A flight simulation training analysis system and method based on big data

Abstract

The present invention relates to the field of flight simulation technology, and in particular to a flight simulation training analysis system and method based on big data, wherein the analysis method comprises the following steps: step S1, selecting a training scene and inputting a training plan; step S2, calculating a switching smoothing value between any two task scenes; step S3, adjusting the order of training tasks according to the switching smoothing value; step S4, performing flight training according to the selected training plan and evaluating the training score. The present invention monitors data in the flight simulation training process, collects and analyzes training task data after switching task scenes, analyzes the switching smoothing value between two task scenes, arranges the training tasks in the training plan according to the switching smoothing value, forms a personalized training plan, and avoids affecting the training plan of trainees due to the switching of task scenes by reasonably planning the conversion process of task scenes, and also improves the accuracy of evaluating the trainees' own abilities.

Description

Technical Field

[0001] The present invention relates to the technical field of flight simulation, and in particular to a flight simulation training analysis system and method based on big data. Background Art

[0002] The flight simulation training system is designed to meet the needs and challenges of the modern aviation field. It enables users to experience and train real flights in a virtual flight world by simulating various flight scenarios and environmental conditions, thereby improving their flight skills and coping capabilities. The flight simulation training system mainly includes key parts such as the flight control system, the virtual environment system, and the human-computer interaction system. As the "intelligent brain" of the drone, the flight control system is responsible for simulating various flight states and parameters, and adjusting the attitude, speed and position of the aircraft in real time according to the instructions input by the user. The virtual environment system is responsible for simulating various environmental conditions during the flight, such as terrain, weather, etc. The human-computer interaction system provides an interactive interface between the user and the simulation system, allowing the user to easily operate and control the flight simulator.

[0003] Before conducting a flight simulation, the instructor needs to develop a training plan based on the students' abilities, which includes multiple training tasks. The scenarios corresponding to each training task may be different. If the current training task is different from the scenario of the next training task, a scene switch is required. Since the style of each task scenario is different, when switching scenes, sudden changes in the environment will affect the students' perceptions and operational actions, causing the students' feelings to jump out of the simulated scenario, which will affect the entire training result. Simulation training needs to reduce the impact of external factors as much as possible, and students need to be kept in a specific simulated environment at all times to ensure the accuracy of the training results. The instructor's sequencing of training tasks is mostly based on experience, without accurate data support, and it is impossible to reasonably and effectively overcome the impact of switching task scenarios based on the sequencing of training tasks. Summary of the invention

[0004] The purpose of the present invention is to provide a flight simulation training analysis system and method based on big data to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: a flight simulation training analysis method based on big data, the analysis method comprising the following steps:

[0006] Step S1, select a training scenario and input a training plan;

[0007] Step S2, obtaining various training tasks contained in the training plan and the task scenarios corresponding to each training task, and calculating the switching smoothness value between any two task scenarios;

[0008] Step S3: adjusting the order of the training tasks according to the switching smoothing value, generating a new training plan, and pushing it to the user terminal;

[0009] Step S4: Select to use a new training plan or the original training plan. The trainee performs flight training according to the selected training plan, obtains flight records, checks the completion results of each training task, and evaluates the training score.

[0010] Further, the step S1 includes: the training scene includes a three-dimensional scene and a two-dimensional scene, and determining whether the three-dimensional scene or the two-dimensional scene is used in this training;

[0011] Obtain the basic information, flight experience, skill level and training records of the pilots participating in the training, and judge the pilots' personal ability level;

[0012] A training plan is developed and inputted based on training objectives and personal ability level, the training plan including takeoff, flight route, training missions and landing.

