CN112257152A - Civil aircraft flight phase identification method based on airborne data - Google Patents
Civil aircraft flight phase identification method based on airborne data Download PDFInfo
- Publication number
- CN112257152A CN112257152A CN202011122311.7A CN202011122311A CN112257152A CN 112257152 A CN112257152 A CN 112257152A CN 202011122311 A CN202011122311 A CN 202011122311A CN 112257152 A CN112257152 A CN 112257152A
- Authority
- CN
- China
- Prior art keywords
- flight
- situation
- aircraft
- vertical motion
- section
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 74
- 230000033001 locomotion Effects 0.000 claims abstract description 85
- 238000007781 pre-processing Methods 0.000 claims abstract description 8
- 238000013459 approach Methods 0.000 claims description 24
- 230000009194 climbing Effects 0.000 claims description 19
- 230000008859 change Effects 0.000 claims description 17
- 230000011218 segmentation Effects 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000013478 data encryption standard Methods 0.000 claims description 10
- 230000001174 ascending effect Effects 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 238000004140 cleaning Methods 0.000 claims description 5
- 230000000630 rising effect Effects 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 14
- 238000004458 analytical method Methods 0.000 abstract description 11
- 230000008901 benefit Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 230000010006 flight Effects 0.000 description 5
- 238000013499 data model Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 102100022278 Arachidonate 5-lipoxygenase-activating protein Human genes 0.000 description 2
- 101710187011 Arachidonate 5-lipoxygenase-activating protein Proteins 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000000638 solvent extraction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 238000009530 blood pressure measurement Methods 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000003344 environmental pollutant Substances 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000446 fuel Substances 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 231100000719 pollutant Toxicity 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/10—Geometric CAD
- G06F30/13—Architectural design, e.g. computer-aided architectural design [CAAD] related to design of buildings, bridges, landscapes, production plants or roads
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/29—Geographical information databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9537—Spatial or temporal dependent retrieval, e.g. spatiotemporal queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Databases & Information Systems (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Architecture (AREA)
- Civil Engineering (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Structural Engineering (AREA)
- Computational Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Remote Sensing (AREA)
- Quality & Reliability (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention belongs to the field of aircraft trajectory analysis and application, and particularly relates to a civil aircraft flight phase identification method based on airborne data, which comprises the following steps: preprocessing a flight path; dividing a vertical motion situation according to the preprocessed flight path; correcting the divided vertical motion situation; dividing flight phases according to the vertical motion situation; constructing a flight state characteristic model according to the characteristics of the flight stage; and the division of the flight phase is carried out according to the preprocessed flight path and the corrected vertical motion situation, so that the re-identification and division of the flight phase are realized, and the implementation process does not need to be carried outThe method distinguishes the types of the aircrafts, has relatively simple and easy execution steps and can solve the problem of the prior artQARThe problem of wrong division of the flight phases in the data is solved, and technical support is provided for the flight phase characteristic analysis of the civil aircraft.
Description
Technical Field
The invention belongs to the field of aircraft trajectory analysis and application, and particularly relates to a civil aircraft flight phase identification method based on airborne data.
Background
Each flight phase division of the civil aircraft from takeoff to landing in the operation process is a very important basic condition in the fields of flight path analysis research such as safety event investigation, performance analysis and flight state monitoring, oil consumption and pollutant emission calculation, flight operation efficiency evaluation, flight data statistics and prediction, airspace operation quality evaluation and the like, for example: in the flight oil consumption estimation process based on the model performance, only the flight phase and the aerodynamic configuration of the aircraft are accurately identified, the motion model and the fuel flow model of the aircraft can be correctly solved, and finally the actual oil consumption calculation result is obtained.
Currently, the commonly used data for track analysis includes Broadcast auto correlation monitoring (ADS-B), Air Traffic Control Radar (ATCRBS), and airborne fast access recorder (QAR). The QAR has the most abundant information, and contains various state monitoring data of the aircraft, even information of flight stages. However, when analyzing a large amount of QAR sample data, it is found that there is a wrong division of the flight phase information, and there are the following in common cases: (1) key flight stages such as take-off, initial climbing, approach and landing are not effectively divided, and the stages are lost or the stage duration is only 1-3 seconds; (2) the normal landing-to-landing-in process is misjudged as grounded continuous takeoff (Touch And Go); (3) a normal initial climb is misinterpreted as an approach. Therefore, the QAR's own flight phase information cannot be used directly in the trajectory analysis calculation program, and can only be used as a manual reference. To solve this problem, the existing QAR track must be re-divided in flight phase and meet the requirements of track analysis calculations. However, at present, the research on identification and division algorithms of the flight phases of civil aircrafts is not common in the technical fields of foreign and domestic academics and engineering. Currently, in a few studies on automatic division of flight phases at home and abroad, three methods can be used:
(1) the method has the advantages that the method is simple and feasible, but only climbing, cruising and descending can be divided, other flight stages need more flight path information to be matched, and meanwhile, when the method is used for processing height jitter, the height change trend on a slightly larger extent cannot be effectively identified by a local linear regression or local mean value smoothing method;
(2) machine learning has the advantages of high recognition accuracy, but on one hand, a large amount of actual flight airborne data are needed for training, the realization process is complex, and on the other hand, the machine learning lacks flexibility for new changes outside a training set;
(3) the fuzzy set model is established, and the method has the advantage of being more convincing in the aspect of processing the jitter of the field values. But simultaneously, because each field needs to set a threshold according to the characteristics of the aircraft performance and the corresponding operation rule, the more the fields are, the more the required thresholds are, the stricter the restrictions on the categories and the operation rules of the aircraft are, and therefore, the flexibility is poor. In addition, the combination of various conditions needs to be considered in the membership calculation process, and the rare special combination conditions cannot be accurately judged, so that no more effective processing method exists at present.
