the order in which rules apply is defined. This ensures that priority determination is both logically structured and flexible enough to handle various flight conflict scenarios in complex airspace environments. Compared to the single-dimensional comparison methods commonly used in existing technologies, this approach achieves millisecond-level right-of-way decisions through task attribute hierarchies, ensuring the continuity of critical tasks. It exhibits stronger adaptability and decision-making rationality, effectively improving the intelligence level of air traffic management.

[0053] S8 generates a pause command for low-priority aircraft, causing them to stop in the current or nearest safe grid before the expected collision time window arrives. After the high-priority aircraft passes safely, their flight path is replanned and resumed. For aircraft of the same priority, a cooperative avoidance mechanism is activated, and an avoidance path is generated based on the BeiDou grid coding.

[0054] When a collision risk assessment indicates a potential conflict, this invention employs different avoidance strategies based on the aircraft's priority. For low-priority aircraft, the system generates a pause command, causing them to stop in the current or nearest safe grid before the expected collision time window arrives. After the high-priority aircraft passes safely, their flight paths are replanned and resumed. For aircraft of the same priority, a cooperative avoidance mechanism is activated, generating L-shaped or oblique avoidance paths based on BeiDou grid coding.

[0055] Specifically, such as Figures 3-4 As shown, the L-shaped avoidance path is generated as follows: based on the grid code of the aircraft's current position, lateral or longitudinal extension path points that meet the minimum turning radius and flight maneuverability are searched in its adjacent grids to form a "right-angle" turning structure, so that the aircraft first deviates from the original route in one direction and then returns to the target route in the vertical direction, thereby bypassing the conflict area; the oblique avoidance path is achieved by inserting one or more intermediate grid nodes with offset angles between the current position and the target position. These nodes start from the current grid and, under the premise of meeting the aircraft's maximum climb / descent angle, minimum safe altitude and airspace restrictions, select adjacent oblique grids that maintain a sufficient grid code distance from the conflict route to form a smooth and short-term effective bypass path.

[0056] The above-mentioned avoidance path generation makes full use of the structured characteristics of Beidou grid coding. It can quickly locate feasible path points through predefined grid adjacency relationships, avoiding the complex three-dimensional spatial path search process in traditional methods, improving path generation efficiency and real-time response capability, while ensuring flight safety and mission continuity. Temporary mission mandatory control: For temporary flight missions that have not been declared in advance, the system will forcibly suspend them before they reach the collision grid after a collision warning is triggered, and a new flight permit must be applied for after the conflict is resolved.

[0057] Flight recovery verification: Before a paused aircraft can take off again, steps S1-S5 must be repeated based on the updated spatiotemporal state (including changes in the positions of other aircraft) to predict and verify the risk of secondary collisions using dynamic grid coding. A risk reassessment mechanism for restarting flight after a pause is implemented to avoid cascading conflicts; grid coding prediction and mandatory control are used to address safety hazards arising from unplanned flight missions.

[0058] The present invention will be described in detail below with reference to specific embodiments.

[0059] Example 1: A certain UAV takes off from a location with latitude and longitude of (116.391275, 39.90765) at 10:00 AM on February 7, 2025, with a flight speed of 100 km / h. According to the method of this invention, the latitude and longitude of the takeoff point are converted into BeiDou grid codes, and the BeiDou grid code position of the UAV is predicted for each time period. Through time filtering, another UAV is found to have a takeoff time of 10:05 AM on February 7, 2025, with a flight speed of 120 km / h, indicating an overlap in takeoff times. The grid code distance between the two UAVs during flight is calculated to assess the collision risk. Calculations show that there is a certain risk of collision between the two UAVs during flight.

[0060] Example 2: Drone A (on a flight route) and Drone B (on a temporary logistics mission) are predicted to overlap in time and space at grid code xxxx01. The system determines that the flight route mission has higher priority and sends a pause command to Drone B, instructing it to remain at the safe grid xxxx00 at 10:15. After Drone A passes through, Drone B reapplies for flight at 10:18. The system approves the resumption of flight after verifying that there is no collision risk based on the updated grid code distribution.

