CN107808552B - Flight behavior detection method and device - Google Patents
Flight behavior detection method and device Download PDFInfo
- Publication number
- CN107808552B CN107808552B CN201711053273.2A CN201711053273A CN107808552B CN 107808552 B CN107808552 B CN 107808552B CN 201711053273 A CN201711053273 A CN 201711053273A CN 107808552 B CN107808552 B CN 107808552B
- Authority
- CN
- China
- Prior art keywords
- flight
- real
- time
- data
- civil
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft
- G08G5/70—Arrangements for monitoring traffic-related situations or conditions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G5/00—Traffic control systems for aircraft
- G08G5/50—Navigation or guidance aids
- G08G5/56—Navigation or guidance aids for two or more aircraft
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
- Navigation (AREA)
Abstract
The invention provides a flight behavior detection method and a flight behavior detection device, wherein the method comprises the following steps: acquiring real-time flight track data of a civil aircraft; and detecting the special behavior of the civil aircraft according to the real-time flight track data. The invention solves the technical problem of low user experience caused by the fact that the flight delay condition cannot be known in advance effectively in the prior art, and achieves the technical effect of improving the user experience.
Description
Technical Field
The invention relates to the technical field of aviation, in particular to a flight behavior detection method and device.
Background
As a common vehicle, an airplane has a much higher degree of freedom in air flight than that of land traffic, and the time associated with a civil airplane is often more discrete and difficult to predict than the time distribution of land traffic. However, for the security personnel, the pick-up robots, at the airport, a prediction of the flight related time (especially the arrival time of the flight in flight) is necessary.
In the related research of time prediction, it is often difficult to predict abnormal flights (especially, flights that are going to land and returning to the home). When a flight takes preparation for landing and return voyage, the flight needs to temporarily land at an airport different from the original destination, which not only requires a new destination airport to temporarily adjust the allocation of resources such as parking positions, support personnel and the like, but also influences the plans of passengers, aircrafts and the like, so that the earlier confirmation of the special behavior is better.
In practical situations, the airport can be confirmed by an empty management command, but the empty management command changes occasionally, and the complete accuracy cannot be guaranteed in consideration of the error rate of personnel operation. However, it is difficult for the receiver at the original destination to be notified in advance, and a general APP with flight dynamics will trigger the update of the state only when the flight has fallen to the airport.
Aiming at the problem that the related time of an abnormal flight cannot be predicted in advance, an effective solution is not provided at present.
Disclosure of Invention
The embodiment of the invention provides a flight behavior detection method, which aims to achieve the purposes of determining flight abnormal behaviors in real time and processing the abnormal behaviors in time so as to improve user experience and comprises the following steps:
acquiring real-time flight track data of a civil aircraft;
and detecting the special behavior of the civil aircraft according to the real-time flight track data.
In one embodiment, the special behavior comprises at least one of: yawing, standby landing, returning and hovering.
In one embodiment, the real-time flight trajectory data includes at least one of: time, latitude, longitude, and altitude.
In one embodiment, acquiring real-time flight trajectory data of a civil aircraft comprises: acquiring real-time flight track data and air traffic control message data of the civil aircraft, wherein the air traffic control message data comprises at least one of the following data: flight number, departure airport code, destination airport code, landing airport information, return flight information.
In one embodiment, before acquiring real-time flight trajectory data of a civil aircraft, the method further comprises:
acquiring historical track data of flights corresponding to the civil aviation passenger plane;
and mining the historical track data to determine one or more conventional navigation routes corresponding to the flight.
In one embodiment, mining the historical trajectory data to determine one or more conventional voyage routes corresponding to the flight includes:
discretizing the data of the historical track data;
after discretization, carrying out deduplication operation on adjacent data points falling into the same grid to obtain one or more conventional navigation routes, wherein the data point of one grid corresponds to one longitude and latitude position.
In one embodiment, detecting a special behavior of the civil aircraft based on the real-time flight trajectory data comprises:
and comparing the real-time flight track route with the conventional navigation route to determine whether the civil aircraft drifts.
In one embodiment, detecting a special behavior of the civil aircraft based on the real-time flight trajectory data comprises:
after determining that the civil aircraft has a yawing condition, determining the position of the civil aircraft;
determining a plurality of predetermined airports nearest to the position of the civil aircraft, or determining a plurality of predetermined airports with the largest historical landing times in the route of the civil aircraft;
and taking the determined plurality of airports as landing airports of the civil aircraft.