Therefore, based on the above technical problem, a new civil aircraft flight phase identification method based on airborne data needs to be designed.
Disclosure of Invention
The invention aims to provide a civil aircraft flight phase identification method based on airborne data.
In order to solve the technical problem, the invention provides a civil aircraft flight phase identification method based on airborne data, which comprises the following steps:
preprocessing a flight path;
dividing a vertical motion situation according to the preprocessed flight path;
correcting the divided vertical motion situation;
dividing flight phases according to the vertical motion situation;
constructing a flight state characteristic model according to the characteristics of the flight stage; and
and dividing the flight phases according to the preprocessed flight path and the corrected vertical motion situation.
Further, the method for preprocessing the flight path comprises the following steps:
the method comprises the steps of obtaining QAR flight path data, and carrying out secondary segmentation on the QAR flight path data to ensure that flight information corresponds to flight paths one by one;
and (4) carrying out data cleaning on the QAR flight path subjected to the secondary segmentation, removing noise points and repeated time-space records to obtain the preprocessed flight path.
Further, the method for dividing the vertical motion situation according to the preprocessed flight path comprises the following steps:
constructing a vertical motion situation model of the aircraft, and dividing the vertical motion situation into a horizontal LEV, an ascending CLM and a descending DES (data encryption standard), namely
For any track point i, the vertical motion situation TRND thereofiComprises the following steps:
wherein,VSithe altitude change rate of the track point i is shown; VSUp,minAnd VSDown,minThe minimum vertical change rates of the rising situation and the falling situation respectively;
wherein, PAiThe pressure height of the ith track point is shown; TIMEiA timestamp of the ith track point;
digitizing the vertical movement situation:
wherein m is any positive number.
Further, the method for correcting the divided vertical motion situation comprises the following steps:
dividing the vertical motion situation section according to a density clustering method, and correcting outliers and invalid situation sections in the vertical motion situation section, namely
For dataset D ═ x1,x2,…,xi,…,xNIn which xiVertical movement situation TRND as course point iiThe value of (1), δ is the local domain length, ε is a neighborhood distance threshold, η is a threshold of the number of points in the neighborhood of the core point, and ε is less than 2m and η is less than or equal to 2 δ, then the DBSCAN algorithm for local traversal is:
step S301, for any data point x in the data set DiIn the number of 2 δ +1 local area data sets L ═ xi-δ,…,xi+δInner calculation Manhattan distance function FManhattan(xi,xk) That is to say that,
FManhattan(xi,xk)＝|xk-xi|；
wherein k is i- δ, …, i + δ;
step S302, will satisfy FManhattan(xi,xk) All L-domain data points ≦ εTo xiEpsilon neighborhood N ofε,iPerforming the following steps; if N is presentε,iIf the number of inner points is greater than or equal to eta, then xiMarked as a core point; otherwise xiIs marked as an outlier and x is marked asiAdding into the outlier O;
step S303, for the next data point xi+1, repeating step S301 and step S302 until the last data point xNFinishing the calculation;
step S304, for any core point j and its neighborhood Nε,jAnd judging the connection with other core points and neighborhoods thereof, if the connection is judged, combining the core points into a cluster, and forming a cluster set C for all the core points
{C1,C2,…,CM}, i.e. a set of posture segments;
step S305, correcting the outlier, changing the state of the outlier into the state of a preamble state section, and merging the outlier into the preamble state section; if the outlier does not have a preceding situation section, changing the situation of the outlier into the situation of a subsequent situation section, and merging the outlier into the subsequent situation section; when a plurality of continuous outliers exist, correcting each outlier one by one;
step S306, the shortest duration T of the effective situationmin,segWhen a vertical motion situation is shorter in duration than Tmin,segIf so, marking the invalid situation section, modifying the invalid situation section to change the situation of the invalid situation section into the situation of a preamble situation section, and merging the invalid situation section into the preamble situation section; if the invalid situation section has no preceding situation section, the situation of the invalid situation section is changed into the situation of a subsequent situation section, and the invalid situation section is merged into the subsequent situation section.
Further, the method for dividing the flight phases according to the vertical motion situation comprises the following steps:
the flight phases are divided into the following phases according to the vertical motion situation and the pneumatic configuration change: roll-off, take-off, initial climb, cruise, descent, approach, landing cancel, missed climb, and roll-in.
Further, the method for constructing the flight state feature model according to the characteristics of the flight phase comprises the following steps:
switching POS depending on flap positionFlapSurface ground speed limit GSTaxi,maxAnd acquiring six aircraft flight state characteristics CHR according to the characteristics of each flight stage by the states of the landing gear position LDG _ SELDW and the vertical movement situation TRND:
the first aircraft flight state characteristic and the second aircraft flight state characteristic are low-speed and high-speed motion states of the aircraft when the aircraft puts down an undercarriage, and respectively correspond to two flight stages of scene sliding and high-speed sliding;
the flight state characteristics of the aircraft are three, four and five, the flight states of the aircraft under different vertical motion situations when the aircraft landing gear is put on and the flaps are simultaneously released, and the flight states correspond to initial climbing after takeoff, approach before landing and missed approach climbing after landing cancellation;
the flight state characteristic six of the aircraft is the flight state of the aircraft in a smooth configuration and corresponds to three flight stages of climbing, cruising and descending on a navigation path;
and carrying out flight state characteristic classification on each preprocessed QAR track point so as to merge and divide continuous flight characteristic points into a plurality of flight characteristic segments.
Further, the method for dividing the flight phases according to the preprocessed flight path and the corrected vertical motion situation comprises the following steps:
each flight phase is provided with one or more flight state characteristic segments, three flight phases of takeoff, landing and landing cancellation are divided firstly, then the rest non-smooth configuration flight phases are divided according to the front-back relation of the adjacent flight characteristic segments, the smooth configuration flight phases are divided according to the flight state characteristic six of the aircraft and the corrected vertical motion situation, and finally the plurality of subsections of the flight phases obtained after division are combined to obtain the rest flight phases so as to finish the division of the flight phases of the aircraft.