[0061] This invention can be widely applied to flight path planning and safety management of drones, aircraft, and other flying vehicles, improving flight safety and reducing collision risks. Simultaneously, this invention helps optimize computing resources and enhance the overall performance of flight path management systems. It has significant practical implications and market value for promoting the in-depth application of the BeiDou Navigation Satellite System. This invention can be extended to Urban Air Traffic Management (UAM) systems, supporting the safe operation of large-scale drone logistics networks and manned aircraft in mixed airspace.

[0062] This invention performs preliminary screening for aircraft flight path collisions based on whether the time windows of different aircraft overlap. Further collision risk probability calculations are then performed on the different aircraft that pass the preliminary screening, reducing the number of flight paths that need to be calculated and improving the computational efficiency of collision risk assessment. Moreover, in the process of further calculating the collision risk probability, the relative flight speed of different aircraft, the distance between BeiDou grid codes, and the overlap ratio of time windows are comprehensively considered to determine and output the collision risk probability of different aircraft at a certain moment, further improving the computational efficiency of collision risk assessment.

[0063] In the initial screening process of the technical solution of this invention, it can be determined whether the time windows of any two aircraft overlap. If they overlap, the initial screening is passed. If they do not overlap, it is determined whether the time difference between the time windows of any two aircraft is less than a preset time threshold. If it is less than the threshold, the initial screening is passed. If it is not less than the threshold, the initial screening is not passed, and there is no risk of flight collision between the two aircraft routes. The impact of different overlapping time windows of different aircraft on the collision risk can be comprehensively considered. Moreover, the preset time threshold can be adaptively adjusted according to the aircraft type, airspace congestion, and mission urgency, which improves the adaptability of route collision risk assessment and prediction.

[0064] In this invention, the overlapping ratio of the time windows of any two aircraft at a given moment, the standard value of their relative flight speeds, and the standardized value of the spatial distance between their BeiDou grid codes are input into the risk assessment model. The model outputs the collision risk probability of the two aircraft at a given moment. Instead of simply inputting the relative flight speeds or spatial distances of the aircraft at that moment directly into the risk assessment model, these parameters are standardized. The risk assessment results include multi-dimensional information such as collision probability, time point, and spatial location, providing comprehensive decision support for aircraft flight path planning and safety management, and improving the computational efficiency of collision risk assessment.

[0065] In this invention, when the probability of collision between any two aircraft at a certain moment exceeds a preset safety threshold, the BeiDou grid code of the possible collision and its time are extracted; priority influencing factors of the two aircraft are obtained; priority information of the two aircraft is determined based on priority influencing factors and preset priority strategies; different avoidance strategies are determined based on the priority of the aircraft, which has stronger adaptability and decision rationality, and effectively improves the reliability of air traffic management.

[0066] Example 2 like Figure 5 As shown, the present invention also provides a flight path collision risk prediction system, comprising: The acquisition module 101 acquires flight information of different aircraft, including: takeoff time, set flight speed, current flight speed, current location, preset flight path, and flight duration. Module 102 is established to create a dynamic trajectory model for predicting the position of the aircraft in the future time period based on the aircraft's takeoff time, set flight speed, current flight speed, current position, and preset flight path, and to convert the aircraft's position in the future time period into BeiDou grid code. The preliminary screening module 103 constructs a time window on the time axis based on the take-off time and flight duration of the aircraft, and performs preliminary screening for collisions of aircraft flight paths based on whether the time windows of different aircraft overlap. The calculation module 104 calculates the position of different aircraft at a certain moment after the initial screening, obtains the BeiDou grid code corresponding to the coordinates of the aircraft's position at a certain moment, and calculates the spatial distance between the BeiDou grid codes corresponding to the positions of different aircraft at a certain moment. The determination and output module 105 determines and outputs the collision risk probability of different aircraft at a certain moment based on the relative flight speed of different aircraft at a certain moment, the distance between Beidou grid codes, and the overlap ratio of time windows.

