Warplane take-off and landing training identification classification and stage division method

Abstract

The invention provides a fighter take-off and landing training recognition, classification and stage division method for solving the practical problem that segmentation, extraction and stage division are not easy due to fusion of fighter take-off and landing training and other flight training. The method comprises the following steps: preliminarily extracting fighter take-off and landing training flight parameter data according to a height threshold value, and determining a starting point and an ending point; according to the height and speed of the starting point and the ending point, further dividing into two classes of special training and other training take-off and landing stages; searching a height minimum value point, and further segmenting the identified two types of take-off and landing training flight parameter data into single take-off and landing training; the course angle, the roll angle, the height and the duration are utilized to divide single-sortie take-off and landing training into five stages of a take-off and landing route. The method has the advantages that (1) taking-off and landing training in various complex training flight parameters can be quickly extracted and is cut into single-sortie training data; (2) taking-off and landing stages in special taking-off and landing training and other training of a fighter can be automatically distinguished, and a taking-off and landing route is automatically divided into five stages.

Description

Technical Field

[0001] The invention belongs to the technical field of intelligent processing of flight parameter data and flight phase division, and specifically relates to a method for identifying, classifying and phase division of fighter aircraft take-off and landing training. Background Art

[0002] Fighter aircraft take-off and landing training is the basis for flight trainees to conduct other technical and tactical flight training, and is one of the keys to cultivating trainees' basic flight control skills. Currently, fighter aircraft take-off and landing training mainly includes two types: one is special take-off and landing training carried out in the early stage of trainees' flight training, and the other is to integrate take-off and landing training into other daily flight training subjects after trainees have basic take-off and landing capabilities, so as to continuously consolidate and improve trainees' take-off and landing control skills through regular training.

[0003] The take-off and landing routes of fighter jets are similar to those of civil aircraft. The five sides from take-off (or return) to landing can be divided into five stages: one side, two sides, three sides, four sides and five sides. The difference is that, first, the current fighter take-off and landing training mostly uses elliptical routes rather than the rectangular routes of civil aviation, that is, the two-side and four-side routes are actually a process of continuous turning; second, the requirements for fixed-point landing of fighter jets are higher, and the requirements for route maintenance accuracy are stricter. Specifically, the requirements for maintaining parameters such as heading angle, roll angle, and segment timing are more stringent.

[0004] At present, the assessment method for fighter take-off and landing training still mainly relies on subjective evaluation by flight instructors based on the standards of take-off and landing routes. This method is highly subjective and has low utilization of flight data. Identifying, classifying and dividing the stages of fighter take-off and landing training is the primary prerequisite for effectively carrying out objective and intelligent evaluation based on flight data, which is of great significance for scientific analysis and evaluation of pilot driving skills.

[0005] The existing method for dividing the flight phases of take-off and landing routes mainly focuses on the key flight parameter threshold judgment state transition points in the civil aviation take-off and landing flight parameter data to achieve automatic segmentation of the take-off and landing routes. The main shortcomings of this method when applied to the division of the take-off and landing phases of fighter aircraft are as follows: (1) The division method is mainly based on the flight parameter data of the civil aviation take-off and landing phases, while the actual flight training subjects of fighter aircraft are more complex and diverse. The existing method lacks the ability to identify and extract the take-off and landing training flight parameters from the diverse flight parameter data; (2) Fighter take-off and landing training includes two types, and the existing method lacks the ability to classify and judge the two types; (3) The types and standards of fighter take-off and landing routes are significantly different from those of civil aviation, and there are higher requirements for the accuracy of route maintenance, which cannot be met by the existing method. Therefore, a method for identifying, classifying and dividing the phases of fighter take-off and landing training is needed to provide technical support for the scientific evaluation of the take-off and landing skill level of trainees. Summary of the invention

[0006] The technical problem to be solved by the present invention is to provide a method for identifying, classifying and dividing stages of fighter take-off and landing training in response to the above-mentioned deficiencies in the prior art, so as to solve the technical problems of identifying, classifying and accurately dividing the take-off and landing data under the diversified flight training parameter data of fighter aircraft.

