Full-motion simulator TCAS simulation method and system based on dynamic decision and real-time interaction

Abstract

The invention relates to the technical field of dynamic decision making and real-time interaction, provides a full-motion simulator TCAS simulation method and system based on dynamic decision making and real-time interaction, and solves the problem of low accuracy of flight conflict dynamic prediction and avoidance decision making. The method comprises the following steps: acquiring position coordinates, movement speeds and direction angles of a plurality of flight targets in a three-dimensional airspace; discretizing the three-dimensional airspace into dynamically updated grid units based on the position coordinates, and calculating the risk potential energy value of each grid unit according to the movement speed and the direction angle; in the simulation process, according to the risk potential energy value, dynamically predicting a conflict occurrence probability value in a future set time period through a Monte Carlo algorithm, and generating an avoidance instruction set; after simulation is finished, according to the avoiding instruction set, a conflict report is generated in the real-time interaction display interface, and the conflict report comprises the number of conflicts, the avoiding success rate and the pilot response time. According to the invention, the accuracy of flight conflict dynamic prediction and avoidance decision in a high-density airspace is improved.

Description

Technical Field

[0001] The present application relates to the technical field of dynamic decision-making and real-time interaction, and in particular to a TCAS simulation method and system for a full-motion simulator based on dynamic decision-making and real-time interaction. Background Art

[0002] In the field of aviation safety, simulation technology for airborne collision avoidance systems must dynamically simulate complex airspace environments, including scenarios such as the real-time interaction of multiple flight targets and changing weather conditions, to provide a highly realistic training environment. This technology must support real-time response to pilot operations, dynamically generate conflict warnings and avoidance instructions, and be able to quantitatively evaluate training effectiveness, effectively improving pilots' emergency decision-making capabilities.

[0003] The current mainstream air collision avoidance simulation technology uses static logic simulation, generating collision avoidance commands based on pre-programmed conflict scenarios and fixed rules. This solution, based on preset flight trajectories and conflict conditions, triggers warning and avoidance commands according to established logic during the simulation, meeting basic training requirements.

[0004] Static logic simulation relies on pre-set scenarios and struggles to adapt to dynamic changes during flight, such as multi-aircraft coordination or unexpected weather disturbances. The generated collision avoidance commands lack flexibility and cannot be adjusted to real-time airspace conditions, resulting in insufficient fidelity in training scenarios. Furthermore, this solution's ability to simulate complex conflicts is limited, making it difficult to meet the requirements of high-precision training. Summary of the Invention

[0005] The present application provides a full-motion simulator TCAS simulation method and system based on dynamic decision-making and real-time interaction, which is used to solve the problem of low accuracy of flight conflict dynamic prediction and avoidance decision-making in high-density airspace in the existing technology.

[0006] In a first aspect, the present application provides a TCAS simulation method for a full-flight simulator based on dynamic decision-making and real-time interaction, comprising: Collect the position coordinates, movement speed and direction angle of multiple flying targets in three-dimensional airspace; discretizing the three-dimensional airspace into dynamically updated grid cells based on the position coordinates, and calculating the risk potential energy value of each grid cell according to the movement speed and the direction angle; During the simulation, based on the risk potential energy value, a Monte Carlo algorithm is used to dynamically predict the probability of conflict within a set future time period, and an avoidance instruction set is generated based on the probability of conflict; After the simulation is completed, a conflict report is generated in a real-time interactive display interface according to the avoidance instruction set. The conflict report includes the number of conflicts, the avoidance success rate, and the pilot's response time.

[0007] Optionally, during the simulation, dynamically predicting a conflict probability value within a future set period of time using a Monte Carlo algorithm based on the risk potential energy value, and generating an avoidance instruction set based on the conflict probability value, including: The risk potential energy value of each grid cell is simulated multiple times through random evolution using the Monte Carlo algorithm; Counting the number of position overlaps for each grid cell in all random evolution simulations, and calculating the probability of conflict occurrence for each grid cell within a set future time period based on the ratio of the number of position overlaps to the total number of random evolution simulations; When it is detected that the probability of conflict occurrence of any grid cell exceeds the preset warning threshold, an avoidance instruction set is generated.

[0008] Optionally, the performing of multiple random evolution simulations on the risk potential energy value of each grid unit by using a Monte Carlo algorithm includes: Obtaining the real-time position value of each flying target at the current moment, and determining the unit where each flying target is located according to the real-time position value of each flying target; Allocate a corresponding random evolution weight to each flight target according to the size ratio of the risk potential energy values ​​between the units where the flight targets are located; During each simulation, the random offset direction of each flying target is determined based on the direction angle of each flying target and the corresponding random evolution weight; Based on the random offset direction, calculating the displacement according to a fixed time step, and updating the position of each flying target based on the displacement; When at least two flying targets are determined to be in the same grid cell according to the updated positions, the grid cells are marked as having overlapped positions, so as to complete a single complete simulation process; The complete simulation process is performed independently at least N times, where N is an integer greater than or equal to 1000.

[0009] Optionally, generating a random offset direction of each flying target based on the direction angle of each flying target and the corresponding random evolution weight includes: For each flight target, the following process is performed: multiplying the preset basic angle deviation value by the corresponding random evolution weight to obtain the allowable offset angle value; An angle interval is constructed with the direction angle as the center, wherein the lower limit of the angle interval is the difference between the direction angle and the allowable offset angle value, and the upper limit of the angle interval is the sum of the direction angle and the allowable offset angle value; Generate a random angle value within the angle interval, and round the random angle value according to a preset precision; Determines the random offset direction based on the rounded random angle value.

[0010] Optionally, generating a conflict report in a real-time interactive display interface according to the avoidance instruction set includes: Record the specific instruction content of each generated avoidance instruction set; Monitor the actual flight trajectory of the pilot after he executes the specific instructions; Comparing and analyzing the actual flight trajectory with the expected trajectory of the avoidance instruction set; Based on the comparative analysis results, a conflict report is output in the form of a visual chart in a real-time interactive display interface.

[0011] Optionally, comparing and analyzing the actual flight trajectory with the expected trajectory of the avoidance instruction set includes: Pairing the spatiotemporal coordinate sequence of the actual flight trajectory with the trajectory points with the same timestamp in the spatiotemporal coordinate sequence of the expected trajectory to generate a trajectory point pair set; For each trajectory point pair in the trajectory point pair set, calculating a plane distance of a horizontal position value and a vertical distance of a height value; When the plane distance or the vertical distance exceeds a preset error threshold, marking the trajectory point pair as an abnormal point; Calculating the avoidance success rate based on the ratio of the number of abnormal points to the total number of trajectory point pairs; Detect the difference between the timestamp of the first trajectory point pair marked as an abnormal point and the timestamp of the avoidance command generation as the response delay time; The avoidance success rate, the response delay time, and the maximum position deviation value are combined to obtain a comparative analysis result.