[0013] Furthermore, the step S2 comprises:

[0014] Step S201, obtaining various training tasks in the training plan, and the task scenario corresponding to each training task, wherein the task scenario is a scenario of inputting environmental parameters to simulate the actual environment, wherein the environmental parameters include one or more of wind direction, weather, sea surface temperature, and cloud height; if the values ​​of the environmental parameters are different, they are marked as different task scenarios;

[0015] Obtain each task scenario included in the training plan. If the training plan includes two or more task scenarios, go to step S202;

[0016] Step S202: randomly select two mission scenarios, extract all pilots' training plans to form a history database, extract flight records with the conversion process of the two selected mission scenarios in the history database, and use flight records with operation errors in the two converted mission scenarios as target flight records;

[0017] Step S203, divide the two task scenes converted in the target flight record into a pre-task scene and a post-task scene according to the order of execution, obtain the training tasks corresponding to the two task scenes and mark them as target training tasks, obtain all operations of the target training tasks, form a time axis one according to the order of operation execution, mark the time node T1 when the operation error occurs on the time axis one, and mark the two time points of the start and completion of the switching of the two task scenes on the time axis one, and the time between the start and completion of the switching is the conversion period [t1, t2];

[0018] Step S204, classify the target training tasks according to their corresponding predecessor task scenarios or successor task scenarios, extract the flight records of the same type of target training tasks from the historical database, retain the flight records without continuous switching task scenarios before and after the target training tasks to form a set A, extract the target training tasks with operation errors in the set A, form the execution process of the target training tasks into a time axis 2, mark the time nodes where the operation errors occur for each target training task on the time axis 2, take the two most distant adjacent time nodes as endpoints, and obtain the time period [t3, t4];

[0019] Step S205, respectively mark the time periods [t3, t4] corresponding to the pre-task scenario and the post-task scenario on the time axis 1, obtain the time period [t3, t4] and mark the time period between the switching node as the target time period, extract the target flight records in which the operation errors occur in step S202 and are within the target time period, and calculate the switching influence factor α within the target time period, and the calculation formula is α=m / M; wherein m is the number of target flight records with operation errors in the target time period, and M is the total number of target flight records with all operation errors that occur in the pre-task scenario and the post-task scenario;

[0020] Step S206, obtaining the switching duration between two mission scenes of each target flight record, marking it as s, wherein the switching duration is the duration of switching from the previous mission scene to the next mission scene, extracting all the switching durations to form a set S, the set S={s1,s2,s3,......,sn}, wherein s1,s2,s3,......,sn respectively represent the switching duration of the two scenes in the first target flight record, the switching duration of the two scenes in the second target flight record, the switching duration of the two scenes in the third target flight record,......, the switching duration of the two scenes in the nth target flight record;

[0021] Calculate the switching smoothness value between the two selected task scenes, and record the switching smoothness value as P;

[0022] The calculation formula is: , where β1 and β2 are weight coefficients.

[0023] Furthermore, step S3 includes: obtaining various training tasks in the training plan, and if there is no fixed specified order, sorting them in descending order according to the switching smoothness values ​​between the training tasks, wherein the arrangement process is: extracting the two task scenes corresponding to the highest switching smoothness values, arranging the two task scenes according to the preceding task scenes and the following task scenes divided in step S2, and then taking the following task scene as a marking point, continuing to calculate the switching smoothness value between it and the remaining task scenes, extracting the highest switching smoothness values ​​in turn for arrangement, and forming a new training plan.

[0024] A flight simulation training analysis system based on big data, which is applied to a flight simulation training analysis method based on big data, the analysis system includes an input module, a conversion analysis module, a sorting module and a training evaluation module;

[0025] The input module is used to select a training scenario and input a training plan;

[0026] The conversion analysis module is used to obtain various training tasks contained in the training plan, as well as the task scenarios corresponding to each training task, and calculate the switching smoothness value between any two task scenarios;

[0027] The sorting module is used to adjust the sorting of training tasks according to the switching smoothing value, generate a new training plan, and push it to the user terminal;

[0028] The training evaluation module selects a new training plan or an original training plan, and the trainee performs flight training according to the selected training plan, obtains flight records, checks the completion results of each training task, and evaluates the training score;

[0029] The output end of the input module is electrically connected to the input end of the conversion analysis module, the output end of the conversion analysis module is electrically connected to the input end of the sorting module, and the input end of the sorting module is electrically connected to the output end of the input module.