In one embodiment, detecting a special behavior of the civil aircraft based on the real-time flight trajectory data comprises:
determining a first point and a last point of a flight track in a preset time window according to the real-time flight track data;
calculating the longitude and latitude distance between the first point and a departure airport and an arrival airport;
calculating the longitude and latitude distance between the last point and the departure airport and the arrival airport;
and when the distance between the flight and the departure airport is reduced and the distance between the flight and the destination airport is increased in the preset time window, determining that the civil aircraft is hovering.
The embodiment of the invention also provides a flight behavior detection device, which is used for achieving the purposes of determining flight abnormal behaviors in real time and processing the abnormal behaviors in time so as to improve the user experience, and comprises the following steps:
the first acquisition module is used for acquiring real-time flight track data of the civil aircraft;
and the detection module is used for detecting the special behavior of the civil aviation passenger plane according to the real-time flight track data.
In one embodiment, the special behavior comprises at least one of: yawing, standby landing, returning and hovering.
In one embodiment, the real-time flight trajectory data includes at least one of: time, latitude, longitude, and altitude.
In an embodiment, the first obtaining module is specifically configured to obtain real-time flight trajectory data and air traffic control message data of the civil aircraft, where the air traffic control message data includes at least one of: flight number, departure airport code, destination airport code, landing airport information, return flight information.
In one embodiment, the above apparatus further comprises: the second acquisition module is used for acquiring historical track data of flights corresponding to the civil aircraft before acquiring real-time flight track data of the civil aircraft;
and the determining module is used for mining the historical track data and determining one or more conventional navigation routes corresponding to the flight.
In one embodiment, the determining module comprises:
the discretization unit is used for discretizing the data of the historical track data;
and the duplication removing unit is used for carrying out duplication removing operation on adjacent data points falling into the same grid after discretization processing to obtain one or more conventional navigation routes, wherein the data point of one grid corresponds to one longitude and latitude position.
In one embodiment, the detection module is specifically configured to compare the real-time flight trajectory route with the regular flight route to determine whether the civil aircraft is yawing.
In one embodiment, the detection module comprises: the first determining unit is used for determining the position of the civil aircraft after determining that the civil aircraft has a yawing condition; the second determining unit is used for determining a plurality of predetermined airports nearest to the position of the civil aircraft, or determining a plurality of predetermined airports with the largest historical number of landing preparation times in the route of the civil aircraft; and the generating unit is used for taking the determined plurality of airports as landing airports of the civil aircraft.
In one embodiment, the detection module comprises: the third determining unit is used for determining a first point and a last point of the flight track in a preset time window according to the real-time flight track data; the first calculating unit is used for calculating the longitude and latitude distance between the first point and a departure airport and between the first point and an arrival airport; the second calculation unit is used for calculating the longitude and latitude distance between the last point and the departure airport and the arrival airport; and the fourth determination unit is used for determining that the civil aircraft is hovering when the distance between the flight and the departure airport is reduced and the distance between the flight and the destination airport is increased in the preset time window.
In the embodiment of the invention, real-time flight track data of a civil aircraft are obtained; according to the real-time flight track data, the special behaviors of the civil aviation passenger plane are detected, and the abnormal behaviors of the flight can be found in time in the above mode, so that the possible delay condition of the flight can be determined in advance, the technical problem that the user experience is low due to the fact that the existing flight delay condition cannot be known effectively in advance is solved, and the technical effect of improving the user experience is achieved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the principles of the invention. In the drawings:
fig. 1 is a method flow diagram of a flight activity detection method according to an embodiment of the invention;
FIG. 2 is a schematic diagram of a conventional route according to an embodiment of the present invention;
fig. 3 is a block diagram of a flight behavior detection apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the following embodiments and accompanying drawings. The exemplary embodiments and descriptions of the present invention are provided to explain the present invention, but not to limit the present invention.
An embodiment of the present invention provides a flight behavior detection method, as shown in fig. 1, which may include the following steps:
s101: acquiring real-time flight track data of a civil aircraft;
wherein the real-time flight trajectory data may include, but is not limited to, at least one of: time, latitude, longitude, and altitude.
S102: and detecting the special behavior of the civil aircraft according to the real-time flight track data.
Wherein the special behavior may include, but is not limited to, at least one of: yawing, standby landing, returning and hovering.
In order to determine the abnormal behavior of the flight, the abnormal behavior of the flight can be determined according to the real-time flight trajectory data, and the abnormal behavior of the flight can be determined by combining the air traffic control message data and the like, so that the judgment is more comprehensive. The empty pipe message data may include, but is not limited to, at least one of the following: flight number, departure airport code, destination airport code, landing airport information, return flight information.