[0012] Optionally, discretizing the three-dimensional airspace into dynamically updated grid cells based on the position coordinates, and calculating the risk potential energy value of each grid cell according to the movement speed and the direction angle includes: Divide the three-dimensional airspace into grid cells of fixed size, and determine the grid cell where each flying target is located according to the position coordinates; Based on the movement speed and the direction angle, calculating the migration probability of each flying target moving to an adjacent grid cell within a set time step; The risk potential energy value of each grid cell is calculated by comprehensively considering the number of flying targets in each grid cell, the migration probability, and the relative movement speed difference between the flying targets.

[0013] In a second aspect, the present application provides a full-flight simulator TCAS simulation system based on dynamic decision-making and real-time interaction, comprising: The acquisition module is used to collect the position coordinates, movement speed and direction angle of multiple flying targets in the three-dimensional airspace; a discretization module, configured to discretize the three-dimensional airspace into dynamically updated grid cells based on the position coordinates, and calculate the risk potential energy value of each grid cell according to the movement speed and the direction angle; a prediction module, configured to dynamically predict, during a simulation process, a probability of conflict occurring within a set future time period based on the risk potential energy value using a Monte Carlo algorithm, and generate an avoidance instruction set based on the probability of conflict occurring; The generation module is used to generate a conflict report in a real-time interactive display interface according to the avoidance instruction set after the simulation is completed. The conflict report includes the number of conflicts, the avoidance success rate and the pilot response time.

[0014] In a third aspect, the present application provides a computing device comprising a processor and a memory, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute any of the full-motion simulator TCAS simulation methods based on dynamic decision-making and real-time interaction as described in the first aspect.

[0015] In a fourth aspect, the present application provides a computer storage medium having computer program instructions stored thereon, which, when executed by a processor, implements a full-motion simulator TCAS simulation method based on dynamic decision-making and real-time interaction as described in any one of the first aspects.

[0016] In the present application, a full-motion simulator TCAS simulation method based on dynamic decision-making and real-time interaction is provided, the method comprising: collecting position coordinates, movement speeds and azimuths of multiple flight targets in a three-dimensional airspace; discretizing the three-dimensional airspace into dynamically updated grid cells based on the position coordinates, and calculating the risk potential energy value of each grid cell according to the movement speed and the azimuth; during the simulation process, dynamically predicting the probability of conflict occurrence within a set future time period through a Monte Carlo algorithm based on the risk potential energy value, and generating an avoidance instruction set based on the conflict probability value; after the simulation is completed, generating a conflict report in a real-time interactive display interface based on the avoidance instruction set, the conflict report including the number of conflicts, the avoidance success rate and the pilot response time.

[0017] The technical solution provided by this application has the following beneficial effects: This application obtains dynamic data of flight targets in real time, provides accurate input for subsequent airspace analysis and conflict prediction, and ensures that the simulation environment is synchronized with the actual flight status. Convert the continuous airspace into discrete units that can be quantified and analyzed, and realize real-time evaluation of the airspace status by dynamically updating the grid and risk potential energy value, laying the foundation for conflict prediction. Use probabilistic simulation methods to predict the potential distribution of conflicts in future time periods, improve the accuracy and foresight of conflict warnings, and adapt to complex and changing airspace environments. Dynamically generate avoidance strategies based on probabilistic prediction results, and provide a set of instructions for altitude, speed or heading adjustments to ensure the scientific nature and flexibility of avoidance decisions. By quantitatively analyzing the number of conflicts, avoidance success rate and pilot response time, provide intuitive data support for training effect evaluation and help optimize training plans.

[0018] Furthermore, during the simulation process, the present application also performs multiple random evolution simulations through the Monte Carlo algorithm based on the risk potential energy value of the grid unit, counts the number of position overlaps of each unit, and calculates the probability of conflict occurrence in the future time period; when the conflict probability of any unit exceeds the warning threshold, an avoidance instruction set including altitude, speed or heading adjustment strategies is generated.

[0019] In addition, high-precision conflict warning can be achieved through dynamic probability prediction and random evolution simulation. The generated avoidance instruction set can adapt to complex airspace changes, improving the authenticity of training scenarios and decision-making reliability.

[0020] These and other aspects of the present application will become more readily apparent from the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 A flowchart of a TCAS simulation method for a full-flight simulator based on dynamic decision-making and real-time interaction provided in an embodiment of the present application; Figure 2 A schematic diagram of the structure of a full-flight simulator TCAS simulation system based on dynamic decision-making and real-time interaction provided in an embodiment of the present application; Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0024] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this document or may be executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any order of execution. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this document are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to being different types.

[0025] Current airborne collision avoidance simulation technology primarily relies on static logic-based preset scenarios. Its conflict rules and avoidance commands are generated based on fixed programming. While this technology can accomplish basic training tasks, it has limitations. Static simulations cannot respond in real time to pilots' dynamic maneuvers and changes in the airspace environment (such as coordinated multi-aircraft maneuvers or sudden weather disturbances), resulting in a disconnect between training scenarios and actual flight. Furthermore, the preset logic struggles to simulate complex airspace situations (such as multiple targets intersecting and conflicting), resulting in a lack of flexibility in the generated avoidance commands and limited training realism. This problem stems from the static and discrete nature of existing technologies, which fail to establish a closed-loop connection between the dynamic environment and real-time decision-making.

[0026] In response to the above-mentioned shortcomings, this application proposes a full-motion simulator TCAS simulation method based on dynamic decision-making and real-time interaction. The core of this method is to build a dynamic response mechanism through real-time airspace gridding and Monte Carlo probability prediction. Specifically, the three-dimensional airspace is discretized into dynamically updated grid cells, the risk potential energy value of each cell is calculated in real time, and the future conflict probability distribution is predicted based on Monte Carlo random evolution simulation, and the avoidance instruction set is dynamically generated according to the probability threshold. This method breaks through the rigid constraints of static logic and achieves three improvements through real-time quantification of airspace status and probabilistic decision-making: first, it dynamically responds to pilot operations and airspace changes, supporting the simulation of complex scenarios such as multi-aircraft collaboration; second, it generates differentiated avoidance strategies through probability prediction to improve the flexibility and adaptability of instructions; and third, it uses closed-loop feedback training data to optimize model parameters and continuously improve simulation accuracy. Therefore, this solution fundamentally solves the problems of insufficient dynamic interactivity and low scene complexity in static simulation, providing technical support for high-fidelity training.

[0027] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0028] Figure 1 A flow chart of a full-flight simulator TCAS simulation method based on dynamic decision-making and real-time interaction provided in an embodiment of the present application is shown as follows: Figure 1 As shown, the method includes: Step 101: Collect the position coordinates, movement speed and direction angle of multiple flying targets in a three-dimensional airspace.

