A threshold-based automatic aircraft motion recognition method and system
Through the threshold-based aircraft action automation recognition method, the derivative is calculated using altitude timing data, and the problem of inaccurate artificial marking dependence and identification in the prior art is solved, and the accuracy, real-time recognition and automation of aircraft actions are achieved, especially stable rise and The identification of descent status provides guarantees for flight safety.
Patent Information
- Application Number
- CN202410766955.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-14
- Publication Date
- 2024-12-13
- Estimated Expiration
- 2044-06-14
AI Technical Summary
The existing aircraft action recognition methods rely on manual labeled data, which have problems such as strong subjectivity, inaccurate identification and inability to process the aircraft's current flight data in real time, and cannot accurately identify the aircraft's actions of stable rise and steady decline, and lack automated algorithms.
The aircraft action type is automatically determined by using threshold-based identification method. By obtaining the altitude timing data of the aircraft, the altitude change value, first-order derivative and second-order derivative are calculated, and combined with the preset judgment threshold, the aircraft action type is automatically judged, including level flight and ascending. , falling, steady rise and steady decline.
It realizes efficient and accurate aircraft movement recognition, reduces manual processing errors, can analyze the current status of the aircraft in real time, overcomes the shortcomings of the inability to identify stable ascent and descent actions and lack of automation in the existing technology, and improves the targetedness and adaptability of identification. , providing protection for flight safety.
Smart Images
Figure CN118332445B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of flight data processing, and in particular to a threshold-based automatic aircraft motion recognition method and system. Background Art
[0002] Establishing a test flight task evaluation model and objectively evaluating each student's actions can improve the student's actions in a targeted manner and ultimately improve flight driving skills. The premise for evaluating flight tasks and flight actions is the recognition of flight actions. If flight actions cannot be accurately recognized, the evaluation of flight tasks and flight actions cannot be carried out. Therefore, how to select and improve the existing aircraft action recognition method is the primary problem that needs to be solved urgently.
[0003] At present, the commonly used aircraft action recognition methods are mainly divided into three categories: recognition methods based on expert systems; recognition methods based on probabilistic graphical models, such as Bayesian network models, support vector machines, etc.; and recognition methods based on neural networks. For the three existing methods, the recognition method of the expert system relies on the intuitive and easy-to-understand rule criteria, while the rule criteria require a lot of prior knowledge. Affected by the incomplete knowledge base, misidentification and missed recognition may occur. The recognition method based on the probabilistic graphical model can use the knowledge of machine learning to form a model of aircraft actions with a high accuracy rate, but due to the complexity of the calculation, it has the disadvantage of a long recognition time. The recognition method of the neural network relies on a large number of samples with manual marking numbers. For different aircraft models, new samples need to be collected and retrained, which is time-consuming and laborious.
[0004] The existing aircraft motion recognition methods have the following disadvantages:
[0005] (1) The existing commonly used aircraft motion recognition methods require manual labeling of data samples, and the manual judgment standards are inconsistent. Therefore, there is no standardized standard for labeling data samples, and the subjective dependence is strong, making it difficult to accurately judge aircraft motions. The model is trained based on historical flight parameter data, and then the model is used to identify aircraft motions based on the current aircraft flight parameter data. There is an impact of historical sample data on flight motion recognition, and it is impossible to process and analyze the current aircraft flight parameter data in real time, so there is a problem of poor targeting.
[0006] (2) The existing threshold-based method for judging aircraft motion can identify the aircraft's stable level flight, ascent, and descent motions based on the altitude change range and altitude change rate, but cannot identify the aircraft's stable ascent and stable descent motions. Moreover, the method only exists at the theoretical level and lacks an algorithm that can be automated. Summary of the invention
[0007] In order to solve the above technical problems, the present invention provides a threshold-based automatic aircraft motion recognition method and system, which can efficiently and accurately recognize aircraft motions. At the same time, the algorithm has a clear logical structure, avoids redundant procedures, and is low in cost.
[0008] The present invention provides a threshold-based automatic aircraft motion recognition method, comprising the following steps:
[0009] S1. Obtain the flight parameter data of the aircraft in a certain flight mission.
[0010] S2, determining the judgment threshold of the flight action;
[0011] The judgment threshold includes: height judgment accuracy d alt , altitude change rate limit value d h , the change rate limit value of the height change rate d h_rate_rate ,Stable rise / fall discrimination accuracy d h_rate .