The invention has the advantages that the invention preprocesses the flight path; dividing a vertical motion situation according to the preprocessed flight path; correcting the divided vertical motion situation; dividing flight phases according to the vertical motion situation; constructing a flight state characteristic model according to the characteristics of the flight stage; and the division of the flight stage is carried out according to the preprocessed flight path and the corrected vertical motion situation, the re-identification and division of the flight stage are realized, the airplane types do not need to be distinguished in the implementation process, the execution steps are relatively simple and easy, the problem of wrong division of the flight stage in QAR data can be solved, and the technical support is provided for the characteristic analysis of the flight stage of the civil aircraft.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
Fig. 1 is a flow chart of a civil aircraft flight phase identification method based on airborne data according to the invention;
FIG. 2 is a schematic diagram of a method for correcting outlier and invalid situation segments in accordance with the present invention;
FIG. 3 is a result of the vertical movement situation partitioning of a sample flight 1 on the barometric altitude profile according to the present invention;
FIG. 4 is a result of the flight status characterization of the sample flight 1 according to the present invention on the barometric altitude profile;
FIG. 5 is a schematic view of a relationship model of flight phases and flight status feature segments according to the present invention;
FIG. 6 is a feature segment based flight staging flow framework in accordance with the present invention;
FIG. 7 is a flight staging result for a sample flight 1 (normal flight) in accordance with the present invention;
FIG. 8 is a result of flight phase segmentation for a sample flight 2 (with a missed flight) in accordance with the present invention;
fig. 9 is a comparison of the QAR self-contained flight phase of the sample flight 3 according to the present invention and the results after repartitioning.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Fig. 1 is a flow chart of a civil aircraft flight phase identification method based on airborne data according to the invention.
As shown in fig. 1, this embodiment 1 provides a civil aircraft flight phase identification method based on airborne data, including: preprocessing a flight path; dividing a vertical motion situation according to the preprocessed flight path; correcting the divided vertical motion situation; dividing flight phases according to the vertical motion situation; constructing a flight state characteristic model according to the characteristics of the flight stage; and the division of the flight phase is carried out according to the preprocessed flight path and the corrected vertical motion situation, the re-identification and division of the flight phase are realized, the airplane types do not need to be distinguished in the implementation process, the execution steps are relatively simple and easy, the problem of error division of the flight phase in QAR data can be solved, technical support is provided for the characteristic analysis of the flight phase of the civil airplane, the execution steps of the technical scheme are relatively simple, the reliability is realized, and the application is convenient.
In this embodiment, the method for preprocessing a flight path includes: the method comprises the steps of obtaining QAR flight path data, and carrying out secondary segmentation on the QAR flight path data to ensure that flight information corresponds to flight paths one by one; carrying out data cleaning on the QAR flight path subjected to the secondary segmentation, removing noise points and repeated time-space records to obtain a preprocessed flight path; establishing a QAR track data model according to sample QAR field information, wherein a table 1 is a field description of the QAR data model;
table 1: field description of QAR data model
QAR flight path data are extracted from an airborne recorder by an airline company after the to-be-executed aircraft completes a flight task period, and flight segmentation is carried out; however, there are cases where the segmented QAR track still contains more than 2 flight records, because the segmentation algorithm mainly depends on the flight stage segmentation, and the flight stage segmentation carried by the QAR is erroneous; therefore, the QAR track data needs to be preprocessed: performing secondary segmentation on the QAR flight path by tracking the states of the N1 and N2 fields to ensure that flight information corresponds to the flight path one to one, namely each flight does not contain the flight paths of other flights; performing data cleaning on the QAR flight path after the secondary segmentation, namely removing noise points of main fields and repeated time-space records (time stamps and latitude and longitude information); the specific cleaned fields are Pressure Altitude (PA), Longitude (LON), Latitude (LAT), landing gear position (LDG _ SELDW) and landing gear air-ground logic (LDG _ CMPRSD), and the track data corresponding to each flight is accurately acquired.
In this embodiment, the method for dividing the vertical motion situation according to the preprocessed flight path includes: constructing a vertical motion situation model of the aircraft, and dividing the vertical motion situation into a horizontal LEV, an ascending CLM and a descending DES (data encryption standard), namely
For any track point i, the vertical motion situation TRND thereofiComprises the following steps:
wherein VSiThe altitude change rate of the track point i is shown; VSUp,minAnd VSDown,minThe minimum vertical change rates of the rising situation and the falling situation are respectively positive numbers;
wherein, PAiThe pressure height of the ith track point is shown; TIMEiA timestamp of the ith track point;
to facilitate later clustering calculations, the vertical motion situation is quantified:
wherein m is any positive number, the magnitude of the value does not affect the division result of the vertical motion situation segment, and m is set to be 100 by default in this embodiment.
FIG. 2 is a schematic diagram of a method for correcting outlier and invalid situation segments in accordance with the present invention;
fig. 3 shows the result of the vertical movement situation partitioning of the sample flight 1 on the barometric altitude profile according to the present invention.