[0029] In step 101, the position coordinates represent the real-time position data of the flying target in three-dimensional space. These coordinates include horizontal position values ​​and vertical altitude values, and are used to determine the spatial distribution of the flying target. The speed represents the current speed of the flying target and is used to calculate its movement trend and potential collision risk. The direction angle represents the angle between the flying target's movement direction and a reference direction, and is used to determine the direction of its flight path.

[0030] In this embodiment, sensors installed in the simulation system or a simulated data interface are used to obtain real-time 3D position coordinates, velocity, and azimuth data for all flight targets. Position coordinates are used to determine the flight target's specific location within the airspace, while velocity and azimuth are used to analyze its motion trends. This data is processed into a unified format and then transferred to the next stage for airspace grid analysis.

[0031] For example, in the simulation system, the position coordinates of flight target A are updated in real time via the simulation data interface. The system records its horizontal position and altitude, while also collecting its velocity and azimuth. Data for flight targets B and C is acquired in the same manner. All data is verified and used to construct the dynamic airspace model.

[0032] Step 102: discretize the three-dimensional space into dynamically updated grid cells based on the position coordinates, and calculate the risk potential energy value of each grid cell according to the movement speed and the direction angle.

[0033] In step 102, the grid cells represent the division of the three-dimensional airspace into fixed-size blocks, each of which is used for independent conflict risk analysis. The risk potential energy value is a quantitative indicator reflecting the potential conflict risk within the grid cell, determined by the target's speed and direction.

[0034] In an embodiment of the present application, the three-dimensional airspace is divided into a plurality of three-dimensional grid cells of the same size, and the position of each cell is defined by its three-dimensional coordinate range. According to the real-time position coordinates of the flying target, the grid cell in which it is located is determined. Based on the movement speed and direction angle, the possibility of the flying target moving to the adjacent grid cell within the set time step is calculated. The risk potential energy value of each grid cell is calculated by combining the number of flying targets in the current grid cell, the movement possibility of adjacent targets and the relative movement speed difference.

[0035] For example, consider a scenario where the airspace is divided into cubic grid cells with fixed sides. Target A is located within a cell. Based on its speed and direction, the probability of it moving to an adjacent cell in the next time step is calculated. Combined with the motion data of targets B and C, the risk potential energy value for that cell is calculated for subsequent conflict prediction.

[0036] Step 103: During the simulation process, a Monte Carlo algorithm is used to dynamically predict the probability of conflict within a future set period of time based on the risk potential energy value, and an avoidance instruction set is generated based on the conflict probability value.

[0037] How dynamics are reflected in step 103: Grid cells are dynamically updated, and therefore the risk potential value is dynamically updated, and therefore the conflict probability value is also updated. The conflict probability value represents the probability of a conflict occurring in a grid cell in the future, calculated through stochastic simulation. The avoidance instruction set represents a set of instructions including altitude, speed, or direction adjustment strategies used to avoid potential conflicts.

[0038] In this embodiment, multiple random evolution simulations are performed on the risk potential value of each grid cell. In each simulation, a random offset direction is generated based on the target's speed and azimuth. Its position is updated at a fixed time step, and any overlap with other targets is detected. The number of grid cell position overlaps across all simulations is counted, and the probability of a collision is calculated. When the probability exceeds a warning threshold, an avoidance instruction set is generated, including an altitude, speed, or azimuth adjustment strategy.

[0039] For example, multiple random simulations are performed on the grid cell where flight target A is located to predict its future position changes. After counting the number of position overlaps, the probability of a collision is calculated. If the probability exceeds a threshold, the system generates avoidance instructions such as "increase altitude" or "slow down" for the pilot to execute.

[0040] Step 104: After the simulation is completed, a conflict report is generated in a real-time interactive display interface according to the avoidance instruction set. The conflict report includes the number of conflicts, the avoidance success rate, and the pilot's response time.

[0041] In step 104 , the conflict report represents summary data including indicators such as the number of conflicts, avoidance success rate, and pilot response time, which is used to evaluate the training effect.

[0042] In this embodiment, the results of each avoidance command execution are recorded, including pilot operation data and actual avoidance results. The command's expected trajectory is compared with the actual flight trajectory, and the number of conflicts and avoidance success rate are counted. The response time from command generation to pilot execution is calculated. All data is aggregated and displayed as a chart in the interactive interface.

[0043] For example, after the simulation is complete, the system calculates the execution of avoidance commands for Target A, analyzes the difference between its actual trajectory and the expected trajectory, and calculates the avoidance success rate and response time. The resulting report shows the number of conflicts and pilot performance during this training session.

[0044] This method collects flight target data in real time, dynamically divides the airspace into grids, calculates risk potential energy, generates avoidance instructions using probabilistic prediction, and ultimately outputs a training evaluation report. This method achieves high-precision conflict warning and flexible avoidance decision-making in complex airspace environments, enhancing the realism and effectiveness of simulation training.

[0045] To address the problem of insufficient dynamic response capability of existing air collision avoidance simulation technologies, in some embodiments, step 103: dynamically predicting the probability of collision within a future set period of time based on the risk potential energy value using a Monte Carlo algorithm during the simulation process, and generating an avoidance instruction set based on the collision probability value, includes: Step 201: Perform multiple random evolution simulations on the risk potential energy value of each grid cell using the Monte Carlo algorithm.

[0046] In step 201, random evolution simulation refers to the process of multiple simulations and deductions of the future motion trajectory of the flight target based on the current airspace state using a probabilistic method. Each simulation generates a possible movement path based on the motion characteristics of the flight target.

[0047] In this embodiment, the system uses the risk potential of each grid cell as a basis for multiple independent simulations of flight targets within that cell. In each simulation, a random offset direction is generated within the target's possible range of movement based on its speed and azimuth. The target's position is updated at a fixed time step, and the state of the grid cell after the shift is recorded. By repeating this process repeatedly, a statistical sample of the target's distribution over the future time period is formed.

[0048] Step 202: Count the number of position overlaps of each grid unit in all random evolution simulations, and calculate the probability of conflict occurrence of each grid unit in a future set time period based on the ratio of the number of position overlaps to the total number of random evolution simulations.

[0049] In step 202, the number of position overlaps refers to the number of times two or more flight target positions appear simultaneously within the same grid cell during the Monte Carlo random evolution simulation, quantifying the likelihood of a collision within that cell. The total number of random evolution simulations represents a preset number of simulations (e.g., 1000) to ensure statistical reliability. This number is determined based on computational accuracy requirements and system performance. A higher number of simulations results in a probability calculation closer to the true distribution.

[0050] In this embodiment of the present application, the system counts the number of times the flight target positions overlap for each grid cell across all simulations and uses the ratio of this number to the total number of simulations as the collision probability. For example, if a cell overlaps 200 times in 1000 simulations, its collision probability is 0.2. This probability is used to quantify the collision risk.