[0012] S3, calculating the altitude change value of the aircraft in the current time period, the first-order derivative of the altitude, the maximum variation range of the first-order derivative of the altitude, and the second-order derivative of the altitude according to the altitude time series data of the flight parameter data;
[0013] The height time series data refers to the height data that changes over time;
[0014] S4, according to the first-order derivative h_rate of the altitude of the aircraft in the current time period and the altitude change rate limit value d h , determine whether the aircraft is in level flight, ascending or descending state in the current time period; if the aircraft is in level flight state in the current time period, enter S5; if the aircraft is in ascending state or descending state in the current time period, enter S6;
[0015] Furthermore, when |h_rate| ≤ d h When the aircraft is judged to be in level flight at the current time period;
[0016] When h_rate <-d h When the aircraft is judged to be in a descending state in the current time period;
[0017] When h_rate > d h , it is determined that the aircraft is in an ascending state during the current time period.
[0018] S5, according to the altitude change value of the aircraft in the current time period and the height discrimination accuracy d alt , determine whether the aircraft is in a stable level flight state in the current time period;
[0019] Furthermore, when , it is determined that the aircraft is in a stable level flight state in the current time period.
[0020] Furthermore, if the absolute value of the first-order derivative of the aircraft's altitude at the next moment |h_rate| is less than or equal to the altitude change rate limit value d h , and the aircraft's altitude change value at the next moment Less than the height determination accuracy d alt , it is determined that the aircraft is in stable level flight at the next moment;
[0021] If the absolute value of the first-order derivative of the aircraft's altitude at the next moment |h_rate| is greater than the altitude change rate limit value d h , or the aircraft's altitude change value at the next moment Not less than the height determination accuracy d alt , it is determined that the aircraft's stable level flight state will no longer continue at the next moment, and the current time period is the stable level flight state time period.
[0022] S6, according to the maximum variation range of the second-order derivative h_rate_rate of the height of the aircraft in the current time period and the first-order derivative of the height , the change rate limit value d of the height change rate h_rate_rate , the stable rise / fall discrimination accuracy d h_rate , determine whether the aircraft is in a stable ascending or descending state in the current time period;
[0023] Furthermore, when and , it is determined that the aircraft is in a stable ascending or descending state in the current time period.
[0024] Furthermore, if the first-order derivative of the aircraft's altitude at the next moment h_rate is less than the negative altitude change rate limit value -d h , and the absolute value of the second-order derivative of the aircraft's altitude at the next moment |h_rate_rate| is less than the change rate limit value d of the altitude change rate h_rate_rate , and the maximum variation range of the first-order derivative of the aircraft's altitude at the next moment Less than the stable rise / fall discrimination accuracy d h_rate , it is determined that the aircraft is in a stable descent state at the next moment;
[0025] If the first-order derivative of the aircraft's altitude at the next moment h_rate is not less than the negative altitude change rate limit value -d h , or the absolute value of the second-order derivative of the aircraft's altitude at the next moment |h_rate_rate| is not less than the change rate limit value d of the altitude change rate h_rate_rate , or the maximum range of change of the first-order derivative of the aircraft's altitude at the next moment Not less than the stable rise / fall discrimination accuracy d h_rate, it is determined that the aircraft's stable descent state will no longer continue at the next moment, and the current time period is a stable descent state time period;
[0026] If the first-order derivative of the aircraft's altitude at the next moment h_rate is greater than the altitude change rate limit d h , and the absolute value of the second-order derivative of the aircraft's altitude at the next moment |h_rate_rate| is less than the change rate limit value d of the altitude change rate h_rate_rate , and the maximum variation range of the first-order derivative of the aircraft's altitude at the next moment Less than the stable rise / fall discrimination accuracy d h_rate , it is determined that the aircraft is in a stable ascending state at the next moment;
[0027] If the first-order derivative of the aircraft's altitude at the next moment h_rate is not greater than the altitude change rate limit value d h , or the absolute value of the second-order derivative of the aircraft's altitude at the next moment |h_rate_rate| is not less than the change rate limit value d of the altitude change rate h_rate_rate , or the maximum range of change of the first-order derivative of the aircraft's altitude at the next moment Not less than the stable rise / fall discrimination accuracy d h_rate , it is determined that the aircraft's stable ascent state will no longer continue at the next moment, and the current time period is the stable ascent state time period.
