Airline conflict detection method

Abstract

The invention belongs to the technical field of aircraft task planning, and particularly relates to a route conflict detection method, which comprises the following steps of: 1, modeling an aircraft state, defining a flight path model of an aircraft, considering a three-dimensional space coordinate and a time dimension of the aircraft, and combining a motion state of the aircraft to establish a space-time grid model; 2, space-time conflict detection: based on a space-time grid model, comprehensively considering information such as the space position, the time window and the speed of the aircraft, and carrying out conflict detection; 3, realizing efficient real-time conflict detection in a multi-aircraft environment by adopting an improved ant colony algorithm; 4, after conflict detection is completed, the system outputs potential conflicts between the aircrafts according to a detection result, and a warning prompt is generated. According to the invention, by setting the unified time axis and three-dimensional space region detection model, whether the air route conflicts or not is automatically identified, the intelligence and safety of the task planning system are improved, and human judgment errors are reduced.

Description

Technical Field

[0001] This invention belongs to the field of aircraft mission planning technology, and specifically relates to a method for detecting flight path conflicts. Background Technology

[0002] Conflict detection is a crucial technology in aviation safety management, especially in high-density airspace or environments with multiple flights operating simultaneously. Traditional conflict detection methods largely rely on simple time- and space-based rules, identifying collision risks between aircraft through static and dynamic assessments. While effective in certain situations, these methods often have significant limitations when faced with dynamic trajectories of multiple aircraft, complex environments, and high real-time requirements, making them prone to false alarms, missed alarms, or slow response times.

[0003] With the improvement of computing power, conflict detection methods based on intelligent optimization algorithms are gradually being applied to aircraft route planning. Ant colony optimization, as a natural heuristic optimization algorithm, has achieved significant results in path planning and shortest path search problems. However, while ant colony optimization has traditionally been applied primarily to path optimization, there is still considerable room for improvement in its application to conflict detection between aircraft. Summary of the Invention

[0004] Purpose of the invention: This invention aims to provide a route conflict detection method based on an improved ant colony algorithm. By setting a unified time axis and a three-dimensional spatial region detection model, it can automatically identify whether a route conflict has occurred, improve the intelligence and security of the mission planning system, and reduce human judgment errors.

[0005] Technical Solution: To achieve the above objectives, the present invention proposes a method for detecting flight path conflicts, the method comprising the following steps: Step 1: Aircraft State Modeling Define the trajectory model of the aircraft, considering the three-dimensional spatial coordinates and time dimension of the aircraft, and establish a spatiotemporal grid model in combination with the motion state of the aircraft.

[0006] Step 2: Spatiotemporal Conflict Detection Based on the spatiotemporal grid model, collision detection is carried out by comprehensively considering information such as the space position, time window and speed of the aircraft, including at least three aspects of detection: spatial collision, vertical collision and temporal collision. Step 3: Improve Ant Colony Algorithm for Conflict Detection To improve the efficiency and accuracy of collision detection, this invention employs an improved ant colony algorithm to achieve efficient real-time collision detection in multi-aircraft environments; this algorithm is an improvement on the traditional ant colony algorithm. Step 4: Output of collision detection results After completing the conflict detection, the system outputs the potential conflicts between the aircraft based on the detection results and generates warning prompts.

[0007] Furthermore, in step 1, the state of each aircraft is represented as a quintuple:

[0008] in, The latitude and longitude of the aircraft. For height, For time, This refers to flight speed.

[0009] Furthermore, in step 2, the criteria for determining conflict include: Spatial conflict: When the horizontal distance between two aircraft is less than the set safe distance. When this occurs, it is considered a spatial conflict:

[0010] in, and Let i and j represent the position vectors of aircraft i and j at time t, respectively; Indicates the distance between aircraft; The set horizontal safety distance threshold.

[0011] Vertical conflict: When the vertical altitude difference between two aircraft is less than the set safe altitude difference. When this occurs, it is considered a vertical conflict:

[0012] in, and These represent the altitudes of aircraft i and j at time t, respectively. The set vertical safety height difference threshold.

[0013] Time conflict: If two aircraft fly to the same area within the same time period, it is considered a time conflict. The time period for determining the conflict is as follows:

[0014] in, This represents the time window in which aircraft i is located within a specific region; This represents the time window in which aircraft j is located in a specific region. This indicates an intersection operation on the time windows; The intersection of the two sets represents an empty set, and a non-empty intersection indicates a time conflict.