[0030] Further, the input module includes a scene selection unit, an information collection unit and a formulation unit;

[0031] The scene selection unit is used to determine whether a three-dimensional scene or a two-dimensional scene is used for this training;

[0032] The information collection unit is used to obtain the basic information, flight experience, skill level and training records of the pilots participating in the training, and to determine the individual ability level of the pilots;

[0033] The formulation unit is used to formulate and input a training plan according to the training objectives and personal ability level, wherein the training plan includes take-off, flight route, training tasks and landing.

[0034] Further, the conversion analysis module includes a switching impact factor calculation unit, a switching duration unit and a switching smoothing value calculation unit;

[0035] The switching impact factor calculation unit is used to randomly select two mission scenarios, extract flight records with the conversion process of the two selected mission scenarios in the historical database, and use the flight records with operation errors in the two converted mission scenarios as target flight records; obtain a target time period containing a switching node; extract the target flight records with operation errors in the target time period, and calculate the switching impact factor in the target time period;

[0036] The switching duration unit is used to calculate the average switching duration of switching between two mission scenarios in all target flight records;

[0037] The switching smoothness value calculation unit is used to calculate the switching smoothness value between two task scenes according to the average value of the switching impact factor and the switching duration.

[0038] Furthermore, the sorting module includes a first-place determination unit and a sequential arrangement unit; the first-place determination unit is used to extract the two task scenarios corresponding to the highest switching smoothness values, and arrange the two task scenarios according to the preceding task scenarios and the following task scenarios divided in step S2; the sequential arrangement unit is used to use the following task scenario as a marking point, continue to calculate the switching smoothness value between it and the remaining task scenarios, extract the highest switching smoothness values ​​in turn for arrangement, and form a new training plan.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] 1. The present invention monitors the data in the flight simulation training process, collects and analyzes the training task data after switching the task scene, analyzes the switching smoothness value between the two task scenes, arranges the training tasks in the training plan according to the switching smoothness value, and forms a personalized training plan. By reasonably planning the conversion process of the task scene, the training plan of the trainees is avoided from being affected by the switching of the task scene, and the accuracy of the assessment of the trainees' own abilities is also improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 The present invention is a flowchart of a flight simulation training analysis method based on big data. DETAILED DESCRIPTION

[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0043] Example: Figure 1 As shown, the present invention provides a flight simulation training analysis method based on big data, and the analysis method comprises the following steps:

[0044] Step S1, select a training scenario and input a training plan;

[0045] The step S1 includes: the training scene includes a three-dimensional scene and a two-dimensional scene, and determining whether the three-dimensional scene or the two-dimensional scene is used in this training;

[0046] Obtain the basic information, flight experience, skill level and training records of the pilots participating in the training, and judge the pilots' personal ability level;

[0047] A training plan is developed and inputted based on training objectives and personal ability level, the training plan including takeoff, flight route, training missions and landing.

[0048] Step S2, obtaining various training tasks contained in the training plan and the task scenarios corresponding to each training task, and calculating the switching smoothness value between any two task scenarios;

[0049] The step S2 comprises:

[0050] Step S201, obtaining various training tasks in the training plan, and the task scenario corresponding to each training task, wherein the task scenario is a scenario of inputting environmental parameters to simulate the actual environment, wherein the environmental parameters include one or more of wind direction, weather, sea surface temperature, and cloud height; if the values ​​of the environmental parameters are different, they are marked as different task scenarios;

[0051] Obtain each task scenario included in the training plan. If the training plan includes two or more task scenarios, go to step S202;

[0052] Step S202: randomly select two mission scenarios, extract all pilots' training plans to form a history database, extract flight records with the conversion process of the two selected mission scenarios in the history database, and use flight records with operation errors in the two converted mission scenarios as target flight records;

[0053] Step S203, divide the two task scenes converted in the target flight record into a pre-task scene and a post-task scene according to the order of execution, obtain the training tasks corresponding to the two task scenes and mark them as target training tasks, obtain all operations of the target training tasks, form a time axis one according to the order of operation execution, mark the time node T1 when the operation error occurs on the time axis one, and mark the two time points of the start and completion of the switching of the two task scenes on the time axis one, and the time between the start and completion of the switching is the conversion period [t1, t2];