[0028] The present invention also provides a threshold-based automatic aircraft motion recognition system, which is used to execute the threshold-based automatic aircraft motion recognition method, and includes the following modules:
[0029] The data acquisition module is used to obtain the flight parameter data of the aircraft in a certain flight mission;
[0030] The threshold preset module is used to determine the judgment threshold of the flight action, and the judgment threshold includes: the height judgment accuracy d alt , altitude change rate limit value d h , the change rate limit value of the height change rate d h_rate_rate ,Stable rise / fall discrimination accuracy d h_rate ;
[0031] A calculation module is connected to the data acquisition module and is used to calculate the altitude change value of the aircraft in the current time period according to the altitude time series data of the flight parameter data. , height first-order derivative h_rate, maximum range of change of height first-order derivative , height second-order derivative h_rate_rate;
[0032] Judgment and analysis module: connected to the calculation module and the threshold preset module, used to determine the value of the first-order derivative h_rate of the height of the aircraft in the current time period and the height change rate limit value dh , determine whether the aircraft is in level flight, ascending or descending state in the current time period; if the aircraft is in level flight state in the current time period, according to the altitude change value of the aircraft in the current time period and the height discrimination accuracy d alt , determine whether the aircraft is in a stable level flight state in the current time period; if the aircraft is in an ascending or descending state in the current time period, according to the maximum change range of the second-order derivative of the height h_rate_rate of the aircraft in the current time period, the first-order derivative of the height , the change rate limit value d of the height change rate h_rate_rate , the stable rise / fall discrimination accuracy d h_rate , determine whether the aircraft is in a stable ascent or stable descent state in the current time period.
[0033] The embodiments of the present invention have the following technical effects:
[0034] 1. The technical solution of the present invention obtains the altitude time series data of the flight parameter data of the aircraft in a certain flight mission, calculates the altitude change value, the first-order derivative of the altitude, the maximum change range of the first-order derivative of the altitude, and the second-order derivative of the altitude in the current time period of the aircraft, and judges the aircraft action type and the preset judgment threshold according to the altitude change value, the first-order derivative of the altitude, the maximum change range of the first-order derivative of the altitude, and the second-order derivative of the altitude in the current time period of the aircraft, thereby solving the problems of strong subjectivity and inaccurate action recognition caused by relying on manually marked sample data, and being unable to judge the aircraft action type based on real-time flight parameter data and poor pertinence, thereby reducing the errors and costs generated by manual data processing, and being able to process and analyze the current flight parameter data of the aircraft in real time for specific flight missions, thereby improving the pertinence and adaptability of aircraft action recognition.
[0035] 2. The technical solution of the present invention more accurately captures the information of the altitude change speed and the rate of change of the altitude change speed by introducing the maximum change range of the second-order derivative of altitude and the first-order derivative of altitude, overcomes the problem that the method of judging the aircraft action based on the threshold value cannot identify the aircraft action of stable ascent and stable descent, and can more effectively judge whether the aircraft is in a stable flight state, thereby providing guarantee for flight safety.
[0036] 3. The technical solution of the present invention determines the duration of the aircraft action by judging the flight action of the aircraft at the next moment, thereby realizing the automatic recognition of the aircraft action, overcoming the problem that the method of judging the aircraft action based on threshold in the prior art only exists at the theoretical level and cannot be automated, and the automatic recognition of the aircraft action can be realized through computer algorithms. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0038] Figure 1 is a flow chart of a threshold-based automatic aircraft motion recognition method provided by an embodiment of the present invention;
[0039] Figure 2 A flight trajectory diagram provided by an embodiment of the present invention;
[0040] Figure 3 It is a schematic diagram of an algorithm flow for determining a stable level flight action provided by an embodiment of the present invention;
[0041] Figure 4 is a schematic diagram of an algorithm flow for determining a stable descent action provided by an embodiment of the present invention;
[0042] Figure 5 It is a schematic diagram of an aircraft action recognition result provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0043] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be described clearly and completely below. 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 belong to the scope of protection of the present invention.
[0044] Figure 1 is a flow chart of a threshold-based automatic aircraft motion recognition method provided by an embodiment of the present invention. Figure 1 , specifically including:
[0045] S1. Obtain the flight parameter data of the aircraft in a certain flight mission;
[0046] Flight parameter data is data information of the entire or partial flight process recorded and collected by the flight parameter recording system.
[0047] S2, determining the judgment threshold of the flight action;
[0048] The judgment threshold includes: height judgment accuracy d alt , altitude change rate limit value d h , the change rate limit value of the height change rate d h_rate_rate ,Stable rise / fall discrimination accuracy dh_rate .