In this embodiment, the method for correcting the divided vertical motion situation includes: because the vertical motion situation change of the flight track is a numerical value queue with time sequence characteristics, in order to accurately segment the flight track according to the vertical motion situation, a DBSCAN density clustering method is used, and optimization is performed on the basis, namely local traversal is used in the clustering process, so that the clustering efficiency is improved; dividing the vertical motion situation section according to a density clustering method, and correcting outliers and invalid situation sections in the vertical motion situation section, namely
For dataset D ═ x1,x2,…,xi,…,xNIn which xiVertical movement situation TRND as course point iiThe value of (1), δ is the local domain length, ε is a neighborhood distance threshold, η is a threshold of the number of points in the neighborhood of the core point, and ε is less than 2m and η is less than or equal to 2 δ, then the DBSCAN algorithm for local traversal is:
step S301, for any data point x in the data set DiIn the number of 2 δ +1 local area data sets L ═ xi-δ,…,xi+δInner calculation Manhattan distance function FManhattan(xi,xk) I.e. by
FManhattan(xi,xk)＝|xk-xi|；
Wherein k is i- δ, …, i + δ;
step S302, will satisfy FManhattan(xi,xk) All L-domain data points ≦ ε added to xiEpsilon neighborhood N ofε,iPerforming the following steps; if N is presentε,iIf the number of inner points is greater than or equal to eta, then xiMarked as a core point; otherwise xiIs marked as an outlier and x is marked asiAdding into the outlier O;
step S303, for the next data point xi+1Repeating step S301 and step S302 until the last data point xNFinishing the calculation;
step S304, for any core point j and its neighborhood Nε,jAnd (4) performing connection judgment on other core points and neighborhoods thereof, namely judging whether intersections exist (have the same data points) or not, if the intersections exist, merging the intersections into a cluster, and forming a cluster set C ═ C for all the core points1,C2,…,CM}, i.e. a set of posture segments;
although the air pressure height field is subjected to data cleaning in the data preprocessing process, situation jitter caused by the fact that the local jitter amplitude of the air pressure height exceeds a threshold value still can occur; the jitters are represented as a few outliers and invalid clusters in the DBSCAN clustering result and are short in duration; in this embodiment, according to the principle of "taking the front-sequence state segment as the priority reference", the outlier state and the invalid state segment caused by the local jitter are corrected;
step S305, correcting the outlier, as shown in FIG. 2, a outlier with a descending situation appears between the ascending section and the horizontal section, changing the situation of the outlier into the situation of the preamble situation section (i.e., ascending), and merging the outlier into the preamble situation section; if the outlier does not have the preceding situation section, the situation of the outlier is changed into the situation of the following situation section by taking the following situation section as a reference, and the outlier is merged into the following situation section; when a plurality of continuous outliers exist (the number is inevitably smaller than eta), correcting each outlier one by one (the correction method is the same as the case of a single outlier);
step S306, as the updating interval of the QAR track points is only 1 second, when the QAR track points are disturbed by airflow, the QAR track points are easy to rise or fall temporarily, so that the situation in a situation section (vertical motion situation section) set obtained after clustering still possibly exists in a short-time situation; this short duration of the continuous situation does not reflect the real flight intent and therefore defines the minimum duration T of the effective situationmin,segWhen a vertical motion situation is shorter in duration than Tmin,segThen it is marked as an invalid situation segment, in this embodiment, T is setmin,seg15s, i.e. the situation is considered to be the result of pilot operation when the continuous situation time exceeds 15 seconds; as shown in fig. 2, modifying the invalid situation section (also according to the principle of "taking the previous situation section as a priority reference"), changing the situation of the invalid situation section into the situation of the previous situation section, and merging the invalid situation section into the previous situation section; if the invalid situation section has no preceding situation section, changing the situation of the invalid situation section into the situation of a subsequent situation section, and merging the invalid situation section into the subsequent situation section; the vertical motion situation of the aircraft is identified by using a local traversal clustering method based on density, so that the problem of local jitter of air pressure height of the aircraft during high-altitude flight can be effectively solved;
one characteristic of DBSCAN is that the DBSCAN is sensitive to parameters, and different parameter settings can generate different clustering results; in order to effectively process the problem of local jitter, the clustering scale needs to be reduced, and local situation jitter needs to be found and corrected, so that the threshold eta of the number of points in the neighborhood of the core point needs to be reduced; meanwhile, under the condition that the local domain length delta meets the condition that eta is less than or equal to 2 delta, the smaller the numerical value is, the higher the clustering efficiency is; therefore, in the present embodiment, η ═ 3 and δ ═ 2 are set; in addition, considering that the maximum climbing rate of the medium and large jet civil aircraft at the practical ascending limit is 500ft/min, the minimum vertical change rate VS of the ascending situation is setUp,min500 ft/min; the lowest descent rate is not specifically required in actual operation, and from the descent phase data of a plurality of sample flights, the lowest continuous descent rate is about 400ft/min, so the minimum vertical change rate VS of the descent situation is setDown,min＝400ft/min；
As shown in FIG. 3, it can be seen that all situation segments for this flight (sample flight 1) are correctly identified; it should be noted that, because the QAR update interval is only 1 second, the track points are very dense, and in order to obtain a better display effect, points of each situation segment of the QAR track have been thinned during the drawing.