[0054] Step S204, classify the target training tasks according to their corresponding predecessor task scenarios or successor task scenarios, extract the flight records of the same type of target training tasks from the historical database, retain the flight records without continuous switching task scenarios before and after the target training tasks to form a set A, extract the target training tasks with operation errors in the set A, form the execution process of the target training tasks into a time axis 2, mark the time nodes where the operation errors occur for each target training task on the time axis 2, take the two most distant adjacent time nodes as endpoints, and obtain the time period [t3, t4];

[0055] Step S205, respectively mark the time periods [t3, t4] corresponding to the pre-task scenario and the post-task scenario on the time axis 1, obtain the time period [t3, t4] and mark the time period between the switching node as the target time period, extract the target flight records in which the operation errors occur in step S202 and are within the target time period, and calculate the switching influence factor α within the target time period, and the calculation formula is α=m / M; wherein m is the number of target flight records with operation errors in the target time period, and M is the total number of target flight records with all operation errors that occur in the pre-task scenario and the post-task scenario;

[0056] Step S206, obtaining the switching duration between two mission scenes of each target flight record, marking it as s, wherein the switching duration is the duration of switching from the previous mission scene to the next mission scene, extracting all the switching durations to form a set S, the set S={s1,s2,s3,......,sn}, wherein s1,s2,s3,......,sn respectively represent the switching duration of the two scenes in the first target flight record, the switching duration of the two scenes in the second target flight record, the switching duration of the two scenes in the third target flight record,......, the switching duration of the two scenes in the nth target flight record;

[0057] Calculate the switching smoothness value between the two selected task scenes, and record the switching smoothness value as P;

[0058] The calculation formula is: , where β1 and β2 are weight coefficients.

[0059] Step S3: adjusting the order of the training tasks according to the switching smoothing value, generating a new training plan, and pushing it to the user terminal;

[0060] The step S3 comprises: obtaining each training task in the training plan, and if there is no fixed specified order, sorting them in descending order according to the switching smoothness values ​​between the training tasks, wherein the arrangement process is: extracting the two task scenes corresponding to the highest switching smoothness values, arranging the two task scenes according to the preceding task scenes and the following task scenes divided in step S2, and then taking the following task scenes as marking points, continuing to calculate the switching smoothness values ​​between them and the remaining task scenes, extracting the highest switching smoothness values ​​in turn for arrangement, and forming a new training plan.

[0061] Step S4: Select to use a new training plan or the original training plan. The trainee performs flight training according to the selected training plan, obtains flight records, checks the completion results of each training task, and evaluates the training score.

[0062] A flight simulation training analysis system based on big data, which is applied to a flight simulation training analysis method based on big data, the analysis system includes an input module, a conversion analysis module, a sorting module and a training evaluation module;

[0063] The output end of the input module is electrically connected to the input end of the conversion analysis module, the output end of the conversion analysis module is electrically connected to the input end of the sorting module, and the input end of the sorting module is electrically connected to the output end of the input module.

[0064] The input module is used to select a training scenario and input a training plan;

[0065] The input module includes a scene selection unit, an information collection unit and a formulation unit;

[0066] The scene selection unit is used to determine whether a three-dimensional scene or a two-dimensional scene is used for this training;

[0067] The information collection unit is used to obtain the basic information, flight experience, skill level and training records of the pilots participating in the training, and to determine the individual ability level of the pilots;

[0068] The formulation unit is used to formulate and input a training plan according to the training objectives and personal ability level, wherein the training plan includes take-off, flight route, training tasks and landing.

[0069] The conversion analysis module is used to obtain various training tasks contained in the training plan, as well as the task scenarios corresponding to each training task, and calculate the switching smoothness value between any two task scenarios;

[0070] The conversion analysis module includes a switching impact factor calculation unit, a switching duration unit and a switching smoothing value calculation unit;

[0071] The switching impact factor calculation unit is used to randomly select two mission scenarios, extract flight records with the conversion process of the two selected mission scenarios in the historical database, and use the flight records with operation errors in the two converted mission scenarios as target flight records; obtain a target time period containing a switching node; extract the target flight records with operation errors in the target time period, and calculate the switching impact factor in the target time period;

[0072] The switching duration unit is used to calculate the average switching duration of switching between two mission scenarios in all target flight records;

[0073] The switching smoothness value calculation unit is used to calculate the switching smoothness value between two task scenes according to the average value of the switching impact factor and the switching duration.