[0049] Optionally, the height determination accuracy d alt , altitude change rate limit value d h , the change rate limit value of the height change rate d h_rate_rate ,Stable rise / fall discrimination accuracy d h_rate The threshold value can be set according to different flight test stages or different types of flights.
[0050] S3. Calculate the altitude change value of the aircraft in the current time period based on the altitude time series data of the flight parameter data , height first-order derivative h_rate, maximum range of change of height first-order derivative , height second-order derivative h_rate_rate;
[0051] The height time series data refers to height data that changes over time.
[0052] Furthermore, according to the maximum value and the minimum value of the flight altitude in the preset time period, the difference between the maximum value and the minimum value of the flight altitude is calculated, and the difference between the maximum value and the minimum value of the flight altitude is used as the altitude change value of the aircraft in the current time period. .
[0053] Further, the calculation of the first-order derivative of altitude according to the altitude time series data of the flight parameter data specifically includes:
[0054] h1′=(h2-h1) / Δ t ;
[0055] Among them, h1′ is the first-order derivative of the flight altitude at time t1, h2 is the flight altitude at time t2, h1 is the flight altitude at time t1, and Δt is the time interval, that is, Δt=t2 - t1.
[0056] Furthermore, calculating the second-order derivative of altitude based on the altitude time series data of the flight parameter data specifically includes:
[0057] h1′′=(h2′-h1′) / Δ t ;
[0058] Among them, h1′′ is the second-order derivative of the flight altitude at time t1, h1′ is the first-order derivative of the flight altitude at time t1, h2′ is the first-order derivative of the flight altitude at time t2, and Δt is the time interval, that is, Δt=t2 - t1.
[0059] The processing of the first and second derivatives of the height data is shown in Table 1;
[0060] Table 1 Height data processing
[0061] Time series number Height data First-order derivative: rate of change h_rate Second-order derivative: rate of change of rate of change h_rate_rate 1 <![CDATA[h1]]> <![CDATA[h1′=(h2-h1) / Δ t ]]> <![CDATA[h1′′=(h2′-h1′) / Δ t ]]> 2 <![CDATA[h2]]> <![CDATA[h2′= (h3-h2) / Δ t ]]> <![CDATA[h2′′=(h3′-h2′) / Δ t ]]> 3 <![CDATA[h3]]> <![CDATA[h3′= (h4-h3) / Δ t ]]> <![CDATA[h3′′=(h4′-h3′) / Δ t ]]> 4 <![CDATA[h4]]> <![CDATA[h4′= (h5-h4) / Δ t ]]> <![CDATA[h4′′=(h5′-h4′) / Δ t ]]> 5 <![CDATA[h5]]> <![CDATA[h5′= (h6-h5) / Δ t ]]> <![CDATA[h5′′=(h6′-h5′) / Δ t ]]> … … … … M-2 <![CDATA[h M-2 ]]> <![CDATA[h M-2 ′= (h M-1 -h M-2 ) / Δ t ]]> <![CDATA[h M-2 ′′=(h M-1 ′-h M-2 ′) / Δ t ]]> M-1 <![CDATA[h M-1 ]]> <![CDATA[h M-1 ′= (h M -h M-1 ) / Δ t ]]> none M <![CDATA[h M ]]> none none
[0062] Furthermore, the maximum variation range of the first-order derivative of the altitude of the aircraft in the current time period is calculated specifically including:
[0063] According to the maximum value of the first-order derivative of the flight altitude and the minimum value of the first-order derivative of the flight altitude within the preset time period, the difference between the maximum value of the first-order derivative of the flight altitude and the minimum value of the first-order derivative of the flight altitude is calculated, and the difference between the maximum value of the first-order derivative of the flight altitude and the minimum value of the first-order derivative of the flight altitude is used as the maximum variation range of the first-order derivative of the altitude of the aircraft in the current time period .
[0064] S4, according to the first-order derivative h_rate of the altitude of the aircraft in the current time period and the altitude change rate limit value d h , determine whether the aircraft is in level flight, ascending or descending state in the current time period; if the aircraft is in level flight state in the current time period, enter S5; if the aircraft is in ascending state or descending state in the current time period, enter S6;
[0065] Furthermore, when |h_rate| ≤ d h When the aircraft is judged to be in level flight at the current time period;
[0066] When h_rate <-d h When the aircraft is judged to be in a descending state in the current time period;
[0067] When h_rate > d h , it is determined that the aircraft is in an ascending state during the current time period.
[0068] S5, according to the altitude change value of the aircraft in the current time period and the height discrimination accuracy d alt , determine whether the aircraft is in a stable level flight state in the current time period;
[0069] Furthermore, when , it is determined that the aircraft is in a stable level flight state in the current time period.