[0067] It should be noted that the implementation steps of the acquisition module 101, the establishment module 102, the preliminary screening module 103, the calculation module 104, and the determination and output module 105 in this embodiment are consistent with the steps in Embodiment 1. Similar to Embodiment 1, the system in this embodiment may also include the functional modules (extraction module 106, determination module 107, and generation module 108) corresponding to steps S6-S8. The implementation steps of the corresponding functional modules are consistent with the steps in Embodiment 1, and will not be described again in this embodiment.

[0068] This invention performs preliminary screening for aircraft flight path collisions based on whether the time windows of different aircraft overlap. Further collision risk probability calculations are then performed on the different aircraft that pass the preliminary screening, reducing the number of flight paths that need to be calculated and improving the computational efficiency of collision risk assessment. Moreover, in the process of further calculating the collision risk probability, the relative flight speed of different aircraft, the distance between BeiDou grid codes, and the overlap ratio of time windows are comprehensively considered to determine and output the collision risk probability of different aircraft at a certain moment, further improving the computational efficiency of collision risk assessment.

[0069] In the initial screening process of the technical solution of this invention, it can be determined whether the time windows of any two aircraft overlap. If they overlap, the initial screening is passed. If they do not overlap, it is determined whether the time difference between the time windows of any two aircraft is less than a preset time threshold. If it is less than the threshold, the initial screening is passed. If it is not less than the threshold, the initial screening is not passed, and there is no risk of flight collision between the two aircraft routes. The impact of different overlapping time windows of different aircraft on the collision risk can be comprehensively considered. Moreover, the preset time threshold can be adaptively adjusted according to the aircraft type, airspace congestion, and mission urgency, which improves the adaptability of route collision risk assessment and prediction.

[0070] In this invention, the overlapping ratio of the time windows of any two aircraft at a given moment, the standard value of their relative flight speeds, and the standardized value of the spatial distance between their BeiDou grid codes are input into the risk assessment model. The model outputs the collision risk probability of the two aircraft at a given moment. Instead of simply inputting the relative flight speeds or spatial distances of the aircraft at that moment directly into the risk assessment model, these parameters are standardized. The risk assessment results include multi-dimensional information such as collision probability, time point, and spatial location, providing comprehensive decision support for aircraft flight path planning and safety management, and improving the computational efficiency of collision risk assessment.

[0071] In this invention, when the probability of collision between any two aircraft at a certain moment exceeds a preset safety threshold, the BeiDou grid code of the possible collision and its time are extracted; priority influencing factors of the two aircraft are obtained; priority information of the two aircraft is determined based on priority influencing factors and preset priority strategies; different avoidance strategies are determined based on the priority of the aircraft, which has stronger adaptability and decision rationality, and effectively improves the reliability of air traffic management.

[0072] While the specific embodiments of the present invention have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of the present invention are still within the scope of protection of the present invention.