[0007] The invention discloses a method for identifying, classifying and dividing fighter aircraft take-off and landing training into stages, which is special in that it comprises the following steps:

[0008] (1) Using a computer, preliminarily extract all flight parameter data including fighter take-off and landing training according to the altitude threshold, and determine the starting point and the ending point;

[0009] (2) Based on the altitude, speed, and heading angle of the starting and ending points, takeoff and landing training is further divided into two categories: special training and other training takeoff and landing stages;

[0010] (3) For special take-off and landing training, search for the minimum altitude point and further divide the take-off and landing training flight parameter data into single-flight take-off and landing training data;

[0011] (4) Using heading angle, roll angle, altitude and time, a single takeoff and landing training is finally divided into five stages of the take-off and landing route.

[0012] As a further technical solution, the step (1) identifies and extracts the take-off and landing training in the diversified flight training flight parameter data, and the specific steps are as follows:

[0013] (1.1) Use a computer to extract the relative pressure altitude from the flight parameter data (this parameter is highly reliable and generally does not have missing values), find the missing values, and fill them with the average of the two adjacent values. Determine the altitude threshold H for fighter takeoff and landing training according to the training outline t ;

[0014] (1.2) According to the relative pressure height H <H t Take-off and landing training judgment criteria, extract all H <H t Flight parameter data index;

[0015] (1.3) Determine whether the flight parameter data index values ​​are continuous, and preliminarily determine the first and last values ​​of the continuous flight parameter data indexes as the first and last endpoint indexes of the take-off and landing training flight parameter segment;

[0016] (1.4) Determine whether the relative pressure altitude of the end point of the take-off and landing training flight parameter data segment extracted in (1.3) is less than 10. If it is greater than 10, remove the segment from the take-off and landing training flight parameter segment, and finally extract the take-off and landing training flight parameter data. Wherein, k represents the number of parameters, and n represents the length of the time series of the take-off and landing training flight parameters.

[0017] As a further technical solution, the step (2) divides the take-off and landing training flight parameter data into a special training data set F T And other training take-off and landing phase datasets F L , the specific steps are as follows:

[0018] (2.1) Determine the flight parameters for take-off and landing training The starting heading angle Is it consistent with the heading angle of the airport runway? If they are not consistent, search frame by frame backward for the point where the heading angle is consistent with the heading angle of the airport runway, and determine whether the duration of the continuous consistent points is greater than 10s. If the condition is met, the initial value of the take-off and landing training flight parameter segment is further refined to the initial point where the heading angle is consistent with the heading angle of the airport runway. If the condition is not met, the segment is discarded.

[0019] (2.2) Determine the relative pressure height H of the starting point s <10, if true, the segment is divided into the take-off and landing special training data set F T ;

[0020] (2.3) Determine the relative pressure height H of the starting point s >10, if true, further determine whether the starting point indicated empty space meets the return landing entry point speed condition V in , if true, it will be divided into other training take-off and landing phase data sets F L .

[0021] As a further technical solution, the step (3) further divides the take-off and landing training flight parameter data into single-flight take-off and landing data (mainly for the special training data set F T , F L It is single flight data), the specific steps are as follows:

[0022] (3.1) Set the low height threshold H d =50, extract relative pressure height H <H d Flight parameter data fragment;

[0023] (3.2) Search H <H d The minimum value in the flight parameter data segment is used as the segmentation point of the single take-off and landing training, and the take-off and landing training flight parameter data is further segmented into single take-off and landing training data F Ti .

[0024] As a further technical solution, the step (4) further divides the single take-off and landing route into five-side route data to complete the fine segmentation of the take-off and landing training flight parameter data, specifically including:

[0025] (4.1) From the initial value of the single takeoff and landing training flight parameter data, search frame by frame for the point where the roll angle φ>20, take it as the end point of one side, and extract one side of the takeoff and landing route;

[0026] (4.2) From one end point, search backward frame by frame for the case where the roll angle φ is less than 2 and the heading angle The point opposite to the heading of one side is taken as the end point of the two sides, and the two sides of the take-off and landing route are extracted;

[0027] (4.3) From the end point of the two sides, search backward frame by frame for the point where the roll angle φ>20, take it as the end point of the three sides, and extract the three sides of the take-off and landing pattern;

[0028] (4.4) From the three-side endpoint, search backward frame by frame for the roll angle φ < 2 and the heading angle The point that is consistent with the heading of the airport runway is taken as the end point of the four sides to extract the four sides of the take-off and landing route;

[0029] (4.3) From the four end points, search for the ground speed V frame by frame d <40, take it as the final end point and extract the fifth side of the take-off and landing pattern.