[0070] Furthermore, if the absolute value of the first-order derivative of the aircraft's altitude at the next moment |h_rate| is less than or equal to the altitude change rate limit value d h , and the aircraft's altitude change value at the next moment Less than the height determination accuracy d alt , it is determined that the aircraft is in stable level flight at the next moment;
[0071] If the absolute value of the first-order derivative of the aircraft's altitude at the next moment |h_rate| is greater than the altitude change rate limit value d h, or the aircraft's altitude change value at the next moment Not less than the height determination accuracy d alt , it is determined that the aircraft's stable level flight state will no longer continue at the next moment, and the current time period is the stable level flight state time period.
[0072] S6, according to the maximum variation range of the second-order derivative h_rate_rate of the height of the aircraft in the current time period and the first-order derivative of the height , the change rate limit value d of the height change rate h_rate_rate , the stable rise / fall discrimination accuracy d h_rate , determine whether the aircraft is in a stable ascent or stable descent state in the current time period.
[0073] Furthermore, when and , it is determined that the aircraft is in a stable ascending or descending state in the current time period.
[0074] Furthermore, if the first-order derivative of the aircraft's altitude at the next moment h_rate is less than the negative altitude change rate limit value -d h , and the absolute value of the second-order derivative of the aircraft's altitude at the next moment |h_rate_rate| is less than the change rate limit value d of the altitude change rate h_rate_rate , and the maximum variation range of the first-order derivative of the aircraft's altitude at the next moment Less than the stable rise / fall discrimination accuracy d h_rate , it is determined that the aircraft is in a stable descent state at the next moment;
[0075] If the first-order derivative of the aircraft's altitude at the next moment h_rate is not less than the negative altitude change rate limit value -d h , or the absolute value of the second-order derivative of the aircraft's altitude at the next moment |h_rate_rate| is not less than the change rate limit value d of the altitude change rate h_rate_rate , or the maximum range of change of the first-order derivative of the aircraft's altitude at the next moment Not less than the stable rise / fall discrimination accuracy d h_rate , it is determined that the aircraft's stable descent state will no longer continue at the next moment, and the current time period is a stable descent state time period;
[0076] If the first-order derivative of the aircraft's altitude at the next moment h_rate is greater than the altitude change rate limit d h , and the absolute value of the second-order derivative of the aircraft's altitude at the next moment |h_rate_rate| is less than the change rate limit value d of the altitude change rate h_rate_rate , and the maximum variation range of the first-order derivative of the aircraft's altitude at the next moment Less than the stable rise / fall discrimination accuracy d h_rate , it is determined that the aircraft is in a stable ascending state at the next moment;
[0077] If the first-order derivative of the aircraft's altitude at the next moment h_rate is not greater than the altitude change rate limit value d h , or the absolute value of the second-order derivative of the aircraft's altitude at the next moment |h_rate_rate| is not less than the change rate limit value d of the altitude change rate h_rate_rate , or the maximum range of change of the first-order derivative of the aircraft's altitude at the next moment Not less than the stable rise / fall discrimination accuracy d h_rate , it is determined that the aircraft's stable ascent state will no longer continue at the next moment, and the current time period is the stable ascent state time period.
[0078] Furthermore, Figure 3 This is the algorithm flow chart for determining stable level flight action. Figure 4 The algorithm flow chart for judging stable descent action is shown in Figure 3 and Figure 4 , an algorithm of an automatic aircraft motion recognition method based on a threshold value specifically includes:
[0079] a. Input the aircraft altitude time series data at M times and the preset threshold;
[0080] b. Introduce intermediate variables temp_state, t, N; where temp_state represents the action type, t represents the starting value of the current judgment time range, and N represents the duration of the aircraft action;
[0081] Furthermore, temp_state=1 indicates stable level flight, temp_state=2 indicates stable descent, temp_state=3 indicates stable ascent, temp_state=14 indicates unstable level flight, temp_state=24 indicates unstable descent, and temp_state=34 indicates unstable ascent;
[0082] c. Initialize the intermediate variables. The initial value of temp_state is -1, the initial value of t is 1, and the initial value of N is 1.