Claims

1. A method for predicting flight path collision risk, characterized in that, include: The flight information of different aircraft is acquired, including: takeoff time, set flight speed, current flight speed, current location, preset flight path, and flight duration. Based on the aircraft's takeoff time, set flight speed, current flight speed, current location, and preset flight path, a dynamic trajectory model is established to predict the aircraft's position in the future time period, and the aircraft's position in the future time period is converted into BeiDou grid code. A time window is constructed on the time axis based on the takeoff time and flight duration of the aircraft. The collision of aircraft routes is initially screened based on whether the time windows of different aircraft overlap. Calculate the position of different aircraft at a certain moment after the initial screening, obtain the BeiDou grid code corresponding to the coordinates of the aircraft's position at a certain moment, and calculate the spatial distance between the BeiDou grid codes corresponding to the positions of different aircraft at a certain moment. Based on the relative flight speeds of different aircraft at a given moment, the distance between BeiDou grid codes, and the overlap ratio of time windows, the collision risk probability of different aircraft at a given moment is determined and output; specifically including: A risk assessment model is established based on the overlap ratio of time windows, relative flight speed, and spatial distance between BeiDou grid codes; the risk assessment model is specifically as follows: ， Where R is the probability of a collision between the two aircraft at a certain moment; The overlap ratio of time windows between any two aircraft; The basic weighting coefficient; This is a time overlap index. The risk weighting coefficient is amplified to reflect the speed. The growth index is based on the speed dimension; Distance sensitivity risk coefficient; This is a risk parameter related to the distance to the inflection point; Risk curve composite index; The standardized value of the spatial distance between the two spacecraft at that moment, corresponding to the BeiDou grid codes. The standard value of the relative flight speed of the two aircraft at that moment; Obtain the overlap ratio of time windows between any two aircraft; Obtain the set flight speed between any two aircraft at a certain moment, and calculate the relative flight speed between the two aircraft at that moment; based on the relative flight speed between the two aircraft at that moment and the minimum and maximum values ​​of the relative flight speed between the two aircraft over the entire journey, determine the standard value of the relative flight speed between the two aircraft at that moment; specifically: ,in, Let be the relative flight speed of any two aircraft at that moment; is the dynamic correction factor for the relative flight speed of any two aircraft at that moment; Let be the minimum relative speed between any two aircraft over the entire flight path. The maximum relative speed between any two aircraft over the entire flight path; Obtain the spatial distance between the corresponding BeiDou grid codes of any two aircraft at that moment; determine the standardized value of the spatial distance between the corresponding BeiDou grid codes of any two aircraft at that moment based on the actual spatial distance between them and the dynamic safe distance threshold; specifically: ,in, This represents the actual spatial distance between the BeiDou grid codes corresponding to the locations of any two spacecraft at that moment. This refers to the dynamic safety distance threshold; where the dynamic safety distance threshold is adaptively adjusted based on flight altitude, flight speed, and airspace density. Input the overlap ratio of the time windows of any two aircraft at a given moment, the standard value of their relative flight speed, and the standardized value of the spatial distance between the BeiDou grid codes into the risk assessment model, and output the probability of collision between the two aircraft at a certain moment.

2. The method for predicting flight path collision risk according to claim 1, characterized in that, A time window is constructed on the timeline based on the aircraft's takeoff time and flight duration. Preliminary screening for aircraft flight path collisions is performed based on whether the time windows of different aircraft overlap. Specifically, this includes: Using the takeoff time of the aircraft as the starting point of the time axis, a time window is established on the time axis for the duration of the aircraft's flight. It is determined whether the time windows of any two aircraft overlap. If they overlap, they are initially screened and passed. The overlap ratio of the time windows is the ratio between the overlap duration and the total length of the time windows of the two aircraft.

3. The method for predicting flight path collision risk according to claim 2, characterized in that, A time window is constructed on the timeline based on the aircraft's takeoff time and flight duration. Preliminary screening for aircraft flight path collisions is performed based on whether the time windows of different aircraft overlap. This also includes: If there is no overlap, determine whether the time difference between the time windows of any two aircraft is less than a preset time threshold. If it is less, the initial screening is passed; if it is not less, the initial screening is not passed. There is no risk of flight collision between the two aircraft routes. The time window overlap ratio is the ratio between the time difference between the time windows of the two aircraft and the total length of the time windows of the two aircraft. The preset time threshold is adaptively adjusted according to the aircraft type, airspace congestion, and mission urgency.