[0030] The technical solution provided by the present invention has at least the following beneficial effects:

[0031] 1. The present invention can quickly identify the take-off and landing training data in the flight parameter data of the diversified flight training subjects of fighter aircraft, and divide the data into special training data sets and other training take-off and landing stage data sets, so as to facilitate the subsequent take-off and landing flight training evaluation under different benchmark conditions.

[0032] 2. The present invention can accurately divide the fighter flight parameter data containing multiple take-off and landing training sorties into single-sort flight parameter data.

[0033] 3. The method for dividing the fighter take-off and landing training route into stages proposed in the present invention can quickly divide the flight parameter data of a single sortie into the five sides of the fighter aircraft's elliptical take-off and landing route, and is suitable for a variety of different fighter aircraft models and land-based simulated landing training, and has broad engineering application prospects.

[0034] In summary, the method for identifying, classifying and dividing stages of fighter take-off and landing training provided by the present invention realizes the function of automatically identifying take-off and landing training from the diversified flight training flight parameter data of fighter aircraft and performing classification and stage division. It has the advantages of being automatic, accurate, efficient and universal, and can be widely used in tasks such as take-off and landing route identification, extraction, segment division and training evaluation in the field of military aviation. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 The present invention is a general flow chart of a method for identifying, classifying and dividing stages of fighter aircraft take-off and landing training;

[0036] Figure 2 A schematic diagram of a method for classifying and dividing fighter aircraft take-off and landing training into stages according to an embodiment of the present invention;

[0037] Figure 3 This is a flow chart of step (1) of an embodiment of the present invention;

[0038] Figure 4 This is a flow chart of step (2) of an embodiment of the present invention;

[0039] Figure 5 This is a flow chart of step (3) of an embodiment of the present invention;

[0040] Figure 6 This is a flow chart of step (4) of an embodiment of the present invention;

[0041] Figure 7 The five-side division result of a single-flight special takeoff and landing training according to an embodiment of the present invention;

[0042] Figure 8 This is a five-side division result of another training take-off and landing phase in an embodiment of the present invention. DETAILED DESCRIPTION

[0043] Example

[0044] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0045] like Figure 1 As shown, an embodiment of the present invention provides a method for identifying, classifying and dividing fighter aircraft take-off and landing training. And other training flight parameter data For example, the heading of its resident airport The fighter aircraft take-off and landing training classification and stage division method of this embodiment is as follows: Figure 2 As shown, the main steps include:

[0046] like Figure 3 As shown, step (1) identifies and extracts the take-off and landing training in the diversified flight training flight parameter data, and the specific steps are as follows:

[0047] (1.1) Import complete flight parameter data, including GPS coordinates, pitch angle, roll angle, heading angle, angle of attack, relative pressure altitude, speed, acceleration and other flight parameters. It should be emphasized that these specific index parameters do not limit the protection scope of this application. Extract the relative pressure altitude H, find the missing value, and use Fill in and determine the height threshold H for take-off and landing training of a certain type of fighter according to the training outline t =420;

[0048] (1.2) According to the relative pressure height H <H t Take-off and landing training judgment criteria, extract all H <H t Flight parameter data index;

[0049] (1.3) Determine whether the flight parameter data index value is continuous, and preliminarily determine the first and last values ​​of the continuous flight parameter data index as the first and last endpoint indexes i of the take-off and landing training flight parameter segment s ,i e ;

[0050] (1.4) Determine the relative pressure altitude H of the end point of the take-off and landing training flight parameter data segment extracted in (1.3) end If it is less than 10, remove the H in the take-off and landing training flight parameter segment end ≥10 segments, finally extracting the take-off and landing training flight parameter data Wherein, k represents the number of parameters, and n represents the length of the time series of the take-off and landing training flight parameters.