[0083] Furthermore, the initial value of the temp_state is -1, indicating that the initial state of the action type is unknown;
[0084] d. According to the aircraft action recognition, the judgment conditions of stable level flight, stable ascent and stable descent are determined, and the action type temp_state is determined;
[0085] e. If the action type at the current moment is different from that at the previous moment, record the time of the previous moment as the end time of the previous duration, use the current moment as the start time of the next flight segment, add 1 to N, and return to step d;
[0086] Specifically, when the aircraft action at a certain time i (i>t) after t is different from temp_state, it means that the current variable temp_state lasts from time t to time i-1, and the aircraft action no longer lasts from time i. Assign time i to t, add 1 to N, and judge the duration range of the next round of aircraft action.
[0087] f. When i=M-2, the recognition process ends and the result arrays Class1 and Class2 are output.
[0088] Specifically, the array Class1 represents an array of M rows and 1 column, representing the aircraft action category at each moment, where M represents the time sequence number;
[0089] The array Class2 (N×3) represents an array of N rows and 3 columns, wherein the first column represents the aircraft action type, and the second column and the third column represent the time serial number of the start and end of the aircraft action type.
[0090] The algorithm flow for determining a stable ascending action is the same as the algorithm flow for determining a stable descending action, and will not be repeated here.
[0091] For example, aircraft motion recognition is performed on a certain flight trajectory. Figure 2 As shown,
[0092] Optionally, the height discrimination accuracy d alt Set to 2m, height change rate limit value d h Set to 0.8m / s, the change rate limit value d of the altitude change rate h_rate_rate Set to 2m / s 2 , stable rise / fall discrimination accuracy d h_rate Set to 3m / s, the recognition results are as follows Figure 5 shown.
[0093] Furthermore, as shown in Table 2, some of the original flight altitude data and the intermediate calculation result data, the second column gives Figure 2 The first 20 altitude data of the flight trajectory are processed according to the processing method described in Table 1 to calculate the first-order derivative and the second-order derivative of the altitude;
[0094] Specifically, h1=2279.9995, h2=2279.9762, then, h1'=(h2-h1) / Δt=-0.233, where Δt=0.1. Similarly, the first-order derivative values of the heights of the other 19 height data in Table 2 can be calculated; h1'=-0.233, h2'=-0.48, then, h1''=(h2'-h1') / Δt=-2.47, where Δt=0.1. Similarly, the second-order derivative values of the heights of the other 18 height data in Table 2 can be calculated.
[0095] For the data at the first moment in Table 2, h_rate=-0.233, there exists 0.233≤0.8. Since there is only one moment, , 0<2, so the current state is stable level flight, Class=1;
[0096] For the data at the second moment in Table 2, h_rate=-0.48, there exists 0.48≤0.8. In addition, for the data at the current moment 1 to 2, there exists , since 0.0233<2, the current state belongs to stable level flight, Class1=1; and so on, the flight states at other times in Table 2 and the results of Class1 can be calculated.
[0097] Table 2 Part of the original flight altitude data and intermediate calculation result data
[0098]
[0099] Furthermore, the results of Class2 can be obtained based on the results of Class1 at each moment. In Table 2, the value of Class1 at the 1st to 3rd moment is 1, and the value of Class1 at the 4th moment is 2. Therefore, the 1st to 3rd moment forms the first level flight stage (N=1). N=1 corresponds to the first row of Class2 data. In the first row of data, the first column of Class2 data is 1, indicating stable level flight; the second column of Class2 data is 1, indicating that the stable level flight starts from the first moment; the third column of Class2 data is 3, indicating that the stable level flight ends at the third moment.
[0100] Figure 2 The Class2 results obtained by the computer algorithm of the flight trajectory shown are shown in columns 2-4 of Table 3. The results in column 2 of Table 3 represent the data in column 1 of Class2: the type of aircraft action; the results in column 3 of Table 3 represent the data in column 2 of Class2: the time number when the aircraft action starts; the results in column 4 of Table 3 represent the data in column 3 of Class2: the time number when the aircraft action ends.