[0074] The sorting module is used to adjust the sorting of training tasks according to the switching smoothing value, generate a new training plan, and push it to the user terminal;

[0075] The sorting module includes a first-place determination unit and a sequential arrangement unit; the first-place determination unit is used to extract the two task scenes corresponding to the highest switching smoothness values, and arrange the two task scenes according to the preceding task scenes and the following task scenes divided in step S2; the sequential arrangement unit is used to use the following task scenes as marking points, continue to calculate the switching smoothness values ​​between them and the remaining task scenes, extract the highest switching smoothness values ​​in turn, and arrange them to form a new training plan.

[0076] The training evaluation module selects to use a new training plan or an original training plan. The trainees perform flight training according to the selected training plan, obtain flight records, view the completion results of each training task, and evaluate the training scores.

[0077] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A flight simulation training analysis method based on big data, characterized by: The analytical method comprises the following steps: Step S1, select a training scenario and input a training plan; Step S2, obtaining various training tasks contained in the training plan and the task scenarios corresponding to each training task, and calculating the switching smoothness value between any two task scenarios; Step S3: adjusting the order of the training tasks according to the switching smoothing value, generating a new training plan, and pushing it to the user terminal; Step S4: Select a new training plan or the original training plan, and the trainee performs flight training according to the selected training plan, obtains flight records, checks the completion results of each training task, and evaluates the training score; The step S1 includes: the training scene includes a three-dimensional scene and a two-dimensional scene, and determining whether the three-dimensional scene or the two-dimensional scene is used in this training; Obtain the basic information, flight experience, skill level and training records of the pilots participating in the training, and judge the pilots' personal ability level; Develop and input a training plan based on training objectives and personal ability level, the training plan including takeoff, flight route, training missions and landing; The step S2 comprises: Step S201, obtaining various training tasks in the training plan, and the task scenario corresponding to each training task, wherein the task scenario is a scenario of inputting environmental parameters to simulate the actual environment, wherein the environmental parameters include one or more of wind direction, weather, sea surface temperature, and cloud height; if the values ​​of the environmental parameters are different, they are marked as different task scenarios; Obtain each task scenario included in the training plan. If the training plan includes two or more task scenarios, go to step S202; Step S202: randomly select two mission scenarios, extract all pilots' training plans to form a history database, extract flight records with the conversion process of the two selected mission scenarios in the history database, and use flight records with operation errors in the two converted mission scenarios as target flight records; Step S203, divide the two task scenes converted in the target flight record into a pre-task scene and a post-task scene according to the order of execution, obtain the training tasks corresponding to the two task scenes and mark them as target training tasks, obtain all operations of the target training tasks, form a time axis one according to the order of operation execution, mark the time node T1 when the operation error occurs on the time axis one, and mark the two time points of the start and completion of the switching of the two task scenes on the time axis one, and the time between the start and completion of the switching is the conversion period [t1, t2]; Step S204, classify the target training tasks according to their corresponding predecessor task scenarios or successor task scenarios, extract the flight records of the same type of target training tasks from the historical database, retain the flight records without continuous switching task scenarios before and after the target training tasks to form a set A, extract the target training tasks with operation errors in the set A, form the execution process of the target training tasks into a time axis 2, mark the time nodes where the operation errors occur for each target training task on the time axis 2, take the two most distant adjacent time nodes as endpoints, and obtain the time period [t3, t4]; Step S205, respectively mark the time periods [t3, t4] corresponding to the pre-task scenario and the post-task scenario on the time axis 1, obtain the time period [t3, t4] and mark the time period between the switching node as the target time period, extract the target flight records in which the operation errors occur in step S202 and are within the target time period, and calculate the switching influence factor α within the target time period, and the calculation formula is α=m / M; wherein m is the number of target flight records with operation errors in the target time period, and M is the total number of target flight records with all operation errors that occur in the pre-task scenario and the post-task scenario; Step S206, obtaining the switching duration between two mission scenes of each target flight record, marking it as s, wherein the switching duration is the duration of switching from the previous mission scene to the next mission scene, extracting all the switching durations to form a set S, the set S={s1,s2,s3,......,sn}, wherein s1,s2,s3,......,sn respectively represent the switching duration of the two scenes in the first target flight record, the switching duration of the two scenes in the second target flight record, the switching duration of the two scenes in the third target flight record,......, the switching duration of the two scenes in the nth target flight record; Calculate the switching smoothness value between the two selected task scenes, and record the switching smoothness value as P; The calculation formula is: P = ( *β1)*[( )*β2], where β1 and β2 are weight coefficients.