Considering that the abnormality and the normality are a relative concept, in order to determine whether there is an abnormality, a route corresponding to a normal flight can be determined first, and after comparison, the flight abnormality can be determined. Therefore, before acquiring real-time flight track data of the civil aircraft, historical track data of flights corresponding to the civil aircraft can be acquired; and mining the historical track data to determine one or more conventional navigation routes corresponding to the flight.
Specifically, mining the historical trajectory data to determine one or more conventional flight routes corresponding to the flight may include: discretizing the data of the historical track data; after discretization, carrying out deduplication operation on adjacent data points falling into the same grid to obtain one or more conventional navigation routes, wherein the data point of one grid corresponds to one longitude and latitude position.
Correspondingly, detecting the special behavior of the civil aircraft according to the real-time flight trajectory data may include: and comparing the real-time flight track route with the conventional navigation route to determine whether the civil aircraft drifts.
Aiming at a possible standby landing situation, after determining that the civil aircraft has a yaw situation, determining the position of the civil aircraft; determining a plurality of predetermined airports nearest to the position of the civil aircraft, or determining a plurality of predetermined airports with the largest historical landing times in the route of the civil aircraft; the determined number of airports may be taken as reserve airports for the civil aircraft.
The determination of whether the flight is hovering can be made as follows:
s1: determining a first point and a last point of a flight track in a preset time window according to the real-time flight track data;
s2: calculating the longitude and latitude distance between the first point and a departure airport and an arrival airport;
s3: calculating the longitude and latitude distance between the last point and the departure airport and the arrival airport;
s4: and when the distance between the flight and the departure airport is reduced and the distance between the flight and the destination airport is increased in the preset time window, determining that the civil aircraft is hovering.
The above flight behavior detection method is described below with reference to a specific embodiment, but it should be noted that the specific embodiment is only for better describing the present application and is not to be construed as a limitation of the present application.
In this example, a real-time detection method for flight special behaviors is proposed for special behaviors of a civil aircraft such as yawing, standby landing, returning, hovering and the like, and based on data which is relatively easy to obtain: the position information (namely, real-time flight track) of the civil aviation passenger plane is deployed in a streaming data calculation mode by taking offline mining of a conventional route of the civil aviation as a starting point, so that the whole-process monitoring of flights flying in a civil aviation airspace is realized. The track mining technology is applied to civil aviation business to analyze flight tracks of flights, and real-time position data of the flights are processed by using streaming calculation to ensure the real-time performance of detection.
Specifically, the special behavior in the flight process is detected by utilizing the real-time track of the civil aircraft. Wherein the special behavior may include: yaw, standby descent, return journey, hover and the like. By detecting the special behaviors in real time and informing an external system in time, the purposes of enriching flight states and improving the accuracy of a time-related prediction system can be achieved, and further the production efficiency of an airport and the travel experience of common passengers and pick-up robots are improved.
The data used may include: flight trajectory data, air traffic control standby message and return message. The flight trajectory data may include: the time, longitude and latitude, altitude, and other real-time states of the aircraft, the air traffic control message may include: flight number, planned departure/destination airport code, drop-off/return destination, etc.
Based on the above data, the following can be performed:
1) discretizing expression of civil aviation routes and mining conventional routes;
2) detecting the yawing behavior of the flight in real time based on the conventional route;
3) by dividing a two-dimensional space and some geometric calculations, detecting the standby landing and return voyage behaviors of flights in real time, and verifying standby landing and return voyage messages of air pipes in real time;
4) and detecting the flight circling behavior in real time, and predicting the returning flight time of the circling flight within a certain error range.
Besides the step 1) of off-line mining of historical data, the steps 2), 3) and 4) are calculated in real time, and the requirements of clients such as airlines, airports, ordinary passengers and the like for acquiring flight information in real time can be met.
In this example, the processing of the data may be MapReduce distributed processing by using Spark and python, etc., the real-time computing platform uses Spark Streaming framework, and respectively receives and transmits the real-time data through Kafka and ActiveMQ message queues, and Redis used to implement necessary data caching and system decoupling.
The calculation mode of the real-time data may be: streaming data is collected on a time window basis, i.e., location data for all air flights in the past few minutes is collected and processed every minute.
The following is a detailed description of the several schemes described above:
1) discretization expression of civil aviation route and conventional route mining
The navigation route of a civil aircraft can be determined by static navigation points, the navigation route of a flight between two airports is basically determined in a two-dimensional longitude and latitude space, and the width of the navigation route generally does not exceed 20 kilometers. Based on the above, under the condition that the navigation point data is unknown, the flight historical track data can be used for mining the conventional route, and the flight historical track data is used as a basis for measuring whether the flight normally navigates.