In this embodiment, the method for dividing flight phases according to vertical motion situations includes: the flight phases are divided into the following phases according to the vertical motion situation and the pneumatic configuration change: roll-off, take-off, initial climb, cruise, descent, approach, landing cancel, missed climb, and roll-in. The normal operation process of the aircraft from a take-off airport to a landing airport can be divided into 9 flight stages such as sliding-out, taking-off, initial climbing, cruising, descending, approaching, landing, sliding-in and the like according to the vertical motion situation and the change of the aerodynamic configuration; aerodynamic configuration changes, i.e. changes in the state of the landing gear and high lift devices (trailing edge flaps, leading edge flaps and leading edge slats), are important references for dividing the non-smooth-form flight phases; since a missed approach condition exists in the QAR sample, this embodiment defines 11 flight phases as shown in table 2;
table 2: attitude and configuration feature definition table for each flight phase
| Phase of flight | Landing gear position | Landing gear air ground logic | Flap | Slat | Vertical situation |
| Sliding out | DOWN | GND | Off | Small | Medium | Total | All in off | LEV |
| Taking off | DOWN | GND→AIR | Small in | In | LEV|CLM |
| Initial climb | UP | AIR | Small in | In | CLM|LEV |
| Climbing device | UP | AIR | Closing device | Closing device | CLM |
| Cruise control system | UP | AIR | Closing device | Closing device | LEV |
| Descend | UP | AIR | Closing device | Closing device | DES |
| Approach to | UP | AIR | Small | medium | full | All in | DES|LEV|CLM |
| Landing | DOWN | AIR→GND | All in | All in | DES|LEV |
| Landing (cancellation) | DOWN | AIR | All in | All in | DES|LEV |
| Climbing in missed approach | DOWN | AIR | All in | All in | CLM |
| Slide in | DOWN | GND | Off | Small | Medium | Total | All in off | LEV |
However, when automatically identifying and dividing the flight phase of a large batch of QAR track samples, the dividing program design cannot be directly performed according to the definition in the table, because there are two reasons: a first aspect is a flap; the flaps and the slats of the large civil aircraft are uniformly controlled by flap handles, and the positions of the designated flaps and the designated slats correspond to the positions of the flaps and the designated slats in each handle gear; however, the flap handle gears of different models, particularly subordinate models of different aircraft manufacturers, are completely different; for example: the flap handle gears of a certain son model of Boeing B737 have 1, 2, 5, 10, 15, 25, 30 and 40, and no mandatory requirement exists between the flight stage and the handle gears, namely, a pilot can select a proper gear according to the situation; the slat is in a general release position at a gear of 1-25, the slat is in a complete release position at a gear of 30-40, and in addition, when the attack angle approaches a critical attack angle, the slat can be automatically and completely released no matter whether the flap is opened or not; the flap handle gears of the A320 family model of the airbus are divided into 0, 1, 2, 3 and FULL, which correspond to six forms: 0. 1, 1+ F, 2, 3 and FULL, have specific morphological requirements at different flight phases, as shown in table 3 below:
table 3: a320 series flap and slat watch
Therefore, flap gears used in the non-smooth configuration flight stage under different models, different units and different airport conditions can be different, and POS is defined for simplifying the using states of flaps and slats in QAR flight pathFlapThe flap position switch is used for indicating whether the flap handle gear is in the release position or not, and the value is ON or OFF; in the QAR sample track data, most models of the Boeing series do not provide effective slat position information, while the airbus series and other models (such as AT75, AT76, DA42 and the like) can provide basically complete flap and slat position information, but part of the aircraft can cause the flap position to be null due to the failure of onboard recording equipment; thus, to improve the universality of the flight staging algorithm, the minimum let-out positions of the FLAPs and slats, respectively, are defined as FLAPMinAnd SLATMinThen, then
In the actual partition program of the present embodiment, FLAPMinAnd SLATMinRespectively taking the minimum positions of FLAPs and slats of all sample models, namely FLAPMin＝1，SLATMin＝16；
The second aspect is the scene stage, where the difference between the field pressure at the high altitude airport and the field pressure at the low altitude airport is very large, and the corresponding barometric altitudeMay differ by more than 10,000 ft; even if the air pressure value of the same airport and the same runway changes from the head of the runway to the tail of the runway, the static pressure measuring sensor of the aircraft is sensitive, so that the rising or falling situation may exist in the surface taxiing stage; therefore, it is not preferable to use only the barometric altitude and the vertical attitude of the aircraft as the basis for dividing the phases of ground taxiing, take-off running and landing running; the common feature of the aircraft in the ground phase is that the landing gear is in the down state and grounded (air-ground logic LDG _ CMPRSD ═ GND), the speed is lower during taxiing and higher during takeoff or landing running; however, the full pressure measurement sensor of the aircraft is not sensitive at low speed motion, resulting in an airspeed meter reading (i.e., meter speed IAS field) of nearly 0 in the QAR track data during the taxi phase; therefore, the ground speed GS is selected to be used as a judgment basis for low-speed sliding and high-speed sliding of the aircraft; the method is characterized in that both a common aircraft model operation manual and an airline operation management regulation have definite limits on the sliding speed, namely, the meter speed cannot exceed 30kt when the surface slides linearly and 10kt when the surface slides in a turning way; considering the influence of the ground wind, defining a maximum ground speed limit GS for the surface taxiingTaxi,max40 kt; when the ground speed of the aircraft on the scene is lower than 40kt, the aircraft is considered to be taxiing; otherwise, it is considered to be running at takeoff or landing.
Fig. 4 shows the flight status feature of the sample flight 1 according to the present invention on the barometric altitude profile.
In this embodiment, the method for constructing the flight state feature model according to the characteristics of the flight phase includes: switching POS depending on flap positionFlapSurface ground speed limit GSTaxi,maxAnd the landing gear position LDG _ SELDW and the state of the vertical movement situation TRND, and acquiring six aircraft flight state characteristics CHR according to the characteristics of each flight phase, as shown in Table 4:
table 4: aircraft flight status feature table
The first aircraft flight state characteristic (aircraft flight state characteristic 1, characteristic 1) and the second aircraft flight state characteristic (aircraft flight state characteristic 2, characteristic 2) are low-speed and high-speed motion states of the aircraft when the aircraft is put down a landing gear, and respectively correspond to two flight stages of scene sliding and high-speed running (scene sliding corresponds to sliding out and sliding in, and high-speed running corresponds to taking off, landing and landing cancellation); the flight state characteristics of the aircraft are three, four and five (the flight state characteristics of the aircraft are 3, 4 and 5, and the characteristics of the aircraft are 3, 4 and 5) which are flight states under different vertical motion situations when the aircraft landing gear is put on and the flaps are released simultaneously, and correspond to initial climbing after takeoff, approach before landing and missed approach after landing cancellation; the aircraft flight state feature six (aircraft flight state feature 6, feature 6) is a flight state of the aircraft in a smooth configuration, and corresponds to three flight phases of climbing, cruising and descending on the airway; carrying out flight state feature classification on each preprocessed QAR track point so as to merge and divide continuous flight feature points into a plurality of flight feature sections; as shown in fig. 4, the six segments (route climb/cruise/descent) of the flight state characteristics of the aircraft of the sample flight 1 account for more than 90% of the total flight time, so that the characteristic division of the takeoff phase is unclear, and therefore, the flight state characteristics are locally enlarged.