4. A method for predicting flight path collision risk according to any one of claims 1-3, characterized in that, it further... include: When the probability of collision between any two aircraft at a certain moment exceeds a preset safety threshold, extract the BeiDou grid code of the possible collision and the time of the collision. Obtain information on the priority influencing factors of the two aircraft, and determine the priority information of the two aircraft based on the priority influencing factors information and the preset priority strategy; For low-priority aircraft, a pause command is generated to stop them in the current or nearest safe grid before the expected collision time window arrives. After the high-priority aircraft passes safely, their flight path is replanned and resumed. For aircraft of the same priority, a cooperative avoidance mechanism is activated, and an avoidance path is generated based on the BeiDou grid coding.

5. The method for predicting flight path collision risk according to claim 4, characterized in that, Priority influencing factors include flight mission type, mission urgency, aircraft endurance, flight altitude, aircraft type, mission execution phase, and user authorization level.

6. A flight path collision risk prediction system, characterized in that, include: The acquisition module acquires flight information of different aircraft, including: takeoff time, set flight speed, current flight speed, current location, preset flight path, and flight duration. The module establishes a dynamic trajectory model to predict the aircraft's position in the future time period based on the aircraft's takeoff time, set flight speed, current flight speed, current location, and preset flight path, and converts the aircraft's position in the future time period into BeiDou grid coding. The preliminary screening module constructs time windows on the timeline based on the aircraft's takeoff time and flight duration, and performs preliminary screening for aircraft flight path collisions based on whether the time windows of different aircraft overlap. The calculation module calculates the position of different aircraft at a certain moment after initial screening, obtains the BeiDou grid code corresponding to the coordinates of the aircraft's position at a certain moment, and calculates the spatial distance between the BeiDou grid codes corresponding to the positions of different aircraft at a certain moment. The determination and output module determines and outputs the collision risk probability of different aircraft at a given moment based on their relative flight speeds, the distance between BeiDou grid codes, and the overlap ratio of time windows. Specifically, this includes: A risk assessment model is established based on the overlap ratio of time windows, relative flight speed, and spatial distance between BeiDou grid codes; the risk assessment model is specifically as follows: ， Where R is the probability of a collision between the two aircraft at a certain moment; The overlap ratio of time windows between any two aircraft; The basic weighting coefficient; This is a time overlap index. The risk weighting coefficient is amplified to reflect the speed. The growth index is based on the speed dimension; Distance sensitivity risk coefficient; This is a risk parameter related to the distance to the inflection point; Risk curve composite index; The standardized value of the spatial distance between the two spacecraft at that moment, corresponding to the BeiDou grid codes. The standard value of the relative flight speed of the two aircraft at that moment; Obtain the overlap ratio of time windows between any two aircraft; Obtain the set flight speed between any two aircraft at a certain moment, and calculate the relative flight speed between the two aircraft at that moment; based on the relative flight speed between the two aircraft at that moment and the minimum and maximum values ​​of the relative flight speed between the two aircraft over the entire journey, determine the standard value of the relative flight speed between the two aircraft at that moment; specifically: ,in, Let be the relative flight speed of any two aircraft at that moment; is the dynamic correction factor for the relative flight speed of any two aircraft at that moment; Let be the minimum relative speed between any two aircraft over the entire flight path. The maximum relative speed between any two aircraft over the entire flight path; Obtain the spatial distance between the corresponding BeiDou grid codes of any two aircraft at that moment; determine the standardized value of the spatial distance between the corresponding BeiDou grid codes of any two aircraft at that moment based on the actual spatial distance between them and the dynamic safe distance threshold; specifically: ,in, This represents the actual spatial distance between the BeiDou grid codes corresponding to the locations of any two spacecraft at that moment. This refers to the dynamic safety distance threshold; where the dynamic safety distance threshold is adaptively adjusted based on flight altitude, flight speed, and airspace density. Input the overlap ratio of the time windows of any two aircraft at a given moment, the standard value of their relative flight speed, and the standardized value of the spatial distance between the BeiDou grid codes into the risk assessment model, and output the probability of collision between the two aircraft at a certain moment.

Images