The inherent width of the conventional route is considered, the precision of the latitude and longitude data can be reduced, and 1-bit or 2-bit effective numbers of the latitude and longitude data are taken, so that the data volume is reduced on the premise of not influencing the expression of the route. The method is similar to the gridding of longitude and latitude space, the position points falling on one grid are represented by the grid, and the discretization expression of the air route is realized through the gridding method.
Specifically, the trajectory data of the normal (non-standby, return and cancel) flights of each route in history can be collected, discretization is carried out on the data, and after discretization, the duplicate removal operation is carried out on adjacent data points falling into the same grid, so that the simplified historical route is obtained. Of course, there may be multiple conventional routes for the same airline. As shown in fig. 2, the trajectories of all normal flights on a certain day of the Chongqing-Wulu-Timeqin airline are shown, and it is obvious that the same airline has a plurality of conventional routes. Intuitively, the proportion of the coincident points of the discrete routes is lower than a certain threshold value, and then the two different routes can be judged. LCS (longest common subsequence) distance can be adopted to depict the distance between different routes, the calculated LCS distance between every two routes is applied to a DB-SCAN clustering algorithm, and a plurality of historical routes on each route are clustered to obtain any conventional route of any route.
2) Flight yaw real-time detection
Yaw is one of the typical abnormal behaviors of the flight, and the yaw behavior of the flight can be detected in real time based on the mined static conventional route.
For example, the position data of the past 3 minutes can be collected every minute, first, the data points are collected according to flight shifts (for example, date-flight number-departure place-arrival place) through the combinanebykey function of Spark Streaming to obtain map type data with the shift as the main key and the position point array of the flight in the current time window as the value, and then, the position data points of each shift are sorted according to time in sequence and are sampled.
After the sampling process, each sampling point can be searched for the closest point in different static routes, and the distance between the sampling point and the closest point in the latitude and longitude space can be calculated: dist _ nearest _ grid, so that it can be located to which static route the current flight is in, and it can be determined whether the current flight has drifted or not by means of the magnitude relation between the preset threshold value and the distance.
Further, according to the variation trend of dist _ nearest _ grid of each sampling point in the current time window, defining more complex flight behavior: if the distance is always at a small level, the flight is considered normal, the flight is yawing when changing from a low level to a high level, the flight is returning to a regular route when changing from the high level to the low level, and the flight is yawing when changing from the high level to the low level.
Since the calculation based on the time window is performed every minute, the calculation of the subsequent time window often requires the use of the state before the current shift, and for this reason, the buffering of the state may be performed using Redis. For the flight in the state of yaw, abnormal behaviors such as backing off, return voyage and the like are more likely to occur than the flight in normal voyage.
3) Flight standby landing/return voyage real-time detection and air traffic control standby landing/return voyage message real-time verification
The preparation and return of flights are also common abnormal behaviors of flights. Based on the real-time position data of the flight, the longitude and latitude when the altitude just falls to 0 can be used for judging which airport the current flight actually falls to, however, the time for the solution to draw a conclusion is too late, and the information delay is not acceptable for the landing airport for guaranteeing the landing airplane or the user who prepares to pick up the airplane at the original destination.
In consideration of the problem, the real-time detection of flight descent preparation and return voyage is provided in the embodiment, and whether the flight descent preparation and return voyage are needed or not is judged as early as possible in the process of flight. In addition, due to the random factors such as the change of personnel operation, weather, airports and the like at any time, false alarm happens to the standby landing and return flight messages of the air traffic control, and the real-time verification of the standby landing and return flight messages of the air traffic control is realized by combining the real-time detection mode of the position information of the flight.
The method can be realized by dividing a two-dimensional longitude and latitude space by using a kd tree algorithm, and can find n airports nearest to the current point in constant time to serve as candidate landing places for any point in the given space, and also can select n airports with the most landing in the history of the current route to serve as the candidate landing places for the most landing on the basis of the historical landing statistical data of the current route. For the flights receiving the message of standby landing and return flight management, the candidate standby landing parts only need to consider the given airport in the message.