[0101] Table 3 Calculation results of computer algorithm recognition
[0102]
[0103] The present invention also provides a threshold-based automatic aircraft motion recognition system, which is used to execute the threshold-based automatic aircraft motion recognition method, and includes the following modules:
[0104] The data acquisition module is used to obtain the flight parameter data of the aircraft in a certain flight mission;
[0105] The threshold preset module is used to determine multiple judgment thresholds of flight actions, and the multiple judgment thresholds include: height judgment accuracy d alt , altitude change rate limit value d h , the change rate limit value of the height change rate d h_rate_rate ,Stable rise / fall discrimination accuracy d h_rate ;
[0106] A calculation module, connected to the data acquisition module, for calculating the altitude change value of the aircraft in the current time period, the first-order derivative of the altitude, the maximum variation range of the first-order derivative of the altitude in the current time period of the aircraft, and the second-order derivative of the altitude according to the altitude time series data of the flight parameter data;
[0107] Judgment and analysis module: connected to the calculation module and the threshold preset module, used to determine the value of the first-order derivative h_rate of the height of the aircraft in the current time period and the height change rate limit value d h , determine whether the aircraft is in level flight, ascending or descending state in the current time period; if the aircraft is in level flight state in the current time period, according to the altitude change value of the aircraft in the current time period and the height discrimination accuracy d alt , determine whether the aircraft is in a stable level flight state in the current time period; if the aircraft is in an ascending or descending state in the current time period, according to the maximum change range of the second-order derivative of the height h_rate_rate of the aircraft in the current time period, the first-order derivative of the height , the change rate limit value d of the height change rate h_rate_rate , the stable rise / fall discrimination accuracy d h_rate , determine whether the aircraft is in a stable ascent or stable descent state in the current time period.
[0108] It should be noted that the terms used in the present invention are only for describing specific embodiments, rather than limiting the scope of the present application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular, but may also include the plural. The terms "include", "comprise" or any other variant thereof are intended to cover non-exclusive inclusion, so that the process, method or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of more restrictions, the elements defined by the sentence "include one..." do not exclude the presence of other identical elements in the process, method or device including the elements.
[0109] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be a connection between the two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.
[0110] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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 replace some or all of the technical features therein by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.
Claims
1. A threshold-based automatic aircraft motion recognition method, characterized in that: The steps include: S1. Obtain the flight parameter data of the aircraft in a certain flight mission; S2, determining the judgment threshold of the flight action; The judgment threshold includes: height judgment accuracy d alt , altitude change rate limit value d h , the change rate limit value of the height change rate d h_rate_rate ,Stable rise / fall discrimination accuracy d h_rate ; S3. Calculate the altitude change value of the aircraft in the current time period based on the altitude time series data of the flight parameter data , height first-order derivative h_rate, maximum range of change of height first-order derivative , height second-order derivative h_rate_rate; The height time series data refers to the height data that changes over time; According to the maximum value and the minimum value of the flight altitude in the preset time period, the difference between the maximum value and the minimum value of the flight altitude is calculated, and the difference between the maximum value and the minimum value of the flight altitude is used as the altitude change value of the aircraft in the current time period ; According to the maximum value of the first-order derivative of the flight altitude and the minimum value of the first-order derivative of the flight altitude within the preset time period, the difference between the maximum value of the first-order derivative of the flight altitude and the minimum value of the first-order derivative of the flight altitude is calculated, and the difference between the maximum value of the first-order derivative of the flight altitude and the minimum value of the first-order derivative of the flight altitude is used as the maximum variation range of the first-order derivative of the altitude of the aircraft in the current time period. ; S4, according to the first-order derivative h_rate of the altitude of the aircraft in the current time period and the altitude change rate limit value d h , determine whether the aircraft is in level flight, ascending or descending state in the current time period; if the aircraft is in level flight state in the current time period, enter S5; if the aircraft is in ascending state or descending state in the current time period, enter S6; S5, according to the altitude change value of the aircraft in the current time period and the height discrimination accuracy d alt , determine whether the aircraft is in a stable level flight state in the current time period; S6, according to the maximum variation range of the second-order derivative h_rate_rate of the height of the aircraft in the current time period and the first-order derivative of the height , the change rate limit value d of the height change rate h_rate_rate , the stable rise / fall discrimination accuracy d h_rate , determine whether the aircraft is in a stable ascending or descending state in the current time period, including: when and When the aircraft is in a stable ascending or descending state in the current time period, the method further includes: If the first-order derivative of the aircraft's altitude at the next moment h_rate is less than the negative altitude change rate limit value -d h , and the absolute value of the second-order derivative of the aircraft's altitude at the next moment |h_rate_rate| is less than the change rate limit value d of the altitude change rate h_rate_rate , and the maximum variation range of the first-order derivative of the aircraft's altitude at the next moment Less than the stable rise / fall discrimination accuracy d h_rate , it is determined that the aircraft is in a stable descent state at the next moment; If the first-order derivative of the aircraft's altitude at the next moment h_rate is not less than the negative altitude change rate limit value -d h , or the absolute value of the second-order derivative of the aircraft's altitude at the next moment |h_rate_rate| is not less than the change rate limit value d of the altitude change rate h_rate_rate , or the maximum range of change of the first-order derivative of the aircraft's altitude at the next moment Not less than the stable rise / fall discrimination accuracy d h_rate , it is determined that the aircraft's stable descent state will no longer continue at the next moment, and the current time period is a stable descent state time period; If the first-order derivative of the aircraft's altitude at the next moment h_rate is greater than the altitude change rate limit d h , and the absolute value of the second-order derivative of the aircraft's altitude at the next moment |h_rate_rate| is less than the change rate limit value d of the altitude change rate h_rate_rate , and the maximum variation range of the first-order derivative of the aircraft's altitude at the next moment Less than the stable rise / fall discrimination accuracy d h_rate , it is determined that the aircraft is in a stable ascending state at the next moment; If the first-order derivative of the aircraft's altitude at the next moment h_rate is not greater than the altitude change rate limit value d h , or the absolute value of the second-order derivative of the aircraft's altitude at the next moment |h_rate_rate| is not less than the change rate limit value d of the altitude change rate h_rate_rate , or the maximum range of change of the first-order derivative of the aircraft's altitude at the next moment Not less than the stable rise / fall discrimination accuracy d h_rate , it is determined that the aircraft's stable ascent state will no longer continue at the next moment, and the current time period is the stable ascent state time period.