[0051] Step 203: When it is detected that the collision probability value of any grid unit exceeds a preset warning threshold, an avoidance instruction set is generated.

[0052] In step 203, the preset warning threshold represents a pre-set collision risk critical value (e.g., 0.25). When the collision probability value of a grid unit exceeds the threshold, it is determined that an avoidance instruction needs to be generated. The threshold value is optimized based on safety standards and historical data.

[0053] In this embodiment of the present application, when the collision probability value for a grid cell exceeds a preset warning threshold, the system generates differentiated avoidance instructions based on the relative position and motion state of the target. For example, an "ascend" instruction may be generated for an approaching target, while a "slow down" instruction may be generated for targets at the same altitude, ensuring the pertinence and operability of the instructions.

[0054] Here's a specific example: In a simulation training scenario, targets A, B, and C simultaneously enter the same airspace. The system first collects real-time position coordinates, speed, and azimuth data for all three. Target A is located in grid cell G5. The system then performs multiple random evolution simulations on this cell. In each simulation, based on target A's speed of 500 km / h and a azimuth of 30 degrees, a random offset angle is generated within a range of 15 degrees to the left or right of its direction of motion. This displacement is calculated using a fixed time step of 10 seconds to update the predicted position. Simultaneously, target B moves toward an adjacent cell at a speed of 600 km / h and a azimuth of 45 degrees, while target C moves at a speed of 550 km / h and a azimuth of 60 degrees. After 1,000 independent simulations, it is determined that targets A and B overlap 180 times within cell G5, and overlap with C 120 times. The maximum number of overlaps, 180, is taken as the number of overlaps for that cell. The conflict probability calculation formula (number of overlaps divided by the total number of simulations) yields a conflict probability of 0.18 for cell G5. The system's preset warning threshold is 0.15. Since 0.18 exceeds this threshold, the decision module generates a set of targeted avoidance instructions, including an instruction to ascend 50 meters for flight target A and an instruction to turn left 10 degrees for flight target B.

[0055] In the embodiment of the present application, through dynamic probability prediction and targeted instruction generation, real-time conflict warning and flexible avoidance in complex airspace environments are achieved, thereby improving the authenticity of simulation training and the reliability of decision-making.

[0056] In order to solve the problem of insufficient dynamic prediction accuracy in existing air collision avoidance simulations, in some embodiments, step 201: performing multiple random evolution simulations of the risk potential energy value of each grid cell using the Monte Carlo algorithm includes: Step 301: Acquire the real-time position value of each flying target at the current moment, and determine the unit where each flying target is located according to the real-time position value of each flying target.

[0057] In step 301, the real-time position value contains the specific coordinate data of the flying target in the three-dimensional airspace, which is used for precise positioning. The unit refers to the grid unit number where the flying target is currently located, which is determined by comparing the coordinates with the grid boundary.

[0058] In an embodiment of the present application, the system first obtains the real-time three-dimensional coordinates of all flying targets, and determines the specific unit number to which each flying target belongs based on the pre-divided grid unit space range, providing a spatial basis for subsequent weight allocation.

[0059] Step 302: assigning a corresponding random evolution weight to each flight target according to the size ratio of the risk potential energy values ​​between the units where each flight target is located.

[0060] In step 302, the ratio of the risk potential energy value refers to the relative relationship between the risk potential energy values ​​of adjacent grid cells. It is obtained by normalizing the risk potential energy values ​​of each cell and then comparing them, and is used to reflect the difference in the degree of danger in different spatial areas. This ratio is derived from the risk potential energy value of the grid cell calculated in step 102, and is obtained by dividing the value of each cell by the sum of the values ​​of all adjacent cells. The random evolution weight refers to the simulation priority coefficient assigned to the flight target based on the ratio of the risk potential energy value. The higher the weight, the greater the range of movement direction changes allowed for the target during the simulation process, which is used to focus on exploring potential paths in high conflict risk areas. The weight value is proportional to the ratio of the risk potential energy value of the grid cell. The random evolution weight allocation is to assign different simulation priorities to the flight targets within the cell based on the relative size of the risk potential energy value of the grid cell. The higher the weight value, the greater the possibility of variation in the movement path of the target.

[0061] In an embodiment of the present application, the system compares the differences in risk potential energy values ​​between adjacent grid cells and assigns higher weights to flying targets in high-risk cells, so that they obtain a larger range of motion direction changes during the simulation process, thereby more fully exploring potential conflict paths.

[0062] Step 303: During each simulation process, the random offset direction of each flying target is determined based on the direction angle of each flying target and the corresponding random evolution weight.

[0063] In step 303, the random offset direction is a random angular deviation added to the original flight target's direction. The deviation range is determined by the random evolution weights to simulate the heading uncertainty that may exist in actual flight. The offset direction is uniformly and randomly generated within the angular range corresponding to the weights.

[0064] In the embodiment of the present application, the maximum allowable deviation angle is determined based on the assigned weight value, with the higher the weight, the larger the angle range. In each simulation, the system randomly selects an deviation direction within the angle range as the flight direction adjustment value for this simulation.

[0065] Step 304: Based on the random offset direction, calculate the displacement according to a fixed time step, and update the position of each flying target based on the displacement.

[0066] In step 304, the displacement represents the distance the target moves in the random offset direction within a fixed time step. This displacement, determined by the current velocity and the step length, is used to update the target's predicted position. The calculation formula is: displacement = velocity × time step × direction unit vector. The position update process calculates the target's distance traveled during the simulation period based on the new direction and fixed time step length, and updates its predicted position coordinates.

[0067] In an embodiment of the present application, the system uses the current speed of the flying target and the randomly generated direction angle, combined with a fixed time step, to calculate the displacement through a kinematic formula, and updates the target position to the new coordinates to complete a single-step movement simulation.

[0068] Step 305: When it is determined based on the updated positions that at least two flying targets are in the same grid unit, the grid units are marked as having overlapping positions, so as to complete a single complete simulation process.

[0069] In step 305, position overlap refers to the situation where the predicted positions of two or more flight targets simultaneously fall into the same grid cell during the simulation, indicating a potential collision risk. Each overlap event is recorded and used for subsequent collision probability statistics.

[0070] In an embodiment of the present application, the system detects the new positions of all flying targets. If two or more targets are found in the same unit, the unit is marked as overlapping, and the flight target numbers and overlapping times involved are recorded.

[0071] Step 306: independently execute at least N complete simulation processes, where N is an integer greater than or equal to 1000.

[0072] In an embodiment of the present application, the system automatically executes a complete simulation process including all the aforementioned sub-steps, using independent random parameters for each simulation, and executing the process for no less than 1,000 times cumulatively to form a stable probability distribution.