FIG. 5 is a schematic view of a relationship model of flight phases and flight status feature segments according to the present invention;
fig. 6 is a characteristic segment-based flight phase segmentation flow framework in accordance with the present invention.
In this embodiment, the method for performing flight phase division according to the preprocessed flight path and the corrected vertical motion situation includes: each flight phase is provided with one or more flight state characteristic segments, and for both normal flights and flights with missed flights, the relationship between the flight phase and the flight state characteristic segments of the aircraft is shown in fig. 5; it can be seen that in the non-smooth configuration flight phase, the sliding-out, sliding-in, taking-off, landing (canceling) and missed approach climbing all have unique flight characteristic segments, but only three flight phases of taking-off, landing and landing (canceling) and the like can be directly divided by combining the aircraft flight state characteristic segment and the landing gear AIR-ground logic (GND | AIR); firstly, dividing three flight stages of takeoff, landing and landing cancellation, then dividing other non-smooth configuration flight stages according to the front-back relation of adjacent flight characteristic sections, dividing smooth configuration flight stages (climbing, cruising and descending) according to the flight state characteristic six of the aircraft and the corrected vertical motion situation, dividing the flow of the QAR complete track flight stage through the flight state characteristic sections as shown in figure 6, finally merging a plurality of subsections of the flight stage obtained after division to obtain the rest flight stages, wherein some flight stages (such as initial climbing and approach) possibly consist of a plurality of flight characteristic sections, and after division, a plurality of subsections of the flight stage can be obtained and need to be merged to complete the division of the flight stage of the aircraft; the established flight state characteristic model and the relationship between the flight state characteristic model and the flight phase are suitable for identifying and dividing the flight phases of all civil aircraft models.
FIG. 7 is a flight staging result for a sample flight 1 (normal flight) in accordance with the present invention;
fig. 8 shows the result of the flight phase division of the sample flight 2 (flight with missed approach) according to the present invention.
In the present embodiment, as shown in fig. 7, it can be seen that each flight phase of the flight (sample flight 1, normal flight) is identified, wherein the takeoff phase is only 34 seconds, which is very short relative to the whole flight history, and therefore, the detail is enlarged locally; the flight has small air pressure height jitter (10 ft within 3 seconds of maximum amplitude, namely 200ft/min) before flying off, which is a phenomenon frequently occurring in QAR tracks within the range of the field; meanwhile, in order to test the recognition performance of the algorithm in the embodiment on the missed approach process, a sample flight 2 (with missed approach flight) with missed approach condition is selected to carry out flight stage repartitioning, and the result is shown in fig. 8, and local amplification is carried out on the landing cancellation, missed approach climbing and subsequent stages; it can be seen that all flight phases from the first landing failure to the second landing success of the flight are effectively identified, and thus, the embodiment can also realize automatic identification and division of flight phases for the missed flight.
Fig. 9 is a comparison of the QAR self-contained flight phase of the sample flight 3 according to the present invention and the results after repartitioning.
In this embodiment, as shown in fig. 9, it can be seen that: the sample flight 3 takeoff stage is not correctly divided in the QAR original information, and is only 1 second (namely 1 data point), while the actual takeoff stage lasts 35 seconds and is consistent with the result of the newly divided takeoff stage; the QAR erroneously identifies the normal roll-in phase as a grounded continuous takeoff phase (Touch And Go), for unknown reasons (the air pressure level during roll-off And roll-in after landing of the flight is stabilized at 4100ft), while the roll-in phase is correctly identified after repartitioning; the stages of takeoff, initial climbing, approach, landing and the like after repartitioning correspond to the state changes of the landing gear and the flap, namely, the flight stage division method of the invention judges from the angle of the change of the aerodynamic configuration of the aircraft, and the flight stage division of the QAR original information is comprehensively judged according to the aspects of possibly pilot operation perception, airport approach and departure program execution progress and the like.
The civil aircraft flight stage identification method QAR flight path flight stage re-division method based on airborne data can effectively divide each flight stage of normal flight and missed flight through aircraft pneumatic configuration and vertical motion situation change, and the situation of error division in QAR original flight stage information is avoided.
In conclusion, the invention preprocesses the flight path; dividing a vertical motion situation according to the preprocessed flight path; correcting the divided vertical motion situation; dividing flight phases according to the vertical motion situation; constructing a flight state characteristic model according to the characteristics of the flight stage; and the division of the flight stage is carried out according to the preprocessed flight path and the corrected vertical motion situation, the re-identification and division of the flight stage are realized, the airplane types do not need to be distinguished in the implementation process, the execution steps are relatively simple and easy, the problem of wrong division of the flight stage in QAR data can be solved, and the technical support is provided for the characteristic analysis of the flight stage of the civil aircraft.
In the embodiments provided in the present application, it should be understood that the disclosed method can be implemented in other ways. The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (7)
1. A civil aircraft flight phase identification method based on airborne data is characterized by comprising the following steps:
preprocessing a flight path;
dividing a vertical motion situation according to the preprocessed flight path;
correcting the divided vertical motion situation;
dividing flight phases according to the vertical motion situation;
constructing a flight state characteristic model according to the characteristics of the flight stage; and
and dividing the flight phases according to the preprocessed flight path and the corrected vertical motion situation.