[0051] like Figure 4 As shown in step (2), the take-off and landing training flight parameter data is divided into a special training data set F T And other training take-off and landing phase datasets F L , the specific steps are as follows:

[0052] (2.1) Determine the interception of step (1) Is the heading angle of the starting point consistent with the heading angle of the airport runway? If they are not consistent, search frame by frame for the point where the heading angle is consistent with the airport runway heading angle, and determine whether the duration of the continuous consistent points is greater than 10s. If the condition is met, the initial value of the take-off and landing training flight parameter segment is further refined to the initial point where the heading angle is consistent with the airport runway heading angle, that is, If the condition is not met, the fragment is removed;

[0053] (2.2) Determine the relative pressure height H of the starting point is <10, if true, the segment is divided into the take-off and landing special training data set F T ;

[0054] (2.3) Determine the relative pressure height H of the starting point is >10, if true, further determine whether the starting point indicated empty space meets the return landing entry point speed condition V in , V in Determined according to the outline of different models, in this example, V in =450. It should be emphasized that these specific index parameters do not limit the protection scope of this application. If established, it will be divided into other training take-off and landing phase data sets F L .

[0055] like Figure 5 As shown in the figure, step (3) further divides the take-off and landing training flight parameter data into single take-off and landing data (mainly for the special training data set F T , F L It is single flight data), the specific steps are as follows:

[0056] (3.1) Set the low height threshold H d =50, extract relative pressure height H <H d Flight parameter data fragment;

[0057] (3.2) Search H <H d The minimum value in the flight parameter data segment is used as the segmentation point of the single take-off and landing training, and the take-off and landing training flight parameter data is further segmented into single take-off and landing training data F Ti .

[0058] like Figure 6 As shown, step (4) further divides the single take-off and landing route into the final route data, completing the fine segmentation of the take-off and landing training flight parameter data, specifically including:

[0059] (4.1) From the initial value i of the single takeoff and landing training flight parameter data s1 = i0, search backward frame by frame for the point where the roll angle φ>20 and use it as the end point of one side Extract one side of the traffic pattern;

[0060] (4.2) Change i s2 =i e1 +1 as the starting point of the two sides, and search backward frame by frame for the roll angle φ<2 and point, and use it as the end point of the two sides i e2 , extract the two sides of the take-off and landing pattern;

[0061] (4.3) Change i s3 =i e2 +1 as the starting point of the three sides, and search backward frame by frame for the point where the roll angle φ>20, and use it as the end point of the three sides i e3 , extract the three sides of the take-off and landing pattern;

[0062] (4.4) Change i s4 =i e3 +1 is used as the starting point of the four sides, and the roll angle φ<2 and the heading angle are searched backward frame by frame. The point is taken as the end point of the four sides i e4 , extract the four sides of the take-off and landing pattern;

[0063] (4.3) Change i s5 =i e4 +1 is used as the starting point of the fifth side, and the ground speed V is found backward frame by frame. d <40, take it as the end point of the five sides i e5 , extract the final leg of the pattern.

[0064] According to the above steps, the five-side division result of a single takeoff and landing special training in one embodiment of the present invention is as follows: Figure 7 As shown, the five-side division results of other training take-off and landing stages of one embodiment of the present invention are as follows Figure 8 shown.

[0065] Based on the multi-dimensional flight parameter data of fighter flight training, the present invention proposes a method for identifying, classifying and dividing the take-off and landing training of fighters, aiming to automatically identify, extract and classify the take-off and landing training data from the diversified flight parameter data of fighter flight training. First, the relative pressure altitude is selected as an indicator to preliminarily screen the take-off and landing training data, and the entire flight parameter data is cut and extracted for take-off and landing training in combination with the criterion of sequence continuity; then, a comprehensive judgment is made based on the starting point altitude, speed and heading angle to classify the take-off and landing training data; secondly, the idea of ​​divide and conquer is adopted, and the low altitude threshold is used as the judgment criterion to extract the low altitude segment, and then the minimum value of the low altitude segment is searched to further divide the take-off and landing training data into single-flight data; finally, the take-off and landing training data is divided into stages according to the heading angle, roll angle, ground speed and other information. This method can quickly realize the identification, extraction and stage division of the take-off and landing training flight parameter data, and is applicable to a variety of different military aircraft models, with broad engineering application prospects.