[0073] Here's a specific example: During the simulation training, the system detected targets D, E, and F simultaneously entering the airspace grid area designated G12. Target D was located at the center of cell G12, with a real-time speed of 480 km / h and a bearing angle of 25 degrees. Target E approached from the adjacent cell G11 at a speed of 520 km / h at a bearing angle of 40 degrees. Target F was moving from cell G13 at a speed of 500 km / h at a bearing angle of 55 degrees. The system first calculated the risk potential energy value for each cell: G12 had a value of 0.35, G11 had a value of 0.28, and G13 had a value of 0.31. Based on the proportion of the risk potential energy values, a random evolution weight of 0.38 was assigned to target D, 0.32 to target E, and 0.30 to target F. In the first simulation, the system generated a random offset of 8 degrees to the left of target D's original 25-degree heading based on a weight of 0.38. Using a fixed 10-second step size, the system calculated a displacement of 1,333 meters, updating its predicted position to the edge of cell G12. Target E received a heading 6 degrees to the right, a displacement of 1,444 meters, and entered cell G12. Target F received a heading 5 degrees to the left, a displacement of 1,389 meters, and remained in cell G13. At this point, targets D and E were detected to have overlapped within cell G12, and the system recorded this overlap. In the second simulation, target D received a heading 4 degrees to the right, remaining in cell G12, while target E received a heading 9 degrees to the left, leaving the cell; no overlap occurred. After repeating this process 1,000 times, statistics showed that targets D and E overlapped 210 times within cell G12, and D and F overlapped 150 times. The maximum number of overlaps for that cell was 210, with the maximum number of overlaps for that cell being taken as the number of overlaps. According to the calculation formula that the conflict probability value is equal to the number of position overlaps divided by the total number of simulations, where the number of position overlaps is 210 and the total number of simulations is 1000, the conflict probability value of unit G12 is calculated to be 0.21.

[0074] In the embodiment of the present application, through the focused simulation guided by weight distribution and a large number of repeated random evolutions, comprehensive detection of potential conflicts in complex airspace environments is achieved, providing a highly reliable probabilistic basis for avoidance decisions, and effectively improving the authenticity and safety of simulation training.

[0075] In order to solve the accuracy control problem of flight target dynamic path simulation, in some embodiments, step 303: generating a random offset direction of each flight target based on the direction angle of each flight target and the corresponding random evolution weight includes: Step 401: For each flight target, execute the following process: multiply the preset basic angle deviation value by the corresponding random evolution weight to obtain the allowable offset angle value.

[0076] In step 401, the base angle deviation value represents a pre-set standard angle variation range, used to control the basic range of variation in the target's motion direction. The allowable deviation angle value represents the actual deviation angle range after weight adjustment, reflecting the maximum allowable directional variation of the target during the simulation.

[0077] In an embodiment of the present application, the system multiplies the preset basic angle deviation value with the random evolution weight corresponding to the flight target to obtain the maximum angle offset value allowed for the target in the current simulation. The larger the weight, the larger the allowed offset angle.

[0078] Step 402: construct an angle interval with the direction angle as the center, the lower limit of the angle interval is the difference between the direction angle and the allowable offset angle value, and the upper limit of the angle interval is the sum of the direction angle and the allowable offset angle value.

[0079] In step 402, the angle interval represents a direction change range formed by allowing the offset angle value to be extended to the left and right sides with the original direction angle of the flying target as the center.

[0080] In an embodiment of the present application, the system uses the current direction angle of the flying target as a reference, subtracts the allowable offset angle value to the left to obtain the lower limit of the interval, and adds the allowable offset angle value to the right to obtain the upper limit of the interval, thereby constructing a complete range of allowable offset directions.

[0081] Step 403: Generate a random angle value within the angle range, and round the random angle value according to a preset precision.

[0082] In step 403, the random angle value represents a specific direction angle randomly selected from an angle interval by uniform distribution. The rounding process represents rounding the randomly generated angle value to the minimum precision unit required by the system.

[0083] In an embodiment of the present application, the system randomly selects an angle value within a determined angle range, and then rounds the value according to a preset accuracy requirement to ensure that the generated angle meets the system processing accuracy.

[0084] Step 404: Determine the random offset direction according to the rounded random angle value.

[0085] In an embodiment of the present application, the system uses the rounded random angle value as the actual offset direction of the flying target in this simulation for subsequent displacement calculations.

[0086] Here's a specific example: During simulation training, the system generated a random offset direction for target D as follows: First, a base angle deviation value of 20 degrees was set. Based on the random evolution weight of 0.38 assigned to target D, the allowable offset angle was calculated as 20 degrees multiplied by 0.38, which equals 7.6 degrees, rounded to 8 degrees. With target D's current heading angle of 25 degrees as the center, an angle interval was constructed from 25 degrees minus 8 degrees to 25 degrees plus 8 degrees, or 17 to 33 degrees. Within this interval, the system randomly generated an angle value of 29.7 degrees, rounded to 1 degree precision to 30 degrees. Based on the rounded result, the random offset direction for target D was determined to be 5 degrees to the right. Simultaneously, the random offset direction for target E was generated as follows: the base angle deviation value of 20 degrees was multiplied by the weight of 0.32 to obtain an allowable offset angle of 6.4 degrees, rounded to 6 degrees. Using the heading angle of 40 degrees, an angle interval of 34 to 46 degrees was constructed. A random angle value of 42.5 degrees was generated, rounded to 43 degrees, and a final offset direction of 3 degrees to the right was determined. The processing process for flight target F is similar. 20 degrees multiplied by the weight 0.3 results in an allowable offset angle value of 6 degrees. An angle range of 49 to 61 degrees is constructed with a direction angle of 55 degrees. 57.2 degrees is randomly generated and rounded to 57 degrees, and an offset direction of 2 degrees to the right is determined.

[0087] In the embodiments of the present application, scientific simulation of the motion path of the flying target is achieved through weight-adjusted offset angle control and random direction generation, which not only ensures the full exploration of high-risk targets but also maintains the rationality of the simulation process, providing a reliable path evolution basis for conflict prediction.

[0088] To address the real-time and visualization issues of flight training effectiveness evaluation, in some embodiments, step 104: generating a conflict report in a real-time interactive display interface based on the avoidance instruction set includes: Step 501: Record the specific instruction content in each generated avoidance instruction set.

[0089] In step 501, the specific instruction content refers to the detailed avoidance operation requirements generated by the system based on the conflict prediction results. It includes specific adjustment types such as "ascend / descend altitude value", "accelerate / decelerate to target speed value", or "turn left / right to a specified direction angle", as well as the corresponding adjustment amplitude value and execution time requirements, which are used to guide the pilot to make precise flight attitude and trajectory adjustments.

[0090] In an embodiment of the present application, the system fully records the details of each avoidance instruction generated, including adjustment type, amplitude, execution time limit and other information, to form an instruction execution list, providing benchmark data for subsequent trajectory comparison.

[0091] Step 502: Monitor the actual flight trajectory of the pilot after executing the specific instruction content.