In this example, flight trajectory data of the past three minutes can be collected every minute, collected and sampled according to the number of shifts, and then the reserve landing and return voyage of the flight are determined according to preset rules:
1) receiving a standby landing return message of an air traffic control, wherein an included angle cos value between a vector formed by a last first point and a last point in a time window and a standby landing point in a first point pointing message is greater than a threshold (for example: the threshold is 0.95);
2) receiving a standby landing return message of an air traffic control, wherein the height difference and the horizontal distance relative to the standby landing place in the message are both smaller than a threshold (for example, the threshold is height 1000 meters, and the horizontal longitude and latitude are 100 kilometers), and the height difference and the distance meet a certain condition (horizontal distance (meters)/height difference is greater than 9);
3) the empty management message is not received, but the spare land with height difference and horizontal distance meeting the judgment conditions in the step 2) exists in the candidate land to be landed list determined by the geographic position and the historical data.
The method 1) can greatly advance the judgment time of the landing and the return voyage by selecting the landing place, the effective ratio is far greater than that of the methods 2) and 3), the methods 2) and 3) are relatively late, the method belongs to a cautious strategy, and the recall rate of the whole scheme can be improved.
The temporary state of the flight generated by the standby landing and the return voyage can be cached by using redis, and in addition, the judgment result can be informed to an external system through a message queue to trigger the calculation of the external system.
4) Flight hover real-time detection
The hovering behavior of the flight can seriously affect the accuracy of prediction of the arrival time of the flight, and can affect the experience of airports and passengers, and the hovering behavior can be detected in real time as follows:
by observing the normal flight course, a vector pointing from the departure place to the destination is assumed, and the projection points of the whole route point on the vector in time sequence are always pointed to the destination from the departure place except for the fixed routes around the departure and arrival airports. Then, according to this characteristic, a method for effectively detecting hovering is proposed in this example, specifically, based on a time window, the distance between the departure airport and the destination airport is calculated for the first point and the last point of the track within the time window, and the distance between the first point and the last point of the track and the latitude and longitude of the departure airport and the latitude and longitude of the arrival airport are calculated respectively, and when the distance between the flight within a certain time window and the departure airport is reduced and the distance between the flight and the destination airport is increased, it can be determined that the current flight is hovering.
The hover recovery time can also be predicted because the recovery time for hover activity will severely impact the arrival time of the flight. The direction change can be calculated through adjacent data points in the time window, the point with the first direction larger than the angle threshold value can be used as the time and the position for starting to circle, the circle track is extracted according to the time and the position, the circle track is used for fitting the circle in the latitude and longitude space, the circle center and the radius of the circle are obtained, the recovery time can be predicted by using the current speed, and if the predicted circle result is a circle and is approximate to the circle, the predicted result can be considered to be accurate.
For the circle obtained by fitting, if the radius is too large, the circle usually indicates that the original route returns, but the recovery time cannot be predicted, and the circle has a certain return probability but cannot be used as a judgment rule.
In the above example, a gridding technique is used to discretize track points in a two-dimensional plane to represent a navigation route of an aircraft, then a track distance is described by an LCS distance, and then a clustering algorithm is used to mine a conventional route. Further, based on the streaming data of the flight trajectory, flight yawing, standby landing, returning and hovering behaviors are detected in real time in a time window; and judging the flight reserve landing and return voyage behaviors according to the information such as the real-time position, the flight direction, the horizontal distance with the reserve landing candidate place, the height difference and the like, and fitting to obtain the hover recovery time based on the geometric shape.
According to the method, sensitive data such as longitude and latitude information of navigation points are not needed, conventional routes of any routes can be excavated only by using historical track data, core data of airports and navigation departments are not used, special behaviors of flights can be detected in real time only by using position information of the flights, and the special behaviors are fed back to various systems of civil aviation and common passengers in time. The method can deduce the tendency of the flight to take the future and return to the journey as soon as possible without depending on the messages of taking the future and return to the journey of the air traffic control to a certain extent, and can verify the sent messages of the air traffic control, thereby improving the accuracy of the information. The method can provide information with extremely high real-time performance for an external system, and can be applied to various systems, such as: airport operations, flight arrival time prediction systems, and the like.
The above framework of Streaming data calculation is not limited to Spark Streaming, and Storm and the like can be adopted, the message queue is not limited to Kafka and ActiveMQ, RabbitMQ and the like can be adopted, and the cache system is not limited to Redis, and HBase and memcache and the like can be adopted. The path discretization in the above example can directly take 1-bit and 2-bit significant figures on the longitude and latitude values, and in practice, can map the longitude and latitude coordinates to actual distances, for example: kilometers, etc., and discretization of the path points can be realized similarly. Besides LCS, the distance between paths can also be edited in different measurement modes such as distance, Euclidean distance and the like, besides, the distance between paths and the similarity between paths are dual, the actual meaning of the description is the same, and other similarity measurement and distance measurement related to the paths can be conceived. The clustering algorithm is not limited to DB-SCAN, K-means, etc., and other algorithms can achieve the purpose. The selection of the various related threshold values can be selected and set according to actual conditions, and can be randomly selected according to needs on the premise of not changing an index algorithm. Any information of landing and return, for example: the operation data of each unit of the airline official network and civil aviation, the app used by the ordinary passengers and the like are similar to the nature of the air traffic control message in nature and can be used.