[0066] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for identifying, classifying and dividing stages of fighter aircraft take-off and landing training, characterized in that: The method comprises the following steps: (1) Using a computer, preliminarily extract all flight parameter data including fighter take-off and landing training according to the altitude threshold, and determine the starting point and the ending point; (2) Based on the altitude, speed, and heading angle of the starting and ending points, takeoff and landing training is further divided into two categories: special training and other training takeoff and landing stages; (3) For special take-off and landing training, search for the minimum altitude point and further divide the take-off and landing training flight parameter data into single-flight take-off and landing training data; (4) Using heading angle, roll angle, altitude and time, a single takeoff and landing training is finally divided into five stages of the take-off and landing route.

2. The method for identifying, classifying and dividing fighter aircraft take-off and landing training according to claim 1 is characterized in that: The step (1) of preliminarily extracting all flight parameter data including fighter take-off and landing training according to the altitude threshold and determining the starting point and the ending point specifically includes: (1.1) Extract the relative pressure altitude from the flight data and determine the altitude threshold H for fighter take-off and landing training t ; (1.2) According to the relative pressure height H <H t Take-off and landing training judgment criteria, extract all H <H t Flight parameter data index; (1.3) Determine whether the flight parameter data index values ​​are continuous, and preliminarily determine the first and last values ​​of the continuous flight parameter data indexes as the first and last endpoint indexes of the take-off and landing training flight parameter segment; (1.4) Determine whether the relative pressure altitude of the end point of the take-off and landing training flight parameter segment extracted in (1.3) is less than 10. If it is greater than 10, remove the segment from the take-off and landing training flight parameter segment.

3. The method for identifying, classifying and dividing fighter aircraft take-off and landing training according to claim 1 is characterized in that: In step (2), according to the heading angle, altitude, and speed of the starting point and the ending point, the take-off and landing training is further divided into two categories: special training and other training take-off and landing stages, specifically including: (2.1) Determine whether the heading angle of the starting point is consistent with the heading angle of the airport runway. If not, search frame by frame for the point where the heading angle is consistent with the heading angle of the airport runway, and determine whether the duration of the continuous consistent points is greater than 10 seconds. If the condition is met, the initial value of the take-off and landing training flight parameter segment is further refined to the initial point where the heading angle is consistent with the heading angle of the airport runway. If the condition is not met, the segment is discarded. (2.2) Determine the relative pressure height H of the starting point s <10, if true, the segment is classified into the take-off and landing special training data set; (2.3) Determine the relative pressure height H of the starting point s >10. If so, further determine whether the indicated airspace at the starting point meets the return landing entry point speed condition. If so, divide it into other training takeoff and landing phase data sets.

4. The method for identifying, classifying and dividing stages of fighter aircraft take-off and landing training according to claim 1, characterized in that: In step (3), for the special take-off and landing training, searching for the altitude minimum point and further dividing the take-off and landing training flight parameter data into single-flight take-off and landing training data specifically includes: (3.1) Set the low height threshold H d =50, extract relative pressure height H <H d Flight parameter data fragment; (3.2) Search H <H d The minimum value in the flight parameter data segment is taken, and the minimum value point is used as the segmentation point for single take-off and landing training, and the take-off and landing training flight parameter data is further segmented into single take-off and landing training data.

5. The method for identifying, classifying and dividing stages of fighter aircraft take-off and landing training according to claim 1 is characterized in that: In step (4), the key flight parameter data such as heading angle, roll angle, altitude, time, etc. are used to finally divide the single take-off and landing training into five stages of the take-off and landing route, specifically including: (4.1) From the initial value of the single takeoff and landing training flight parameter data, search frame by frame for the point where the roll angle φ>20, take it as the end point of one side, and extract one side of the takeoff and landing route; (4.2) From one end point, search backward frame by frame for the case where the roll angle φ is less than 2 and the heading angle The point opposite to the heading of one side is taken as the end point of the two sides, and the two sides of the take-off and landing route are extracted; (4.3) From the end point of the two sides, search backward frame by frame for the point where the roll angle φ>20, take it as the end point of the three sides, and extract the three sides of the take-off and landing pattern; (4.4) From the three-side endpoint, search backward frame by frame for the roll angle φ < 2 and the heading angle The point that is consistent with the heading of the airport runway is taken as the end point of the four sides to extract the four sides of the take-off and landing route; (4.3) From the four end points, search for the ground speed V frame by frame d <40, take it as the final end point and extract the fifth side of the take-off and landing pattern.

Images