[0092] In step 502 , the actual flight trajectory represents the actual motion path data of the flight target after the pilot executes the avoidance instruction, and is composed of a position coordinate sequence.

[0093] In an embodiment of the present application, the system continuously collects real-time position information of the flying target through a positioning device, and records its motion trajectory at fixed time intervals to ensure that the data completely corresponds to the instruction execution period.

[0094] Step 503: Compare and analyze the actual flight trajectory with the expected trajectory of the avoidance instruction set.

[0095] In step 503 , the expected trajectory represents an ideal flight path calculated based on the theoretical requirements of the avoidance instruction, and is used for comparison with the actual trajectory.

[0096] In an embodiment of the present application, the system calculates a theoretical flight path based on the adjustment requirements of the avoidance instruction and the initial state of the flight target through a kinematic model as a reference standard for evaluating the accuracy of the pilot's operation.

[0097] Step 504: Based on the comparison and analysis results, a conflict report is output in the form of a visual chart in the real-time interactive display interface.

[0098] In step 504 , the visualization chart represents a comprehensive report that presents the analysis results in a graphical manner, including a trajectory comparison chart and a display of key indicators.

[0099] In an embodiment of the present application, the system superimposes the actual trajectory and the expected trajectory, identifies the deviation areas with different colors, and displays core indicators such as the number of conflicts and instruction execution delay time in the form of bar charts and line charts.

[0100] Here is a specific example: During the simulation training, after the system detected a potential conflict risk between flight targets A and B, it generated an avoidance instruction set requiring flight target A to ascend 80 meters within 5 seconds and flight target B to decelerate to 85% of its original speed within 3 seconds. The system fully recorded the contents of these two specific instructions, including the adjustment type, amplitude, and time requirements. The pilot then began to execute the instructions. The system continuously collected the actual trajectory of flight target A, showing that it ascended 75 meters within 6 seconds and flight target B decelerated to 82% of its original speed within 4 seconds. The system compared and analyzed the actual trajectory with the expected trajectory. The altitude deviation of flight target A was calculated by subtracting the expected altitude of 80 meters from the actual ascent altitude of 75 meters to obtain a deviation of 5 meters. The speed deviation of flight target B was calculated by subtracting the expected speed after deceleration from the actual speed after deceleration to obtain a deviation of 3%. Based on these comparative data, the system generates a visual report on the interactive interface, using a two-color curve overlay to display the expected and actual trajectories. The trajectory of flight target A is marked with a 5-meter height deviation area in red, and the trajectory of flight target B is marked with a 3% speed deviation area in yellow. The report also shows that in this training, the command response delay of flight target A was 1 second, and the delay of flight target B was 1.5 seconds. The overall avoidance success rate was assessed as good.

[0101] In the embodiment of the present application, through the recording and comparative analysis of the entire process of instruction execution, an objective quantitative evaluation of the training effect is achieved, and the differences between the pilot's operation and the theoretical requirements are intuitively displayed, providing a clear basis for training improvement, and effectively improving the quality and efficiency of training.

[0102] To address the accuracy issue of quantitative evaluation of avoidance effectiveness during flight training, in some embodiments, step 503 of comparing and analyzing the actual flight trajectory with the expected trajectory of the avoidance instruction set includes: Step 601: Pair the trajectory points with the same timestamp in the spatiotemporal coordinate sequence of the actual flight trajectory and the spatiotemporal coordinate sequence of the expected trajectory to generate a trajectory point pair set.

[0103] In step 601, the trajectory point pair set represents a pairing set formed by one-to-one correspondence between the actual flight trajectory and the expected trajectory according to the position data at the same time point, which is used to accurately compare the flight status differences at each moment.

[0104] In the embodiment of the present application, the system uses a timestamp matching algorithm to align the actually collected trajectory points with the theoretically calculated expected trajectory points in chronological order, ensuring that each comparison point represents two states at the same moment.

[0105] Step 602: For each trajectory point pair in the trajectory point pair set, calculate the plane distance of the horizontal position value and the vertical distance of the height value.

[0106] In step 602, the horizontal distance represents the position deviation of the trajectory point in the horizontal direction, reflecting the degree of deviation of the flight target in the longitude and latitude dimensions. The vertical distance represents the position deviation of the trajectory point in the height direction, reflecting the degree of deviation of the flight target in the altitude.

[0107] In the embodiment of the present application, the system calculates the straight-line distance on the horizontal plane and the difference on the height axis for each pair of trajectory points, and comprehensively quantifies the position deviation.

[0108] Step 603: When the plane distance or the vertical distance exceeds a preset error threshold, mark the trajectory point pair as an abnormal point.

[0109] In step 603 , the abnormal point represents a trajectory point in the actual flight trajectory that exceeds the allowable error range, reflecting the specific moment when the avoidance operation did not meet expectations.

[0110] In an embodiment of the present application, the system compares the calculated plane distance and vertical distance with a preset safety threshold. If any dimension exceeds the threshold, the moment is marked as abnormal, and the abnormality type and deviation amount are recorded.

[0111] Step 604: Calculate the avoidance success rate based on the ratio of the number of abnormal points to the total number of trajectory point pairs.

[0112] In step 604 , the avoidance success rate represents the proportion of trajectory points that successfully meet the expected requirements to the total trajectory points, reflecting the overall avoidance effect.

[0113] In the embodiment of the present application, the system counts the number of all trajectory points that are not marked as abnormal points, divides the number by the total number of trajectory points, and obtains the avoidance success rate indicator.

[0114] Step 605: Detect the difference between the timestamp of the first trajectory point pair marked as an abnormal point and the timestamp of the avoidance instruction generation as the response delay time.

[0115] In step 605 , the response delay time represents the time difference from when the instruction is issued to when the pilot starts to effectively execute it, reflecting the operation reaction speed.

[0116] In the embodiment of the present application, the system identifies the timestamp of the first abnormal point, subtracts the timestamp of the instruction generation, and obtains the delay time from the pilot receiving the instruction to starting to execute it.

[0117] Step 606: Combine the avoidance success rate, the response delay time, and the maximum position deviation value to obtain a comparative analysis result.

[0118] In step 606, the maximum position deviation value refers to the maximum horizontal distance or maximum height difference between the actual flight trajectory and the expected trajectory in all trajectory point pairs. It is obtained in the following way: during the comparative analysis process, the system records the plane distance and vertical distance values ​​calculated for each trajectory point pair, and then screens out the maximum plane distance and the maximum vertical distance from all trajectory point pairs, and takes the larger of the two maximum values ​​as the final maximum position deviation value. For example, when the maximum plane distance is 210 meters and the maximum vertical distance is 4 meters, the maximum position deviation value is 210 meters.

[0119] In an embodiment of the present application, the system traverses the deviation data of all abnormal points, extracts the maximum values ​​in the plane and vertical directions, and together with the avoidance success rate and response delay time, constitutes the final evaluation result.