[0015] Furthermore, in step 3, the improved ant colony algorithm is an improvement on the traditional ant colony algorithm. The specific process is as follows: First, a dynamic heuristic function is established: This heuristic function is used to evaluate the distance between aircraft, flight time, and proximity to the conflict zone; its specific form is as follows:

[0016] in, It is the distance between aircraft i and j at time t. This refers to the overlap between the aircraft and the conflict zone. and The weights of the heuristic factors.

[0017] Establish a pheromone update mechanism: The pheromone update mechanism adjusts the pheromone concentration based on the conflict cost of the current spacecraft path, using the following formula:

[0018] Where ρ is the pheromone evaporation rate. It is the cost of the current path.

[0019] Design an elite ant strategy: This strategy helps ant colonies quickly focus on areas with less conflict by increasing the pheromone concentration on high-quality paths, thereby improving search efficiency; Establish path selection rules: Ants select paths based on the heuristic value and pheromone concentration of the current path, using the following formula:

[0020] Where N is the set of neighboring paths currently available to the aircraft. and These are the weights of the pheromone and the heuristic function, respectively.

[0021] Furthermore, in step 4, the specific output format includes: Conflicting aircraft pairs: Lists aircraft pairs that may clash; Conflict types: spatial conflict, vertical conflict, or temporal conflict; Conflict Segment: Displays the spatial segment and time window in which the conflict occurred.

[0022] Furthermore, step 4 provides solutions: suggestions for evasive actions that the aircraft may take, such as adjusting its course, changing its altitude, or adjusting its flight time.

[0023] Technical advantages: The detection method proposed in this invention has the following outstanding features: Improved real-time performance and accuracy: By introducing a spatiotemporal grid and an improved ant colony algorithm, it is possible to detect conflicts between aircraft more accurately and provide avoidance suggestions quickly.

[0024] Supports multi-aircraft collaborative operations: In high-density airspace with multiple aircraft, it can efficiently detect and avoid conflicts, ensuring the safe conduct of flight missions.

[0025] High computational performance: The improved ant colony algorithm enables fast real-time collision detection and feedback without adding too much computational burden.

[0026] It can detect multiple types of conflicts simultaneously, adapting to the needs of complex task planning; Provides automatic adjustment suggestions to reduce the burden on operators; It supports graphical interface display, improving task planning efficiency and security; It is easy to integrate into existing flight mission planning software. Attached Figure Description

[0027] Figure 1 This is a general block diagram of the conflict detection and path optimization system; Figure 2 A diagram illustrating the state of the aircraft; Figure 3 Here is a flowchart of the collision detection algorithm; Figure 4 This is a schematic diagram of path selection and pheromone update in the ant colony algorithm. Detailed Implementation

[0028] To more clearly illustrate the technical solutions of the embodiments of the present invention, the present invention will be described in detail below with reference to the accompanying drawings or specific implementation examples. It should be noted that some (but not all) of the disclosed examples are shown in the drawings. In fact, many different examples can be described, and these examples should not be construed as limited to the examples set forth herein. Rather, these examples are described to better demonstrate the positive effects of the present invention, and all aspects not detailed herein are considered to be well-known or conventional techniques in the art.

[0029] See appendix Figure 1 The purpose of this invention is to propose a new conflict detection method based on an improved ant colony algorithm, so as to improve the efficiency, accuracy and real-time performance of conflict detection in multi-aircraft systems and meet the needs of modern air traffic management.

[0030] This invention proposes a conflict detection and path optimization system for multi-aircraft mission scenarios. It boasts advantages such as clear structure, high processing efficiency, and strong adaptability, effectively identifying various conflict types and performing intelligent path optimization. The overall structure and implementation process of this invention are described in detail below with reference to the accompanying drawings.

[0031] like Figure 1 As shown, the system of this invention generally includes the following modules: a task input module, an aircraft state modeling module (corresponding to...). Figure 2), conflict detection module (corresponding) Figure 3 ), Path replanning module (corresponding) Figure 4 The system includes a task planning data module, a state modeling and conflict resolution process, and a final output module for conflict-free flight paths and task adjustment suggestions.