Based on the same inventive concept, an embodiment of the present invention further provides a flight behavior detection apparatus, as described in the following embodiments. Because the principle of the flight behavior detection device for solving the problem is similar to that of the flight behavior detection method, the implementation of the flight behavior detection device can refer to the implementation of the flight behavior detection method, and repeated details are not repeated. As used hereinafter, the term "unit" or "module" may be a combination of software and/or hardware that implements a predetermined function. Although the means described in the embodiments below are preferably implemented in software, an implementation in hardware, or a combination of software and hardware is also possible and contemplated. Fig. 3 is a block diagram of a flight behavior detection apparatus according to an embodiment of the present invention, and as shown in fig. 3, the flight behavior detection apparatus may include: a first acquisition module 301 and a detection module 302, the structure of which is described below.
The first acquisition module 301 is used for acquiring real-time flight trajectory data of the civil aircraft;
a detection module 302, configured to detect a special behavior of the civil aircraft according to the real-time flight trajectory data.
In one embodiment, the special behavior may include, but is not limited to, at least one of: yawing, standby landing, returning and hovering.
In one embodiment, the real-time flight trajectory data may include, but is not limited to, at least one of: time, latitude, longitude, and altitude.
In an embodiment, the first obtaining module 301 may be specifically configured to obtain real-time flight trajectory data and air traffic control message data of the civil aircraft, where the air traffic control message data may include, but is not limited to, at least one of the following: flight number, departure airport code, destination airport code, landing airport information, return flight information.
In one embodiment, the apparatus may further include: the second acquisition module is used for acquiring historical track data of flights corresponding to the civil aircraft before acquiring real-time flight track data of the civil aircraft; and the determining module is used for mining the historical track data and determining one or more conventional navigation routes corresponding to the flight.
In one embodiment, the determining module may include: the discretization unit is used for discretizing the data of the historical track data; and the duplication removing unit is used for carrying out duplication removing operation on adjacent data points falling into the same grid after discretization processing to obtain one or more conventional navigation routes, wherein the data point of one grid corresponds to one longitude and latitude position.
In one embodiment, the detection module 302 may be specifically configured to compare the real-time flight trajectory route with the regular flight route to determine whether the civil aircraft is yawing.
In one embodiment, the detection module 302 may include: the first determining unit is used for determining the position of the civil aircraft after determining that the civil aircraft has a yawing condition; the second determining unit is used for determining a plurality of predetermined airports nearest to the position of the civil aircraft, or determining a plurality of predetermined airports with the largest historical number of landing preparation times in the route of the civil aircraft; and the generating unit is used for taking the determined plurality of airports as landing airports of the civil aircraft.
In one embodiment, the detection module 302 may include: the third determining unit is used for determining a first point and a last point of the flight track in a preset time window according to the real-time flight track data; the first calculating unit is used for calculating the longitude and latitude distance between the first point and a departure airport and between the first point and an arrival airport; the second calculation unit is used for calculating the longitude and latitude distance between the last point and the departure airport and the arrival airport; and the fourth determination unit is used for determining that the civil aircraft is hovering when the distance between the flight and the departure airport is reduced and the distance between the flight and the destination airport is increased in the preset time window.
In another embodiment, a software is provided, which is used to execute the technical solutions described in the above embodiments and preferred embodiments.
In another embodiment, a storage medium is provided, in which the software is stored, and the storage medium includes but is not limited to: optical disks, floppy disks, hard disks, erasable memory, etc.
From the above description, it can be seen that the embodiments of the present invention achieve the following technical effects: acquiring real-time flight track data of a civil aircraft; according to the real-time flight track data, the special behaviors of the civil aviation passenger plane are detected, and the abnormal behaviors of the flight can be found in time in the above mode, so that the possible delay condition of the flight can be determined in advance, the technical problem that the user experience is low due to the fact that the existing flight delay condition cannot be known effectively in advance is solved, and the technical effect of improving the user experience is achieved.