[0120] Here's a specific example: During the simulation training, the system conducted a full-process evaluation of the avoidance maneuvers for targets A and B. First, a set of trajectory point pairs was established, matching the actual position data of target A every 0.2 seconds with the corresponding time point position in the expected trajectory, resulting in a total of 30 pairs of trajectory points. For each pair of trajectory points, the horizontal distance and altitude difference were calculated. The horizontal distance was calculated by the difference in the longitude and latitude coordinates of the two points, while the altitude difference was directly subtracted. The horizontal error threshold was set to 10 meters, and the altitude error threshold was set to 5 meters. Analysis revealed that the altitude deviation of 6 meters, exceeding the threshold, began at the sixth pair of points. This was marked as the first outlier. Its timestamp differed from the command generation timestamp by 1.2 seconds, indicating the response delay. Continuing to analyze the remaining trajectory points, a total of five altitude outliers and two horizontal outliers were marked. The avoidance success rate was calculated by dividing the number of unmarked trajectory points (23) by the total number of trajectory points (30), yielding an avoidance success rate of approximately 77%. The maximum position deviation occurred at the 15th pair of points, with an altitude difference of 8 meters. The analysis process for flight target B was similar, resulting in 25 pairs of trajectory points. The speed deviation was calculated by subtracting the actual speed from the expected speed and dividing it by the expected speed. A total of three speed anomalies were marked, with a response delay of 1.5 seconds and an avoidance success rate of 88%.

[0121] In the embodiment of the present application, through the refined trajectory comparison and multi-dimensional deviation analysis of time and space alignment, a comprehensive and objective evaluation of the avoidance operation effect is achieved, providing accurate data support for pilot training improvements, and effectively improving training quality and flight safety levels.

[0122] To address the accuracy issue of dynamic assessment of airspace conflict risk, in some embodiments, step 102: discretizing the three-dimensional airspace into dynamically updated grid cells based on the position coordinates, and calculating the risk potential energy value of each grid cell based on the motion speed and the direction angle, includes: Step 701: Divide the three-dimensional airspace into grid units of fixed size, and determine the grid unit where each flying target is located based on the position coordinates.

[0123] In step 701 , a fixed-size grid unit represents dividing a three-dimensional space into a plurality of cubic blocks of the same size, and each block defines a spatial position by a three-dimensional coordinate range.

[0124] In an embodiment of the present application, the system evenly divides the entire airspace according to a preset division rule, quickly locates the specific grid unit where the flying target is located based on the real-time position coordinates of the flying target, and provides a spatial benchmark for risk analysis.

[0125] Step 702: Based on the movement speed and the direction angle, calculate the migration probability of each flying target moving to an adjacent grid unit within a set time step.

[0126] In step 702, the migration probability represents the possibility of the flying target moving to the adjacent grid unit in the next time step, which is determined by the movement speed and direction angle.

[0127] In an embodiment of the present application, the system calculates the probability distribution of the flying target moving to adjacent units in front, back, left, right, top, and bottom within a set time based on its current motion state, combined with its motion direction and speed, reflecting the target's motion trend.

[0128] Step 703: Calculate the risk potential energy value of each grid cell by comprehensively considering the number of flying targets in each grid cell, the migration probability, and the relative motion speed difference between the flying targets.

[0129] In step 703, the relative motion speed difference indicates the degree of difference in motion speed between different flying targets in the same grid unit, reflecting the potential collision risk.

[0130] In an embodiment of the present application, the system counts the number of flying targets in each grid unit, combines the migration probability of each target, and then calculates the speed difference between the targets. By weighted fusion of these factors, the real-time risk potential value of the unit is obtained.

[0131] Here's a specific example: During the simulation training process, the system calculated the risk potential energy value for the grid cell numbered G5. First, it was determined that there were flying targets A and B within the cell. The speed of flying target A was 500 units and the direction angle was 30 degrees. Based on its motion state, the system calculated that within the next time step of 10 seconds, the probability of migrating to the adjacent cell G6 on the right was 0.65, and the probability of migrating to the cell directly in front of it, G8, was 0.25. The speed of flying target B was 600 units and the direction angle was 210 degrees. The calculated probability of migrating to the cell G4 on the left was 0.7, and the probability of migrating to the cell G2 behind was 0.2. The system calculated that the relative speed difference between the two targets was 100 units. According to the risk potential energy calculation formula, the weight coefficient for the number of targets within a cell is 0.4, the weight coefficient for the migration probability difference is 0.3, and the weight coefficient for the speed difference is 0.3. Specifically, the calculation process is to multiply the number of targets (2) by 0.4 to get 0.8, multiply the migration probability difference (0.05) by 0.3 to get 0.015, and multiply the speed difference (100 divided by 1000) by 0.3 to get 0.03. Adding these three together, the risk potential energy value for cell G5 is 0.845. The system also calculates the risk potential energy values ​​for adjacent cells G6 as 0.52 and G8 as 0.31.

[0132] In the embodiment of the present application, through grid space management and multi-factor fusion calculation, a refined dynamic assessment of airspace risks is achieved, providing a reliable basis for conflict warning and improving the accuracy and timeliness of flight safety monitoring.

[0133] Figure 2 A structural diagram of a full-flight simulator TCAS simulation system based on dynamic decision-making and real-time interaction provided in an embodiment of the present application is shown as follows: Figure 2 As shown, the system includes: The acquisition module 21 is used to acquire the position coordinates, movement speed and direction angle of multiple flying targets in the three-dimensional airspace.

[0134] The discretization module 22 is configured to discretize the three-dimensional space into dynamically updated grid cells based on the position coordinates, and calculate the risk potential energy value of each grid cell according to the movement speed and the direction angle.

[0135] The prediction module 23 is used to dynamically predict the probability of conflict within a set period of time in the future according to the risk potential value through the Monte Carlo algorithm during the simulation process, and generate an avoidance instruction set according to the probability of conflict.

[0136] The generation module 24 is used to generate a conflict report in a real-time interactive display interface according to the avoidance instruction set after the simulation is completed. The conflict report includes the number of conflicts, the avoidance success rate and the pilot response time.

[0137] Figure 2The TCAS simulation system based on dynamic decision making and real-time interaction can be executed Figure 1 The implementation principles and technical effects of the TCAS simulation method for a full-flight simulator based on dynamic decision-making and real-time interaction described in the illustrated embodiment will not be elaborated upon. The specific manner in which each module and unit performs operations in the TCAS simulation system for a full-flight simulator based on dynamic decision-making and real-time interaction in the aforementioned embodiment has been described in detail in the related embodiments and will not be further elaborated upon here.

[0138] In one possible design, Figure 2 The TCAS simulation system of the full-flight simulator based on dynamic decision-making and real-time interaction of the embodiment shown can be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32; The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0139] The processing component 32 is used to perform the above Figure 1 The embodiment provides a TCAS simulation method for a full-flight simulator based on dynamic decision-making and real-time interaction.