2. The flight simulation training analysis method based on big data according to claim 1, characterized in that: The step S3 comprises: obtaining each training task in the training plan, and if there is no fixed specified order, sorting them in descending order according to the switching smoothness values ​​between the training tasks, wherein the arrangement process is: extracting the two task scenes corresponding to the highest switching smoothness values, arranging the two task scenes according to the preceding task scenes and the following task scenes divided in step S2, and then taking the following task scenes as marking points, continuing to calculate the switching smoothness values ​​between them and the remaining task scenes, extracting the highest switching smoothness values ​​in turn for arrangement, and forming a new training plan.

3. A flight simulation training analysis system based on big data, which is applied to a flight simulation training analysis method based on big data as described in any one of claims 1-2, characterized in that: The analysis system includes an input module, a conversion analysis module, a sorting module and a training evaluation module; The input module is used to select a training scenario and input a training plan; The conversion analysis module is used to obtain various training tasks contained in the training plan, as well as the task scenarios corresponding to each training task, and calculate the switching smoothness value between any two task scenarios; The sorting module is used to adjust the sorting of training tasks according to the switching smoothing value, generate a new training plan, and push it to the user terminal; The training evaluation module selects a new training plan or an original training plan, and the trainee performs flight training according to the selected training plan, obtains flight records, checks the completion results of each training task, and evaluates the training score; The output end of the input module is electrically connected to the input end of the conversion analysis module, the output end of the conversion analysis module is electrically connected to the input end of the sorting module, and the input end of the sorting module is electrically connected to the output end of the input module.

4. The flight simulation training analysis system based on big data according to claim 3 is characterized in that: The input module includes a scene selection unit, an information collection unit and a formulation unit; The scene selection unit is used to determine whether a three-dimensional scene or a two-dimensional scene is used for this training; The information collection unit is used to obtain the basic information, flight experience, skill level and training records of the pilots participating in the training, and to determine the individual ability level of the pilots; The formulation unit is used to formulate and input a training plan according to the training objectives and personal ability level, wherein the training plan includes take-off, flight route, training tasks and landing.

5. The flight simulation training analysis system based on big data according to claim 3 is characterized in that: The conversion analysis module includes a switching impact factor calculation unit, a switching duration unit and a switching smoothing value calculation unit; The switching impact factor calculation unit is used to randomly select two mission scenarios, extract flight records with the conversion process of the two selected mission scenarios in the historical database, and use the flight records with operation errors in the two converted mission scenarios as target flight records; obtain a target time period containing a switching node; extract the target flight records with operation errors in the target time period, and calculate the switching impact factor in the target time period; The switching duration unit is used to calculate the average switching duration of switching between two mission scenarios in all target flight records; The switching smoothness value calculation unit is used to calculate the switching smoothness value between two task scenes according to the average value of the switching impact factor and the switching duration.

6. The flight simulation training analysis system based on big data according to claim 3 is characterized by: The sorting module includes a first-place determination unit and a sequential arrangement unit; the first-place determination unit is used to extract the two task scenes corresponding to the highest switching smoothness values, and arrange the two task scenes according to the preceding task scenes and the following task scenes divided in step S2; the sequential arrangement unit is used to use the following task scenes as marking points, continue to calculate the switching smoothness values ​​between them and the remaining task scenes, extract the highest switching smoothness values ​​in turn, and arrange them to form a new training plan.

Images