2. The civil aircraft flight phase identification method based on airborne data according to claim 1,
the method for preprocessing the flight path comprises the following steps:
the method comprises the steps of obtaining QAR flight path data, and carrying out secondary segmentation on the QAR flight path data to ensure that flight information corresponds to flight paths one by one;
and (4) carrying out data cleaning on the QAR flight path subjected to the secondary segmentation, removing noise points and repeated time-space records to obtain the preprocessed flight path.
3. The civil aircraft flight phase identification method based on airborne data according to claim 2,
the method for dividing the vertical motion situation according to the preprocessed flight path comprises the following steps:
constructing a vertical motion situation model of the aircraft, and dividing the vertical motion situation into a horizontal LEV, an ascending CLM and a descending DES (data encryption standard), namely
For any track point i, the vertical motion situation TRND thereofiComprises the following steps:
wherein VSiThe altitude change rate of the track point i is shown; VSUp,minAnd VSDown,minThe minimum vertical change rates of the rising situation and the falling situation respectively;
wherein, PAiThe pressure height of the ith track point is shown; TIMEiA timestamp of the ith track point;
digitizing the vertical movement situation:
wherein m is any positive number.
4. Civil aircraft flight phase identification method based on airborne data according to claim 3,
the method for correcting the divided vertical motion situation comprises the following steps:
dividing the vertical motion situation section according to a density clustering method, and correcting outliers and invalid situation sections in the vertical motion situation section, namely
For dataset D ═ x1,x2,…,xi,…,xNIn which xiIs the perpendicularity of track point iMovement situation TRNDiThe value of (1), δ is the local domain length, ε is a neighborhood distance threshold, η is a threshold of the number of points in the neighborhood of the core point, and ε is less than 2m and η is less than or equal to 2 δ, then the DBSCAN algorithm for local traversal is:
step S301, for any data point x in the data set DiIn the number of 2 δ +1 local area data sets L ═ xi-δ，…，xi+δInner calculation Manhattan distance function FManhattan(xi,xk) That is to say that,
FManhattan(xi,xk)＝|xk-xi|；
wherein k is i- δ, …, i + δ;
step S302, will satisfy FManhattan(xi,xk) All L-domain data points ≦ ε added to xiEpsilon neighborhood N ofε,iPerforming the following steps; if N is presentε,iIf the number of inner points is greater than or equal to eta, then xiMarked as a core point; otherwise xiIs marked as an outlier and x is marked asiAdding into the outlier O;
step S303, for the next data point xi+1Repeating step S301 and step S302 until the last data point xNFinishing the calculation;
step S304, for any core point j and its neighborhood Nε,jAnd performing connection judgment with other core points and neighborhoods thereof, if the core points are connected, combining the core points into a cluster, and forming a cluster set C ═ { C ═ C for all the core points1,C2,…,CM}, i.e. a set of posture segments;
step S305, correcting the outlier, changing the state of the outlier into the state of a preamble state section, and merging the outlier into the preamble state section; if the outlier does not have a preceding situation section, changing the situation of the outlier into the situation of a subsequent situation section, and merging the outlier into the subsequent situation section; when a plurality of continuous outliers exist, correcting each outlier one by one;
step S306, the shortest duration T of the effective situationmin,segWhen a vertical motion situation is shorter in duration than Tmin,segThen, mark as noneThe effective situation section modifies the ineffective situation section, changes the situation of the ineffective situation section into the situation of the preorder situation section, and merges the ineffective situation section into the preorder situation section; if the invalid situation section has no preceding situation section, the situation of the invalid situation section is changed into the situation of a subsequent situation section, and the invalid situation section is merged into the subsequent situation section.
5. The civil aircraft flight phase identification method based on airborne data according to claim 4,
the method for dividing the flight phases according to the vertical motion situation comprises the following steps:
the flight phases are divided into the following phases according to the vertical motion situation and the pneumatic configuration change: roll-off, take-off, initial climb, cruise, descent, approach, landing cancel, missed climb, and roll-in.
6. The civil aircraft flight phase identification method based on airborne data according to claim 5,
the method for constructing the flight state characteristic model according to the characteristics of the flight phase comprises the following steps:
switching POS depending on flap positionFlapSurface ground speed limit GSTaxi,maxAnd acquiring six aircraft flight state characteristics CHR according to the characteristics of each flight stage by the states of the landing gear position LDG _ SELDW and the vertical movement situation TRND:
the first aircraft flight state characteristic and the second aircraft flight state characteristic are low-speed and high-speed motion states of the aircraft when the aircraft puts down an undercarriage, and respectively correspond to two flight stages of scene sliding and high-speed sliding;
the flight state characteristics of the aircraft are three, four and five, the flight states of the aircraft under different vertical motion situations when the aircraft landing gear is put on and the flaps are simultaneously released, and the flight states correspond to initial climbing after takeoff, approach before landing and missed approach climbing after landing cancellation;
the flight state characteristic six of the aircraft is the flight state of the aircraft in a smooth configuration and corresponds to three flight stages of climbing, cruising and descending on a navigation path;
and carrying out flight state characteristic classification on each preprocessed QAR track point so as to merge and divide continuous flight characteristic points into a plurality of flight characteristic segments.