[0032] In specific implementation, the overall architecture of the conflict detection and path optimization system proposed in this invention is as follows: Figure 1 As shown. The system starts with the input of flight mission or path data and enters the aircraft state modeling module (…). Figure 2 ), establish key dynamic parameters; then proceed to the conflict detection module ( Figure 3 The system categorizes and identifies conflicts based on their different types; if a conflict is detected, the system will invoke the path replanning module. Figure 4 The system optimizes and adjusts the process using intelligent algorithms, ultimately outputting conflict-free paths and task adjustment suggestions to ensure safe and efficient task execution.

[0033] like Figure 2 As shown, during the mission initialization phase, the system establishes a complete aircraft state model based on the aircraft's operational plan, mission type, and current state. The modeled parameters include, but are not limited to, the aircraft's current position, speed, altitude, heading angle, remaining fuel, mission duration, and mission type. This state information serves as the core input, providing data support for subsequent conflict identification.

[0034] During the mission initialization phase, the system first performs state modeling for each aircraft. This modeling process includes: static parameter modeling: obtaining the basic attributes and mission requirements of the aircraft, including current position (latitude, longitude, and altitude), flight speed, heading angle, remaining fuel, mission type, mission duration, etc.

[0035] Flight path modeling: For a given flight path (usually provided in the form of waypoints), the system generates a spatiotemporally continuous sequence of trajectories using a path interpolation algorithm. This interpolation process includes: Flight segments are constructed based on waypoints and intermediate path points are inserted at time or distance intervals. Each interpolation point includes spatial location (latitude, longitude, and altitude), timestamp, and velocity vector; The interpolation process takes into account constraints on aircraft performance parameters (such as maximum turning radius and climb / descent rate); The interpolation accuracy can be dynamically set according to the collision detection accuracy requirements to support high-precision trajectory overlap determination.

[0036] The modeling results provide a detailed time-space dynamic path basis for conflict detection.

[0037] Subsequently, as Figure 3 As shown, the system enters the conflict detection process. The conflict detection module first parses the mission and spacecraft status data and then calls the conflict type determination submodule. This module quickly classifies the possible conflict types according to the conflict classification criteria, determining whether it belongs to spatial conflict, vertical conflict, or temporal conflict.

[0038] The collision detection algorithm used in this invention is as follows: Figure 3 As shown, the main steps include: Step 1: Task Data Input: Obtain the aircraft trajectory and state model; Step 2, Conflict Type Determination: Perform preliminary conflict type classification on the input data; Step 3: Various conflict detection modules: including spatial conflict detection, vertical height conflict detection, and temporal conflict detection; Step 4: Determine if a conflict exists: If a conflict exists, proceed to the path replanning module. Figure 4 ); Step 5: Output the results: Feed back the detection results and adjustment suggestions to the task management module.

[0039] This flowchart constitutes the core decision-making mechanism of this invention.

[0040] If a conflict is detected, the system automatically enters the path replanning phase. For example... Figure 4 As shown, the system employs a path optimization strategy based on the Ant Colony Optimization (ACO) algorithm, using biomimetic computing to adaptively adjust the flight path. The algorithm first initializes multiple sets of optional paths (simulating ants), and scores each path based on objective functions such as flight distance, path safety, and fuel consumption. Then, it globally updates the pheromones based on the evaluation results, guiding the path selection towards the optimal path. Through multiple iterations, the path gradually converges to an optimized result that satisfies the conflict avoidance requirements.

[0041] See appendix Figure 4 The diagram illustrates the mechanism by which this invention employs the Ant Colony Algorithm (ACO) for path replanning after a conflict is detected. This mainly includes: Multi-path initialization: Simulates an "ant" starting from the origin and trying different paths based on heuristic information; Route evaluation: The route is evaluated based on indicators such as route length, safety, and fuel consumption; Pheromon update: Release more pheromones on excellent paths to guide subsequent path selection toward the optimal; Multiple iterations: Through multiple rounds of search, the system eventually converges to a feasible solution for conflict avoidance.

[0042] This module and Figure 2 This forms a closed loop, serving as its conflict response subsystem.

[0043] Finally, the system integrates the conflict detection results with the optimized path, generates mission adjustment suggestions, and returns them to the user interface control module for subsequent flight mission rescheduling, path updates, or manual decision support.

[0044] Example 1, Step 1: Aircraft State Modeling First, a trajectory model for the aircraft is defined, considering its three-dimensional spatial coordinates and time dimension, and a spatiotemporal grid model is established in conjunction with its motion state. The state of each aircraft is represented as a quintuple:

[0045] in, The latitude and longitude of the aircraft. For height, For time, This refers to flight speed.