It will be apparent to those skilled in the art that the modules or steps of the embodiments of the invention described above may be implemented by a general purpose computing device, they may be centralized on a single computing device or distributed across a network of multiple computing devices, and alternatively, they may be implemented by program code executable by a computing device, such that they may be stored in a storage device and executed by a computing device, and in some cases, the steps shown or described may be performed in an order different than that described herein, or they may be separately fabricated into individual integrated circuit modules, or multiple ones of them may be fabricated into a single integrated circuit module. Thus, embodiments of the invention are not limited to any specific combination of hardware and software.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and various modifications and changes may be made to the embodiment of the present invention by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (14)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711053273.2A CN107808552B (en) | 2017-10-27 | 2017-10-27 | Flight behavior detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711053273.2A CN107808552B (en) | 2017-10-27 | 2017-10-27 | Flight behavior detection method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107808552A CN107808552A (en) | 2018-03-16 |
| CN107808552B true CN107808552B (en) | 2020-04-21 |
Family
ID=61591554
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711053273.2A Active CN107808552B (en) | 2017-10-27 | 2017-10-27 | Flight behavior detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107808552B (en) |
Families Citing this family (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108648511A (en) * | 2018-06-29 | 2018-10-12 | 飞友科技有限公司 | A method of judging that Aircraft Air spirals based on ADS-B data |
| CN109903554A (en) * | 2019-02-21 | 2019-06-18 | 长安大学 | A Spark-based road network traffic operation analysis method |
| CN110009545B (en) * | 2019-03-19 | 2023-01-24 | 中国民航大学 | A parallel fusion method of flight location information based on multiple data sources |
| CN110379210B (en) * | 2019-07-30 | 2020-11-03 | 四川九洲空管科技有限责任公司 | Method and device for monitoring abnormal flight of civil aircraft |
| CN110751859B (en) * | 2019-10-17 | 2021-01-12 | 深圳市瑞达飞行科技有限公司 | Data processing method and device, computer system and readable storage medium |
| CN110827582A (en) * | 2019-10-25 | 2020-02-21 | 海南太美航空股份有限公司 | System and method for automatically acquiring flight landing point in emergency |
| CN110712765B (en) * | 2019-10-30 | 2021-06-18 | 北京航空航天大学 | A method for locating abnormal operation of aircraft based on operation sequence |
| CN111695050A (en) * | 2020-05-29 | 2020-09-22 | 飞友科技有限公司 | Airport position navigation method and flight service system based on user behaviors |
| CN112182133B (en) * | 2020-09-29 | 2022-02-15 | 南京北斗创新应用科技研究院有限公司 | AIS data-based ship loitering detection method |
| CN112348960B (en) * | 2020-11-27 | 2024-05-07 | 中国人民解放军空军工程大学 | A method for airspace conflict detection applicable to the global space range |
| CN113112876A (en) * | 2021-04-09 | 2021-07-13 | 河北师范大学 | A flight behavior detection method |
| CN113177097B (en) * | 2021-04-16 | 2023-07-25 | 江西航天鄱湖云科技有限公司 | Track start judging method based on attribute clustering and space-time constraint |
| CN114490788B (en) * | 2022-01-14 | 2025-12-19 | 山东航空股份有限公司 | Flight trajectory optimization method and system based on dynamic sampling |
| CN116052482B (en) * | 2023-04-03 | 2023-06-23 | 中航信移动科技有限公司 | Method, electronic device and storage medium for early warning of aircraft trajectory deviation |
| CN116363908B (en) * | 2023-06-02 | 2023-08-04 | 中航信移动科技有限公司 | Flight track yaw detection method, electronic equipment and storage medium |
| CN119249155B (en) * | 2024-12-04 | 2025-07-01 | 青岛民航凯亚系统集成有限公司 | Machine learning-based flight return drop identification method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101572019A (en) * | 2009-06-01 | 2009-11-04 | 民航数据通信有限责任公司 | Radar track fitting and statistical analysis device |
| CN102819966A (en) * | 2012-09-10 | 2012-12-12 | 南京航空航天大学 | Off-course flight passing time forecasting method based on radar tracks |
| CN104484717A (en) * | 2014-12-09 | 2015-04-01 | 中国航空工业集团公司第六三一研究所 | Onboard flight path prediction method based on current air route |
| CN105303896A (en) * | 2015-09-07 | 2016-02-03 | 合肥飞友网络科技有限公司 | Precise Prediction Method of Flight Estimated Arrival Time |