7. The civil aircraft flight phase identification method based on airborne data according to claim 6,
the method for dividing the flight phases according to the preprocessed flight path and the corrected vertical motion situation comprises the following steps:
each flight phase is provided with one or more flight state characteristic segments, three flight phases of takeoff, landing and landing cancellation are divided firstly, then the rest non-smooth configuration flight phases are divided according to the front-back relation of the adjacent flight characteristic segments, the smooth configuration flight phases are divided according to the flight state characteristic six of the aircraft and the corrected vertical motion situation, and finally the plurality of subsections of the flight phases obtained after division are combined to obtain the rest flight phases so as to finish the division of the flight phases of the aircraft.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011122311.7A CN112257152A (en) | 2020-10-20 | 2020-10-20 | Civil aircraft flight phase identification method based on airborne data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011122311.7A CN112257152A (en) | 2020-10-20 | 2020-10-20 | Civil aircraft flight phase identification method based on airborne data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112257152A true CN112257152A (en) | 2021-01-22 |
Family
ID=74245566
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011122311.7A Withdrawn CN112257152A (en) | 2020-10-20 | 2020-10-20 | Civil aircraft flight phase identification method based on airborne data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112257152A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112749764A (en) * | 2021-01-28 | 2021-05-04 | 厦门大学 | Aeroengine running state classification method based on QAR data |
| CN113033621A (en) * | 2021-03-05 | 2021-06-25 | 南京航空航天大学 | Method for identifying unstable approach and inducement thereof of civil aircraft |
| CN113093794A (en) * | 2021-03-29 | 2021-07-09 | 西北工业大学 | Multimode accurate partitioning method for wide-area flight |
| EP4163750A1 (en) * | 2021-10-11 | 2023-04-12 | Leonardo S.p.a. | Method and system for detecting flight regimes of an aircraft, on the basis of measurements acquired during an aircraft flight |
| WO2023087717A1 (en) * | 2021-11-18 | 2023-05-25 | 中国电子科技集团公司第二十八研究所 | Method for determining transition altitude elements in flight climbing stage on basis of constant-value segment identification |
| CN117972454A (en) * | 2023-12-26 | 2024-05-03 | 中国人民解放军海军航空大学 | VMSD-TICC-based flight phase division method and division terminal |
| CN118332445A (en) * | 2024-06-14 | 2024-07-12 | 西安理工大学 | Automatic aircraft action recognition method and system based on threshold value |
-
2020
- 2020-10-20 CN CN202011122311.7A patent/CN112257152A/en not_active Withdrawn
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112749764A (en) * | 2021-01-28 | 2021-05-04 | 厦门大学 | Aeroengine running state classification method based on QAR data |
| CN113033621A (en) * | 2021-03-05 | 2021-06-25 | 南京航空航天大学 | Method for identifying unstable approach and inducement thereof of civil aircraft |
| CN113033621B (en) * | 2021-03-05 | 2022-01-18 | 南京航空航天大学 | Method for identifying unstable approach and inducement thereof of civil aircraft |
| CN113093794A (en) * | 2021-03-29 | 2021-07-09 | 西北工业大学 | Multimode accurate partitioning method for wide-area flight |
| EP4163750A1 (en) * | 2021-10-11 | 2023-04-12 | Leonardo S.p.a. | Method and system for detecting flight regimes of an aircraft, on the basis of measurements acquired during an aircraft flight |
| WO2023062519A1 (en) * | 2021-10-11 | 2023-04-20 | Leonardo S.P.A. | Method and system for detecting flight regimes of an aircraft, on the basis of measurements acquired during an aircraft flight |
| WO2023087717A1 (en) * | 2021-11-18 | 2023-05-25 | 中国电子科技集团公司第二十八研究所 | Method for determining transition altitude elements in flight climbing stage on basis of constant-value segment identification |
| CN117972454A (en) * | 2023-12-26 | 2024-05-03 | 中国人民解放军海军航空大学 | VMSD-TICC-based flight phase division method and division terminal |
| CN118332445A (en) * | 2024-06-14 | 2024-07-12 | 西安理工大学 | Automatic aircraft action recognition method and system based on threshold value |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112257152A (en) | Civil aircraft flight phase identification method based on airborne data | |
| CN112257151A (en) | Aircraft flight staging identification system | |
| CN107862910B (en) | Method for predicting taxi delay time and departure delay time based on airport scene taxi multiple conflict modes | |
| CN110852497A (en) | Scene variable slide-out time prediction system based on big data deep learning | |
| Lv et al. | A novel method of overrun risk measurement and assessment using large scale QAR data | |
| CN106846920A (en) | A kind of blank pipe aid decision-making method based on nature extraction of semantics | |
| CN113610282A (en) | Flight taxi time prediction method | |
| Mirmohammadsadeghi et al. | Enhancements to the runway capacity simulation model using the asde-x data for estimating airports throughput under various wake separation systems | |
| Galagedera et al. | Evaluation of operational risk factors at runway high speed exits | |
| CN113033621B (en) | Method for identifying unstable approach and inducement thereof of civil aircraft | |
| Wang et al. | Airspace risk management using surveillance track data: Stabilized approaches | |
| Salgueiro et al. | Aircraft Takeoff and Landing Weight Estimation from Surveillance Data | |
| CN114692290A (en) | Improved FRAM (FRAM) method-based airplane landing safety quality analysis method | |
| CN112793797A (en) | Early warning method and system for landing bounce of airplane | |
| CN113435051A (en) | Airport scene distributed operation simulation method and system based on operation rules | |
| CN117972454A (en) | VMSD-TICC-based flight phase division method and division terminal | |
| CN106651220B (en) | Pilot operation quality evaluation method based on curve fitting | |
| CN111967676A (en) | Method and system for predicting risk of aircraft tail rubbing during takeoff based on stepwise regression | |
| CN117953731A (en) | Incoming flight flow flight plan prediction method for terminal area traffic simulation | |
| CN116415818B (en) | Method and system for confirming risk points in aircraft approach stage based on clustering algorithm | |
| CN102521901A (en) | Method for automatically estimating and realizing flight quality of pilots | |
| Hu et al. | Runway occupancy time constraint and runway throughput estimation under reduced arrival wake separation rules | |
| Fala et al. | Study on machine learning methods for general aviation flight phase identification | |
| Mirmohammadsadeghi et al. | Prediction of runway occupancy time and runway exit distance with feedforward neural networks | |
| Hook et al. | How digital safety systems could revolutionize aviation safety |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210122 |
|
| WW01 | Invention patent application withdrawn after publication |