[0046] Step 2: Spatiotemporal Conflict Detection The collision detection method of this invention is based on a spatiotemporal grid model, comprehensively considering information such as the spacecraft's spatial position, time window, and velocity to perform collision detection. The collision determination criteria include: Spatial conflict: When the horizontal distance between two aircraft is less than the set safe distance. When this occurs, it is considered a spatial conflict:

[0047] in, and Let i and j represent the position vectors of aircraft i and j at time t, respectively; Indicates the distance between aircraft; The set horizontal safety distance threshold.

[0048] Vertical conflict: When the vertical altitude difference between two aircraft is less than the set safe altitude difference. When this occurs, it is considered a vertical conflict:

[0049] in, and These represent the altitudes of aircraft i and j at time t, respectively. The set vertical safety height difference threshold.

[0050] Time conflict: If two aircraft fly to the same area within the same time period, it is considered a time conflict. The time period for determining the conflict is as follows:

[0051] in, This represents the time window in which aircraft i is located within a specific region; This represents the time window in which aircraft j is located in a specific region. This indicates an intersection operation on the time windows; The intersection of the two sets represents an empty set, and a non-empty intersection indicates a time conflict.

[0052] Step 3: Improve Ant Colony Algorithm for Conflict Detection To improve the efficiency and accuracy of collision detection, this invention employs an improved ant colony algorithm to achieve efficient real-time collision detection in multi-aircraft environments. This algorithm is an improvement upon the traditional ant colony algorithm and mainly includes the following: Dynamic heuristic functions: Heuristic functions are used to evaluate the distance between aircraft, flight time, and proximity to the conflict zone. The specific form is:

[0053] in, It is the distance between aircraft i and j at time t. This refers to the overlap between the aircraft and the conflict zone. and The weights of the heuristic factors.

[0054] Pheromone Update Mechanism: The pheromone update mechanism adjusts the pheromone concentration based on the conflict cost of the current spacecraft path, using the following formula:

[0055] Where ρ is the pheromone evaporation rate. It is the cost of the current path.

[0056] Elite Ant Strategy: This strategy enhances the pheromone concentration on high-quality paths, helping ant colonies quickly focus on areas with less conflict, thereby improving search efficiency.

[0057] Path selection rules: Ants select paths based on the heuristic value and pheromone concentration of the current path, using the following formula:

[0058] Where N is the set of neighboring paths currently available to the aircraft. and These are the weights of the pheromone and the heuristic function, respectively.

[0059] Step 4: Output of collision detection results After completing the collision detection, the system outputs the potential collisions between the aircraft based on the detection results and generates a warning message. The specific output format includes: Conflicting aircraft pairs: List aircraft pairs that may clash.

[0060] Conflict types: spatial conflict, vertical conflict, or temporal conflict.

[0061] Conflict Segment: Displays the spatial segment and time window in which the conflict occurred.

[0062] Recommended solutions: Suggested evasive actions for the aircraft, such as adjusting course, changing altitude, or adjusting flight time.

[0063] This invention has good scalability and universal applicability. In terms of scalability, the system structure is modularly designed, and various conflict detection modules and optimization strategies can be deployed, replaced, or extended independently. For example, it supports the introduction of other intelligent optimization algorithms (such as genetic algorithms and particle swarm optimization algorithms) to improve path optimization capabilities. In terms of applicability, the system is not only suitable for manned aircraft mission planning, but can also be widely applied to various civil flight scenarios such as UAV swarms, emergency airspace scheduling, and low-altitude airspace management.

[0064] In summary, the conflict detection and path optimization system provided by this invention combines multi-source task data with intelligent optimization algorithms to construct a complete conflict prediction and avoidance mechanism. It has the advantages of flexible structure, accurate detection, and high efficiency, and has broad engineering application value and promotion prospects.

[0065] The above specific embodiments or examples are only used to explain the technical solutions of the present invention and are not intended to limit the present application. Parts not described in detail are considered to be conventional technical means or common knowledge in the field. It can be understood by those skilled in the art that, based on the design concept of the present application, the technical solutions described in the foregoing embodiments can be adapted or some or all of the technical features can be equivalently replaced. These modifications, equivalent replacements, and adaptive improvements do not depart from the technical essence of the present invention and should all be covered within the protection scope of the present application.