| US9569959B1 (en) * | 2012-10-02 | 2017-02-14 | Rockwell Collins, Inc. | Predictive analysis for threat detection |
| CN106651108A (en) * | 2016-10-25 | 2017-05-10 | 合肥飞友网络科技有限公司 | Method for scheduling airport vehicles according to flight information |
-
2017
- 2017-10-27 CN CN201711053273.2A patent/CN107808552B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101572019A (en) * | 2009-06-01 | 2009-11-04 | 民航数据通信有限责任公司 | Radar track fitting and statistical analysis device |
| CN102819966A (en) * | 2012-09-10 | 2012-12-12 | 南京航空航天大学 | Off-course flight passing time forecasting method based on radar tracks |
| US9569959B1 (en) * | 2012-10-02 | 2017-02-14 | Rockwell Collins, Inc. | Predictive analysis for threat detection |
| CN104484717A (en) * | 2014-12-09 | 2015-04-01 | 中国航空工业集团公司第六三一研究所 | Onboard flight path prediction method based on current air route |
| CN105303896A (en) * | 2015-09-07 | 2016-02-03 | 合肥飞友网络科技有限公司 | Precise Prediction Method of Flight Estimated Arrival Time |
| CN106651108A (en) * | 2016-10-25 | 2017-05-10 | 合肥飞友网络科技有限公司 | Method for scheduling airport vehicles according to flight information |
Non-Patent Citations (2)
| Title |
|---|
| Anomaly detection via a Gaussian Mixture Model for flight operation and safety monitoring;Lishuai Li Et al.;《Transportation Research Part C: Emerging Technologies》;20160210;第64卷;第45-57页 * |
| 空中交通流量统计预测技术研究;殷允楠;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20110615(第6期);第C031-160页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107808552A (en) | 2018-03-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107808552B (en) | Flight behavior detection method and device | |
| CN110992733B (en) | Online detection method and device for flight deviation from normal track behavior | |
| US9858822B1 (en) | Airspace activity tracking using unmanned aerial vehicles | |
| US11688291B2 (en) | Cockpit display systems and methods for displaying taxiing route on airport moving map | |
| US10678265B2 (en) | Revised speed advisory for an aircraft during flight based on holding time | |
| US8774989B1 (en) | Aircraft energy state display | |
| Hamdi et al. | Drone-as-a-service composition under uncertainty | |
| EP3032518B1 (en) | Aircraft turns for interval managent | |
| Schultz et al. | Analysis of airport ground operations based on ADS-B data | |
| CN112396872B (en) | Airplane yaw judging method and device based on computer flight plan CFP data and storage medium | |
| CN106971634A (en) | A kind of spatial domain collision detection method predicted based on aircraft's flight track and system | |
| US10460608B2 (en) | System and method for determining uncertainty in a predicted flight path for an aerial vehicle | |
| US9377306B2 (en) | Device and method for prediction on the ground of characteristics of the position of an aircraft along a path | |
| US20080035784A1 (en) | Aircraft wake vortex predictor and visualizer | |
| CN117198095A (en) | A smart air travel distributed traffic management system | |
| CN112419792B (en) | Aircraft flight conflict detection method, system, device and medium | |
| US20230129613A1 (en) | Pilot flight path feedback tool | |
| FR3038751A1 (en) | METHOD FOR INTEGRATING A CONSTRAINED ROAD OPTIMIZATION APPLICATION IN AN OPEN ARCHITECTURE AIRCRAFT SYSTEM OF CLIENT-TYPE SERVER | |
| CN109598373A (en) | A kind of preprocess method for being used to predict flight arrival time based on ADS-B data | |
| CN117094424A (en) | Real-time aircraft flight delay prediction | |
| CN107544536B (en) | Method and system for performance-based reach and ordering and spacing | |
| Hrastovec et al. | Machine learning model for aircraft performances | |
| CN111912408B (en) | Method performed by an aircraft with a navigation device and navigation device for an aircraft | |
| Wang et al. | A flight trajectory prediction method based on trajectory clustering | |
| Lascara et al. | Measuring performance of initial Ground-based Interval Management–Spacing (GIM-S) operations |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: 100041 Room 1201, Building 1, Compound 1, No. 1 Tianshunzhuang North Road, Shijingshan District, Beijing Patentee after: AVIC Xin Mobile Technology Co.,Ltd. Country or region after: China Address before: 101318 No.7 Yumin Street, Houshayu Town, Shunyi District, Beijing Patentee before: ZHONGHANGXIN MOBILE TECHNOLOGY CO.,LTD. Country or region before: China |
|
| CP03 | Change of name, title or address |