2. The threshold-based automatic aircraft motion recognition method according to claim 1, characterized in that: S4, based on the first-order derivative h_rate of the altitude of the aircraft in the current time period and the altitude change rate limit value d h , determine whether the aircraft is in level flight, ascending or descending state in the current time period, including: When |h_rate| ≤ d h When the aircraft is judged to be in level flight at the current time period; When h_rate <-d h When the aircraft is judged to be in a descending state in the current time period; When h_rate > d h , it is determined that the aircraft is in an ascending state during the current time period.
3. The threshold-based automatic aircraft motion recognition method according to claim 1, characterized in that: S5, based on the altitude change value of the aircraft in the current time period and the height discrimination accuracy d alt , to determine whether the aircraft is in a stable level flight state in the current time period, including: when , it is determined that the aircraft is in a stable level flight state in the current time period.
4. The threshold-based automatic aircraft motion recognition method according to claim 3, characterized in that: When When the aircraft is in a stable level flight state during the current time period, the method further includes: If the absolute value of the first-order derivative of the aircraft's altitude at the next moment |h_rate| is less than or equal to the altitude change rate limit value d h , and the aircraft's altitude change value at the next moment Less than the height determination accuracy d alt , it is determined that the aircraft is in stable level flight at the next moment; If the absolute value of the first-order derivative of the aircraft's altitude at the next moment |h_rate| is greater than the altitude change rate limit value d h , or the aircraft's altitude change value at the next moment Not less than the height determination accuracy d alt , it is determined that the aircraft's stable level flight state will no longer continue at the next moment, and the current time period is the stable level flight state time period.
5. A threshold-based aircraft motion automatic recognition system, used to execute the threshold-based aircraft motion automatic recognition method according to any one of claims 1 to 4, characterized in that: Includes the following modules: The data acquisition module is used to obtain the flight parameter data of the aircraft in a certain flight mission; The threshold preset module is used to determine the judgment threshold of the flight action, and the judgment threshold includes: the height judgment accuracy d alt , altitude change rate limit value d h , the change rate limit value of the height change rate d h_rate_rate ,Stable rise / fall discrimination accuracy d h_rate ; A calculation module is connected to the data acquisition module and is used to calculate the altitude change value of the aircraft in the current time period according to the altitude time series data of the flight parameter data. , height first-order derivative h_rate, maximum range of change of height first-order derivative , height second-order derivative h_rate_rate; Judgment and analysis module: connected to the calculation module and the threshold preset module, used to determine the value of the first-order derivative h_rate of the height of the aircraft in the current time period and the height change rate limit value d h , determine whether the aircraft is in level flight, ascending or descending state in the current time period; if the aircraft is in level flight state in the current time period, according to the altitude change value of the aircraft in the current time period and the height discrimination accuracy d alt , determine whether the aircraft is in a stable level flight state in the current time period; if the aircraft is in an ascending or descending state in the current time period, according to the maximum change range of the second-order derivative of the height h_rate_rate of the aircraft in the current time period, the first-order derivative of the height , the change rate limit value d of the height change rate h_rate_rate , the stable rise / fall discrimination accuracy d h_rate , determine whether the aircraft is in a stable ascent or stable descent state in the current time period.