Claims

1. A method for detecting flight path conflicts, characterized in that, The method includes the following steps: Step 1: Aircraft state modeling. Define the aircraft's trajectory model, considering the aircraft's three-dimensional spatial coordinates and time dimension, and establish a spatiotemporal mesh model in combination with the aircraft's motion state; Step 2: Spatiotemporal conflict detection. Based on the spatiotemporal grid model, spatial conflict, vertical conflict, and temporal conflict detection are performed by comprehensively considering the spacecraft's spatial position, time window, and velocity information. Step 3: Improve ant colony algorithm for conflict detection. Use an improved ant colony algorithm to achieve real-time conflict detection in a multi-aircraft environment. Step 4: Output the conflict detection results. Based on the detection results, output the potential conflicts between the aircraft and generate warning prompts.

2. The method for detecting flight path conflicts as described in claim 1, characterized in that, In step 1, the state of each aircraft is represented by a quintuple: in, The latitude and longitude of the aircraft. For height, For time, This refers to flight speed.

3. The flight path conflict detection method as described in claim 1, characterized in that, In step 1, the flight path modeling includes: constructing flight segments based on waypoints and inserting intermediate path points at time or distance intervals. Each interpolation point includes spatial location, timestamp, and velocity vector. The interpolation process is constrained by the aircraft's maximum turning radius and climb / descent rate. The interpolation accuracy can be dynamically set according to the conflict detection accuracy requirements.

4. The flight path conflict detection method as described in claim 2, characterized in that, In step 2, the criteria for determining conflict include: Spatial conflict: When the horizontal distance between two aircraft is less than the set safe distance. When this occurs, it is considered a spatial conflict: in, and Let i and j represent the position vectors of aircraft i and j at time t, respectively; Indicates the distance between aircraft; The set horizontal safety distance threshold; Vertical conflict: When the vertical altitude difference between two aircraft is less than the set safe altitude difference. When this occurs, it is considered a vertical conflict: in, and These represent the altitudes of aircraft i and j at time t, respectively. The set vertical safety height difference threshold; Time conflict: If two aircraft fly to the same area within the same time period, it is considered a time conflict. The time period for determining the conflict is as follows: in, This represents the time window in which aircraft i is located within a specific region; This represents the time window in which aircraft j is located in a specific region. This indicates an intersection operation on the time windows; The intersection of the two sets represents an empty set, and a non-empty intersection indicates a time conflict.

5. The flight path conflict detection method as described in claim 4, characterized in that, In step 3, the improved ant colony algorithm is based on the traditional ant colony algorithm, and the specific process is as follows: First, a dynamic heuristic function is established: This heuristic function is used to evaluate the distance between aircraft, flight time, and proximity to the conflict zone; its specific form is as follows: in, It is the distance between aircraft i and j at time t. This refers to the overlap between the aircraft and the conflict zone. and The weights of the heuristic factors.

6. The method for detecting flight path conflicts as described in claim 5, characterized in that, In step 3, the improved ant colony algorithm also includes developing a pheromone update mechanism. Establish a pheromone update mechanism: The pheromone update mechanism adjusts the pheromone concentration based on the conflict cost of the current spacecraft path, using the following formula: Where ρ is the pheromone evaporation rate. It is the cost of the current path.

7. The method for detecting flight path conflicts as described in claim 6, characterized in that, In step 3, the improved ant colony algorithm also includes designing an elite ant strategy, selecting the ants with the lowest path conflict cost during the iteration process as elite ants, and increasing their pheromone release concentration.

8. The method for detecting flight path conflicts as described in claim 7, characterized in that, In step 3, the improved ant colony algorithm also includes formulating path selection rules, as follows: Where N is the set of neighboring paths currently available to the aircraft. and These are the weights of the pheromone and the heuristic function, respectively.

9. The method for detecting flight path conflicts as described in claim 1, characterized in that, In step 4, the output format includes the conflicting aircraft pair, conflict type, and conflict segment; where the conflict segment includes the spatial segment and time window in which the conflict occurs.

10. The route conflict detection method according to claim 9, characterized in that, Step 4 also includes outputting conflict avoidance suggestions, which include at least one or more of the following: adjusting the course, changing the flight altitude, and adjusting the flight time.

Images