[0140] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above method.

[0141] The storage component 31 is configured to store various types of data to support operations on the terminal. The storage component can be implemented by any type of volatile or non-volatile memory device, or a combination thereof, such as static random-access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.

[0142] Of course, a computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0143] The input / output interface provides an interface between the processing component and the peripheral interface module, which can be an output device, an input device, etc.

[0144] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0145] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0146] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 The embodiment shown is a full-flight simulator TCAS simulation method based on dynamic decision-making and real-time interaction.

[0147] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0148] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0149] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0150] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A TCAS simulation method for a full-flight simulator based on dynamic decision-making and real-time interaction, characterized in that: include: Collect the position coordinates, movement speed and direction angle of multiple flying targets in three-dimensional airspace; discretizing the three-dimensional airspace into dynamically updated grid cells based on the position coordinates, and calculating the risk potential energy value of each grid cell according to the movement speed and the direction angle; During the simulation, based on the risk potential energy value, a Monte Carlo algorithm is used to dynamically predict the probability of conflict within a set future time period, and an avoidance instruction set is generated based on the probability of conflict; After the simulation is completed, a conflict report is generated in a real-time interactive display interface according to the avoidance instruction set. The conflict report includes the number of conflicts, the avoidance success rate, and the pilot's response time.

2. The TCAS simulation method for a full-flight simulator based on dynamic decision-making and real-time interaction according to claim 1 is characterized in that: During the simulation process, based on the risk potential energy value, a Monte Carlo algorithm is used to dynamically predict the probability of conflict within a future set period of time, and an avoidance instruction set is generated based on the conflict probability value, including: The risk potential energy value of each grid cell is simulated multiple times through random evolution using the Monte Carlo algorithm; Counting the number of position overlaps for each grid cell in all random evolution simulations, and calculating the probability of conflict occurrence for each grid cell within a set future time period based on the ratio of the number of position overlaps to the total number of random evolution simulations; When it is detected that the probability of conflict occurrence of any grid cell exceeds the preset warning threshold, an avoidance instruction set is generated.

3. The TCAS simulation method for a full-flight simulator based on dynamic decision-making and real-time interaction according to claim 2 is characterized in that: The Monte Carlo algorithm is used to perform multiple random evolution simulations on the risk potential energy value of each grid cell, including: Obtaining the real-time position value of each flying target at the current moment, and determining the unit where each flying target is located according to the real-time position value of each flying target; Allocate a corresponding random evolution weight to each flight target according to the size ratio of the risk potential energy values ​​between the units where the flight targets are located; During each simulation, the random offset direction of each flying target is determined based on the direction angle of each flying target and the corresponding random evolution weight; Based on the random offset direction, calculating the displacement according to a fixed time step, and updating the position of each flying target based on the displacement; When at least two flying targets are determined to be in the same grid cell according to the updated positions, the grid cells are marked as having overlapped positions, so as to complete a single complete simulation process; The complete simulation process is performed independently at least N times, where N is an integer greater than or equal to 1000.

4. The TCAS simulation method for a full-flight simulator based on dynamic decision-making and real-time interaction according to claim 3 is characterized in that: The generating of the random offset direction of each flying target based on the direction angle of each flying target and the corresponding random evolution weight includes: For each flight target, the following process is performed: multiplying the preset basic angle deviation value by the corresponding random evolution weight to obtain the allowable offset angle value; An angle interval is constructed with the direction angle as the center, wherein the lower limit of the angle interval is the difference between the direction angle and the allowable offset angle value, and the upper limit of the angle interval is the sum of the direction angle and the allowable offset angle value; Generate a random angle value within the angle interval, and round the random angle value according to a preset precision; Determines the random offset direction based on the rounded random angle value.

5. The TCAS simulation method for a full-flight simulator based on dynamic decision-making and real-time interaction according to claim 1 is characterized in that: Generating a conflict report in a real-time interactive display interface according to the avoidance instruction set includes: Record the specific instruction content of each generated avoidance instruction set; Monitor the actual flight trajectory of the pilot after he executes the specific instructions; Comparing and analyzing the actual flight trajectory with the expected trajectory of the avoidance instruction set; Based on the comparative analysis results, a conflict report is output in the form of a visual chart in a real-time interactive display interface.

6. The TCAS simulation method for a full-flight simulator based on dynamic decision-making and real-time interaction according to claim 5 is characterized in that: The comparing and analyzing the actual flight trajectory with the expected trajectory of the avoidance instruction set includes: Pairing the spatiotemporal coordinate sequence of the actual flight trajectory with the trajectory points with the same timestamp in the spatiotemporal coordinate sequence of the expected trajectory to generate a trajectory point pair set; For each trajectory point pair in the trajectory point pair set, calculating a plane distance of a horizontal position value and a vertical distance of a height value; When the plane distance or the vertical distance exceeds a preset error threshold, marking the trajectory point pair as an abnormal point; Calculating the avoidance success rate based on the ratio of the number of abnormal points to the total number of trajectory point pairs; Detect the difference between the timestamp of the first trajectory point pair marked as an abnormal point and the timestamp of the avoidance command generation as the response delay time; The avoidance success rate, the response delay time, and the maximum position deviation value are combined to obtain a comparative analysis result.

7. The TCAS simulation method for a full-flight simulator based on dynamic decision-making and real-time interaction according to claim 1 is characterized in that: The discretizing the three-dimensional airspace into dynamically updated grid cells based on the position coordinates, and calculating the risk potential energy value of each grid cell according to the movement speed and the direction angle, includes: Divide the three-dimensional airspace into grid cells of fixed size, and determine the grid cell where each flying target is located according to the position coordinates; Based on the movement speed and the direction angle, calculating the migration probability of each flying target moving to an adjacent grid cell within a set time step; The risk potential energy value of each grid cell is calculated by comprehensively considering the number of flying targets in each grid cell, the migration probability, and the relative movement speed difference between the flying targets.

8. A full-flight simulator TCAS simulation system based on dynamic decision-making and real-time interaction, characterized in that: include: The acquisition module is used to collect the position coordinates, movement speed and direction angle of multiple flying targets in the three-dimensional airspace; a discretization module, configured to discretize the three-dimensional airspace into dynamically updated grid cells based on the position coordinates, and calculate the risk potential energy value of each grid cell according to the movement speed and the direction angle; a prediction module, configured to dynamically predict, during a simulation process, a probability of conflict occurring within a set future time period based on the risk potential energy value using a Monte Carlo algorithm, and generate an avoidance instruction set based on the probability of conflict occurring; The generation module is used to generate a conflict report in a real-time interactive display interface according to the avoidance instruction set after the simulation is completed. The conflict report includes the number of conflicts, the avoidance success rate and the pilot response time.

Images